* [PATCH 01/37] perf record: Encode -k clockid frequency into Perf trace
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
@ 2018-10-25 11:09 ` Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 02/37] perf annotate: Add Sparc support Arnaldo Carvalho de Melo
` (36 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:09 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Alexey Budankov,
Alexander Shishkin, Andi Kleen, Jiri Olsa, Namhyung Kim,
Peter Zijlstra, Arnaldo Carvalho de Melo
From: Alexey Budankov <alexey.budankov@linux.intel.com>
Store -k clockid frequency into Perf trace to enable timestamps
derived metrics conversion into wall clock time on reporting stage.
Below is the example of perf report output:
tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc
...
[ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ]
tools/perf/perf report --header
# ========
...
# event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4
...
# clockid frequency: 1000 MHz
...
# ========
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/23a4a1dc-b160-85a0-347d-40a2ed6d007b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 24 ++++++++++++++++++++++--
tools/perf/perf.h | 1 +
tools/perf/util/env.h | 1 +
| 23 +++++++++++++++++++++++
| 1 +
5 files changed, 48 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0980dfe3396b..10cf889c6d75 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -592,6 +592,9 @@ static void record__init_features(struct record *rec)
if (!rec->opts.full_auxtrace)
perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+ if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+ perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
perf_header__clear_feat(&session->header, HEADER_STAT);
}
@@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__init_features(rec);
+ if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+ session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
if (forks) {
err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
argv, data->is_pipe,
@@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = {
CLOCKID_END,
};
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+ struct timespec res;
+
+ *res_ns = 0;
+ if (!clock_getres(clk_id, &res))
+ *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+ else
+ pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+ return 0;
+}
+
static int parse_clockid(const struct option *opt, const char *str, int unset)
{
struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
/* if its a number, we're done */
if (sscanf(str, "%d", &opts->clockid) == 1)
- return 0;
+ return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
/* allow a "CLOCK_" prefix to the name */
if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
for (cm = clockids; cm->name; cm++) {
if (!strcasecmp(str, cm->name)) {
opts->clockid = cm->clockid;
- return 0;
+ return get_clockid_res(opts->clockid,
+ &opts->clockid_res_ns);
}
}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 21bf7f5a3cf5..0ed4a34c74c4 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -81,6 +81,7 @@ struct record_opts {
unsigned initial_delay;
bool use_clockid;
clockid_t clockid;
+ u64 clockid_res_ns;
unsigned int proc_map_timeout;
};
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc368530..d01b8355f4ca 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -63,6 +63,7 @@ struct perf_env {
struct numa_node *numa_nodes;
struct memory_node *memory_nodes;
unsigned long long memory_bsize;
+ u64 clockid_res_ns;
};
extern struct perf_env perf_env;
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1ec1d9bc2d63..4fd45be95a43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1034,6 +1034,13 @@ static int write_auxtrace(struct feat_fd *ff,
return err;
}
+static int write_clockid(struct feat_fd *ff,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ return do_write(ff, &ff->ph->env.clockid_res_ns,
+ sizeof(ff->ph->env.clockid_res_ns));
+}
+
static int cpu_cache_level__sort(const void *a, const void *b)
{
struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1508,6 +1515,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
fprintf(fp, "# Core ID and Socket ID information is not available\n");
}
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+ fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+ ff->ph->env.clockid_res_ns * 1000);
+}
+
static void free_event_desc(struct perf_evsel *events)
{
struct perf_evsel *evsel;
@@ -2531,6 +2544,15 @@ static int process_mem_topology(struct feat_fd *ff,
return ret;
}
+static int process_clockid(struct feat_fd *ff,
+ void *data __maybe_unused)
+{
+ if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+ return -1;
+
+ return 0;
+}
+
struct feature_ops {
int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2590,6 +2612,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPN(CACHE, cache, true),
FEAT_OPR(SAMPLE_TIME, sample_time, false),
FEAT_OPR(MEM_TOPOLOGY, mem_topology, true),
+ FEAT_OPR(CLOCKID, clockid, false)
};
struct header_print_data {
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e17903caa71d..0d553ddca0a3 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -38,6 +38,7 @@ enum {
HEADER_CACHE,
HEADER_SAMPLE_TIME,
HEADER_MEM_TOPOLOGY,
+ HEADER_CLOCKID,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 02/37] perf annotate: Add Sparc support
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 01/37] perf record: Encode -k clockid frequency into Perf trace Arnaldo Carvalho de Melo
@ 2018-10-25 11:09 ` Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 03/37] perf jitdump: " Arnaldo Carvalho de Melo
` (35 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:09 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, David Miller,
Arnaldo Carvalho de Melo
From: David Miller <davem@davemloft.net>
E.g.:
$ perf annotate --stdio2
Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887
__gettimeofday /lib32/libc-2.27.so [Percent: local period]
Percent│
│
│
│ Disassembly of section .text:
│
│ 000a6fa0 <__gettimeofday@@GLIBC_2.0>:
0.47 │ save %sp, -96, %sp
0.73 │ sethi %hi(0xe9000), %l7
│ → call __frame_state_for@@GLIBC_2.0+0x480
0.30 │ add %l7, 0x58, %l7 ! e9058 <nftw64@@GLIBC_2.3.3+0x818>
1.33 │ mov %i0, %o0
│ mov %i1, %o1
0.43 │ mov 0x74, %g1
│ ta 0x10
88.92 │ ↓ bcc 30
2.95 │ clr %g1
│ neg %o0
│ mov 1, %g1
0.31 │30: cmp %g1, 0
│ bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44>
│ mov %o0, %i0
1.96 │ ← return %i7 + 8
2.62 │ nop
│ sethi %hi(0), %g1
│ neg %o0, %g2
│ add %g1, 0x160, %g1
│ ld [ %l7 + %g1 ], %g1
│ st %g2, [ %g7 + %g1 ]
│ ← return %i7 + 8
│ mov -1, %o0
Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/sparc/annotate/instructions.c | 169 ++++++++++++++++++++++++++
tools/perf/util/annotate.c | 8 ++
2 files changed, 177 insertions(+)
create mode 100644 tools/perf/arch/sparc/annotate/instructions.c
diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c
new file mode 100644
index 000000000000..2614c010c235
--- /dev/null
+++ b/tools/perf/arch/sparc/annotate/instructions.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static int is_branch_cond(const char *cond)
+{
+ if (cond[0] == '\0')
+ return 1;
+
+ if (cond[0] == 'a' && cond[1] == '\0')
+ return 1;
+
+ if (cond[0] == 'c' &&
+ (cond[1] == 'c' || cond[1] == 's') &&
+ cond[2] == '\0')
+ return 1;
+
+ if (cond[0] == 'e' &&
+ (cond[1] == '\0' ||
+ (cond[1] == 'q' && cond[2] == '\0')))
+ return 1;
+
+ if (cond[0] == 'g' &&
+ (cond[1] == '\0' ||
+ (cond[1] == 't' && cond[2] == '\0') ||
+ (cond[1] == 'e' && cond[2] == '\0') ||
+ (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+ return 1;
+
+ if (cond[0] == 'l' &&
+ (cond[1] == '\0' ||
+ (cond[1] == 't' && cond[2] == '\0') ||
+ (cond[1] == 'u' && cond[2] == '\0') ||
+ (cond[1] == 'e' && cond[2] == '\0') ||
+ (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+ return 1;
+
+ if (cond[0] == 'n' &&
+ (cond[1] == '\0' ||
+ (cond[1] == 'e' && cond[2] == '\0') ||
+ (cond[1] == 'z' && cond[2] == '\0') ||
+ (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0')))
+ return 1;
+
+ if (cond[0] == 'b' &&
+ cond[1] == 'p' &&
+ cond[2] == 'o' &&
+ cond[3] == 's' &&
+ cond[4] == '\0')
+ return 1;
+
+ if (cond[0] == 'v' &&
+ (cond[1] == 'c' || cond[1] == 's') &&
+ cond[2] == '\0')
+ return 1;
+
+ if (cond[0] == 'b' &&
+ cond[1] == 'z' &&
+ cond[2] == '\0')
+ return 1;
+
+ return 0;
+}
+
+static int is_branch_reg_cond(const char *cond)
+{
+ if ((cond[0] == 'n' || cond[0] == 'l') &&
+ cond[1] == 'z' &&
+ cond[2] == '\0')
+ return 1;
+
+ if (cond[0] == 'z' &&
+ cond[1] == '\0')
+ return 1;
+
+ if ((cond[0] == 'g' || cond[0] == 'l') &&
+ cond[1] == 'e' &&
+ cond[2] == 'z' &&
+ cond[3] == '\0')
+ return 1;
+
+ if (cond[0] == 'g' &&
+ cond[1] == 'z' &&
+ cond[2] == '\0')
+ return 1;
+
+ return 0;
+}
+
+static int is_branch_float_cond(const char *cond)
+{
+ if (cond[0] == '\0')
+ return 1;
+
+ if ((cond[0] == 'a' || cond[0] == 'e' ||
+ cond[0] == 'z' || cond[0] == 'g' ||
+ cond[0] == 'l' || cond[0] == 'n' ||
+ cond[0] == 'o' || cond[0] == 'u') &&
+ cond[1] == '\0')
+ return 1;
+
+ if (((cond[0] == 'g' && cond[1] == 'e') ||
+ (cond[0] == 'l' && (cond[1] == 'e' ||
+ cond[1] == 'g')) ||
+ (cond[0] == 'n' && (cond[1] == 'e' ||
+ cond[1] == 'z')) ||
+ (cond[0] == 'u' && (cond[1] == 'e' ||
+ cond[1] == 'g' ||
+ cond[1] == 'l'))) &&
+ cond[2] == '\0')
+ return 1;
+
+ if (cond[0] == 'u' &&
+ (cond[1] == 'g' || cond[1] == 'l') &&
+ cond[2] == 'e' &&
+ cond[3] == '\0')
+ return 1;
+
+ return 0;
+}
+
+static struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+ struct ins_ops *ops = NULL;
+
+ if (!strcmp(name, "call") ||
+ !strcmp(name, "jmp") ||
+ !strcmp(name, "jmpl")) {
+ ops = &call_ops;
+ } else if (!strcmp(name, "ret") ||
+ !strcmp(name, "retl") ||
+ !strcmp(name, "return")) {
+ ops = &ret_ops;
+ } else if (!strcmp(name, "mov")) {
+ ops = &mov_ops;
+ } else {
+ if (name[0] == 'c' &&
+ (name[1] == 'w' || name[1] == 'x'))
+ name += 2;
+
+ if (name[0] == 'b') {
+ const char *cond = name + 1;
+
+ if (cond[0] == 'r') {
+ if (is_branch_reg_cond(cond + 1))
+ ops = &jump_ops;
+ } else if (is_branch_cond(cond)) {
+ ops = &jump_ops;
+ }
+ } else if (name[0] == 'f' && name[1] == 'b') {
+ if (is_branch_float_cond(name + 2))
+ ops = &jump_ops;
+ }
+ }
+
+ if (ops)
+ arch__associate_ins_ops(arch, name, ops);
+
+ return ops;
+}
+
+static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+ if (!arch->initialized) {
+ arch->initialized = true;
+ arch->associate_instruction_ops = sparc__associate_instruction_ops;
+ arch->objdump.comment_char = '#';
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a17491b..6936daf89ddd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -139,6 +139,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
#include "arch/x86/annotate/instructions.c"
#include "arch/powerpc/annotate/instructions.c"
#include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
static struct arch architectures[] = {
{
@@ -170,6 +171,13 @@ static struct arch architectures[] = {
.comment_char = '#',
},
},
+ {
+ .name = "sparc",
+ .init = sparc__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
};
static void ins__delete(struct ins_operands *ops)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 03/37] perf jitdump: Add Sparc support.
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 01/37] perf record: Encode -k clockid frequency into Perf trace Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 02/37] perf annotate: Add Sparc support Arnaldo Carvalho de Melo
@ 2018-10-25 11:09 ` Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 04/37] perf symbols: Set PLT entry/header sizes properly on Sparc Arnaldo Carvalho de Melo
` (34 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:09 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, David Miller,
Arnaldo Carvalho de Melo
From: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.211545.1487970139012324624.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/sparc/Makefile | 2 ++
tools/perf/util/genelf.h | 6 ++++++
2 files changed, 8 insertions(+)
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 7fbca175099e..275dea7ff59a 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,3 +1,5 @@
ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
+
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d51c7fe..b72440bf9a79 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,12 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
#elif defined(__powerpc__)
#define GEN_ELF_ARCH EM_PPC
#define GEN_ELF_CLASS ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH EM_SPARCV9
+#define GEN_ELF_CLASS ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH EM_SPARC
+#define GEN_ELF_CLASS ELFCLASS32
#else
#error "unsupported architecture"
#endif
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 04/37] perf symbols: Set PLT entry/header sizes properly on Sparc
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (2 preceding siblings ...)
2018-10-25 11:09 ` [PATCH 03/37] perf jitdump: " Arnaldo Carvalho de Melo
@ 2018-10-25 11:09 ` Arnaldo Carvalho de Melo
2018-10-25 11:09 ` [PATCH 05/37] perf arm64: Fix generate system call table failed with /tmp mounted with noexec Arnaldo Carvalho de Melo
` (33 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:09 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, David Miller,
Alexander Shishkin, Alexis Berlemont, David Tolnay, Hanjun Guo,
Hemant Kumar, Li Bin, Masami Hiramatsu, Milian Wolff,
Namhyung Kim, Peter Zijlstra, Wang Nan, zhangmengting,
Arnaldo Carvalho de Melo
From: David Miller <davem@davemloft.net>
Using the sh_entsize for both values isn't correct. It happens to be
correct on x86...
For both 32-bit and 64-bit sparc, there are four PLT entries in the PLT
section.
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: David Tolnay <dtolnay@gmail.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: zhangmengting@huawei.com
Fixes: b2f7605076d6 ("perf symbols: Fix plt entry calculation for ARM and AARCH64")
Link: http://lkml.kernel.org/r/20181017.120859.2268840244308635255.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/symbol-elf.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 29770ea61768..6e70cc00c161 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -324,7 +324,17 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
plt_entry_size = 16;
break;
- default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+ case EM_SPARC:
+ plt_header_size = 48;
+ plt_entry_size = 12;
+ break;
+
+ case EM_SPARCV9:
+ plt_header_size = 128;
+ plt_entry_size = 32;
+ break;
+
+ default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */
plt_header_size = shdr_plt.sh_entsize;
plt_entry_size = shdr_plt.sh_entsize;
break;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 05/37] perf arm64: Fix generate system call table failed with /tmp mounted with noexec
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (3 preceding siblings ...)
2018-10-25 11:09 ` [PATCH 04/37] perf symbols: Set PLT entry/header sizes properly on Sparc Arnaldo Carvalho de Melo
@ 2018-10-25 11:09 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 06/37] tools lib subcmd: Introduce OPTION_ULONG Arnaldo Carvalho de Melo
` (32 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:09 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Hongxu Jia,
Alexander Shishkin, Hendrik Brueckner, Jiri Olsa, Kim Phillips,
Michael Ellerman, Namhyung Kim, Peter Zijlstra, Ravi Bangoria,
Sébastien Boisvert, Thomas Richter,
Arnaldo Carvalho de Melo
From: Hongxu Jia <hongxu.jia@windriver.com>
When /tmp is mounted with noexec, mksyscalltbl fails.
[snip]
|perf-1.0/tools/perf/arch/arm64/entry/syscalls//mksyscalltbl:
/tmp/create-table-6VGPSt: Permission denied
[snip]
Add variable TMPDIR as prefix dir of the temporary file, if it is set,
replace default /tmp.
Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sébastien Boisvert <sboisvert@gydle.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Fixes: 2b5882435606 ("perf arm64: Generate system call table from asm/unistd.h")
LPU-Reference: 1539851173-14959-1-git-send-email-hongxu.jia@windriver.com
Link: https://lkml.kernel.org/n/tip-1qrgq840ci0c5cy4oww957ge@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 2dbb8cade048..c88fd32563eb 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -23,7 +23,7 @@ create_table_from_c()
{
local sc nr last_sc
- create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+ create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
{
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 06/37] tools lib subcmd: Introduce OPTION_ULONG
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (4 preceding siblings ...)
2018-10-25 11:09 ` [PATCH 05/37] perf arm64: Fix generate system call table failed with /tmp mounted with noexec Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 07/37] perf trace: Introduce --max-events Arnaldo Carvalho de Melo
` (31 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, Andi Kleen, David Ahern,
Jiri Olsa, Josh Poimboeuf, Kim Phillips, Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
For completeness, will be used in 'perf trace --max-events'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-glaj3pwespxfj2fdjs9a20b6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/subcmd/parse-options.c | 19 +++++++++++++++++++
tools/lib/subcmd/parse-options.h | 2 ++
2 files changed, 21 insertions(+)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index cb7154eccbdc..dbb9efbf718a 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -116,6 +116,7 @@ static int get_value(struct parse_opt_ctx_t *p,
case OPTION_INTEGER:
case OPTION_UINTEGER:
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
default:
break;
@@ -166,6 +167,7 @@ static int get_value(struct parse_opt_ctx_t *p,
case OPTION_INTEGER:
case OPTION_UINTEGER:
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
default:
break;
@@ -295,6 +297,22 @@ static int get_value(struct parse_opt_ctx_t *p,
return opterror(opt, "expects a numerical value", flags);
return 0;
+ case OPTION_ULONG:
+ if (unset) {
+ *(unsigned long *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(unsigned long *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ *(unsigned long *)opt->value = strtoul(arg, (char **)&s, 10);
+ if (*s)
+ return opterror(opt, "expects a numerical value", flags);
+ return 0;
+
case OPTION_U64:
if (unset) {
*(u64 *)opt->value = 0;
@@ -703,6 +721,7 @@ static void print_option_help(const struct option *opts, int full)
case OPTION_ARGUMENT:
break;
case OPTION_LONG:
+ case OPTION_ULONG:
case OPTION_U64:
case OPTION_INTEGER:
case OPTION_UINTEGER:
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 92fdbe1519f6..6ca2a8bfe716 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -25,6 +25,7 @@ enum parse_opt_type {
OPTION_STRING,
OPTION_INTEGER,
OPTION_LONG,
+ OPTION_ULONG,
OPTION_CALLBACK,
OPTION_U64,
OPTION_UINTEGER,
@@ -133,6 +134,7 @@ struct option {
#define OPT_INTEGER(s, l, v, h) { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_ULONG(s, l, v, h) { .type = OPTION_ULONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 07/37] perf trace: Introduce --max-events
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (5 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 06/37] tools lib subcmd: Introduce OPTION_ULONG Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 08/37] perf evsel: Introduce per event max_events property Arnaldo Carvalho de Melo
` (30 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Milian Wolff, Namhyung Kim, Rudá Moura, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-trace.txt | 47 +++++++++++++++++++++++++++++++++
tools/perf/builtin-trace.c | 21 +++++++++++++++
2 files changed, 68 insertions(+)
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 115db9e06ecd..0d1a1cd4d328 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
--kernel-syscall-graph::
Show the kernel callchains on the syscall exit path.
+--max-events=N::
+ Stop after processing N events. Note that strace-like events are considered
+ only at exit time or when a syscall is interrupted, i.e. in those cases this
+ option is equivalent to the number of lines printed.
+
--max-stack::
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. Note that at this point
@@ -238,6 +243,48 @@ Trace syscalls, major and minor pagefaults:
As you can see, there was major pagefault in python process, from
CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
+Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
+
+ $ perf trace -e open* --max-events 4
+ [root@jouet perf]# trace -e open* --max-events 4
+ 2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
+ 2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+ 3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+ 4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
+ $
+
+Trace the first minor page fault when running a workload:
+
+ # perf trace -F min --max-stack=7 --max-events 1 sleep 1
+ 0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
+ __clear_user ([kernel.kallsyms])
+ load_elf_binary ([kernel.kallsyms])
+ search_binary_handler ([kernel.kallsyms])
+ __do_execve_file.isra.33 ([kernel.kallsyms])
+ __x64_sys_execve ([kernel.kallsyms])
+ do_syscall_64 ([kernel.kallsyms])
+ entry_SYSCALL_64 ([kernel.kallsyms])
+ #
+
+Trace the next min page page fault to take place on the first CPU:
+
+ # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
+ 0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
+ js::gc::FreeSpan::initAsEmpty (inlined)
+ js::gc::Arena::setAsNotAllocated (inlined)
+ js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
+ js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
+ js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
+ js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
+ js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
+ js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+ js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
+ JSThinInlineString::new_<(js::AllowGC)1> (inlined)
+ AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
+ js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+ [0x18b26e6bc2bd] (/tmp/perf-17136.map)
+ #
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 90289f31dd87..74638034861c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -89,6 +89,8 @@ struct trace {
u64 base_time;
FILE *output;
unsigned long nr_events;
+ unsigned long nr_events_printed;
+ unsigned long max_events;
struct strlist *ev_qualifier;
struct {
size_t nr;
@@ -1664,6 +1666,8 @@ static int trace__printf_interrupted_entry(struct trace *trace)
printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
ttrace->entry_pending = false;
+ ++trace->nr_events_printed;
+
return printed;
}
@@ -1940,6 +1944,13 @@ errno_print: {
fputc('\n', trace->output);
+ /*
+ * We only consider an 'event' for the sake of --max-events a non-filtered
+ * sys_enter + sys_exit and other tracepoint events.
+ */
+ if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
+ interrupted = true;
+
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
@@ -2072,6 +2083,7 @@ static void bpf_output__fprintf(struct trace *trace,
{
binary__fprintf(sample->raw_data, sample->raw_size, 8,
bpf_output__printer, NULL, trace->output);
+ ++trace->nr_events_printed;
}
static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
@@ -2127,6 +2139,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
event_format__fprintf(evsel->tp_format, sample->cpu,
sample->raw_data, sample->raw_size,
trace->output);
+ ++trace->nr_events_printed;
}
}
@@ -2225,6 +2238,8 @@ static int trace__pgfault(struct trace *trace,
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+ ++trace->nr_events_printed;
out:
err = 0;
out_put:
@@ -2402,6 +2417,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
tracepoint_handler handler = evsel->handler;
handler(trace, evsel, event, sample);
}
+
+ if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
+ interrupted = true;
}
static int trace__add_syscall_newtp(struct trace *trace)
@@ -3249,6 +3267,7 @@ int cmd_trace(int argc, const char **argv)
.trace_syscalls = false,
.kernel_syscallchains = false,
.max_stack = UINT_MAX,
+ .max_events = ULONG_MAX,
};
const char *output_name = NULL;
const struct option trace_options[] = {
@@ -3301,6 +3320,8 @@ int cmd_trace(int argc, const char **argv)
&record_parse_callchain_opt),
OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
"Show the kernel callchains on the syscall exit path"),
+ OPT_ULONG(0, "max-events", &trace.max_events,
+ "Set the maximum number of events to print, exit after that is reached. "),
OPT_UINTEGER(0, "min-stack", &trace.min_stack,
"Set the minimum stack depth when parsing the callchain, "
"anything below the specified depth will be ignored."),
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 08/37] perf evsel: Introduce per event max_events property
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (6 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 07/37] perf trace: Introduce --max-events Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 09/37] perf evsel: Mark a evsel as disabled when asking the kernel do disable it Arnaldo Carvalho de Melo
` (29 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Milian Wolff, Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
This simply adds the field to 'struct perf_evsel' and allows setting
it via the event parser, to test it lets trace trace:
First look at where in a function that receives an evsel we can put a probe
to read how evsel->max_events was setup:
# perf probe -x ~/bin/perf -L trace__event_handler
<trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0>
0 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
3 {
4 struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
5 int callchain_ret = 0;
7 if (sample->callchain) {
8 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
9 if (callchain_ret == 0) {
10 if (callchain_cursor.nr < trace->min_stack)
11 goto out;
12 callchain_ret = 1;
}
}
See what variables we can probe at line 7:
# perf probe -x ~/bin/perf -V trace__event_handler:7
Available variables at trace__event_handler:7
@<trace__event_handler+89>
int callchain_ret
struct perf_evsel* evsel
struct perf_sample* sample
struct thread* thread
struct trace* trace
union perf_event* event
Add a probe at that line asking for evsel->max_events to be collected and named
as "max_events":
# perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events'
Added new event:
probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events)
You can now use it in all perf tools, such as:
perf record -e probe_perf:trace__event_handler -aR sleep 1
Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e.
the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event,
while the traced trace is tracing all scheduler tracepoints, will stop at two
events (--max-events 2) and will just set evsel->max_events for all the sched
tracepoints to 9, we will see the output of both traces intermixed:
# trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000
0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000
0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
#
Now, if the traced trace sends its output to /dev/null, we'll see just
what the first level trace outputs: that evsel->max_events is indeed
being set to 9:
# trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/
0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
#
Now that we can set evsel->max_events, we can go to the next step, honour that
per-event property in 'perf trace'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evsel.c | 4 ++++
tools/perf/util/evsel.h | 3 +++
tools/perf/util/parse-events.c | 8 ++++++++
tools/perf/util/parse-events.h | 1 +
tools/perf/util/parse-events.l | 1 +
5 files changed, 17 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 29d7b97f66fb..7e95ec1c19a8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -232,6 +232,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
evsel->leader = evsel;
evsel->unit = "";
evsel->scale = 1.0;
+ evsel->max_events = ULONG_MAX;
evsel->evlist = NULL;
evsel->bpf_fd = -1;
INIT_LIST_HEAD(&evsel->node);
@@ -793,6 +794,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
max_stack = term->val.max_stack;
break;
+ case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+ evsel->max_events = term->val.max_events;
+ break;
case PERF_EVSEL__CONFIG_TERM_INHERIT:
/*
* attr->inherit should has already been set by
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4107c39f4a54..ad5d615c6db6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum term_type {
PERF_EVSEL__CONFIG_TERM_STACK_USER,
PERF_EVSEL__CONFIG_TERM_INHERIT,
PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+ PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
PERF_EVSEL__CONFIG_TERM_OVERWRITE,
PERF_EVSEL__CONFIG_TERM_DRV_CFG,
PERF_EVSEL__CONFIG_TERM_BRANCH,
@@ -65,6 +66,7 @@ struct perf_evsel_config_term {
bool inherit;
bool overwrite;
char *branch;
+ unsigned long max_events;
} val;
bool weak;
};
@@ -99,6 +101,7 @@ struct perf_evsel {
struct perf_counts *prev_raw_counts;
int idx;
u32 ids;
+ unsigned long max_events;
char *name;
double scale;
const char *unit;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7c9186..59be3466d64d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -926,6 +926,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
[PARSE_EVENTS__TERM_TYPE_NOINHERIT] = "no-inherit",
[PARSE_EVENTS__TERM_TYPE_INHERIT] = "inherit",
[PARSE_EVENTS__TERM_TYPE_MAX_STACK] = "max-stack",
+ [PARSE_EVENTS__TERM_TYPE_MAX_EVENTS] = "nr",
[PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite",
[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite",
[PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config",
@@ -1037,6 +1038,9 @@ do { \
case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
CHECK_TYPE_VAL(NUM);
break;
+ case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+ CHECK_TYPE_VAL(NUM);
+ break;
default:
err->str = strdup("unknown term");
err->idx = term->err_term;
@@ -1084,6 +1088,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
case PARSE_EVENTS__TERM_TYPE_INHERIT:
case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+ case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
return config_term_common(attr, term, err);
@@ -1162,6 +1167,9 @@ do { \
case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
break;
+ case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+ ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+ break;
case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
break;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 4473dac27aee..5ed035cbcbb7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
PARSE_EVENTS__TERM_TYPE_NOINHERIT,
PARSE_EVENTS__TERM_TYPE_INHERIT,
PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+ PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
PARSE_EVENTS__TERM_TYPE_OVERWRITE,
PARSE_EVENTS__TERM_TYPE_DRV_CFG,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3ed0f3..7805c71aaae2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -269,6 +269,7 @@ time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
call-graph { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
stack-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
max-stack { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 09/37] perf evsel: Mark a evsel as disabled when asking the kernel do disable it
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (7 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 08/37] perf evsel: Introduce per event max_events property Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 10/37] perf trace: Drop addr_location refcounts Arnaldo Carvalho de Melo
` (28 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Because there may be more such events in the ring buffer that should be
discarded when an app decides to stop considering them.
At some point we'll do this with eBPF, this way we stop them at origin,
before they are placed in the ring buffer.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-uzufuxws4hufigx07ue1dpv6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist.c | 2 +-
tools/perf/util/evsel.c | 23 +++++++++++++++++------
tools/perf/util/evsel.h | 1 +
3 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..e88e6f9b1463 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -358,7 +358,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
struct perf_evsel *pos;
evlist__for_each_entry(evlist, pos) {
- if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+ if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd)
continue;
perf_evsel__disable(pos);
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7e95ec1c19a8..6d187059a373 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1207,16 +1207,27 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
int perf_evsel__enable(struct perf_evsel *evsel)
{
- return perf_evsel__run_ioctl(evsel,
- PERF_EVENT_IOC_ENABLE,
- 0);
+ int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+
+ if (!err)
+ evsel->disabled = false;
+
+ return err;
}
int perf_evsel__disable(struct perf_evsel *evsel)
{
- return perf_evsel__run_ioctl(evsel,
- PERF_EVENT_IOC_DISABLE,
- 0);
+ int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+ /*
+ * We mark it disabled here so that tools that disable a event can
+ * ignore events after they disable it. I.e. the ring buffer may have
+ * already a few more events queued up before the kernel got the stop
+ * request.
+ */
+ if (!err)
+ evsel->disabled = true;
+
+ return err;
}
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ad5d615c6db6..4ef50f157b50 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -122,6 +122,7 @@ struct perf_evsel {
bool snapshot;
bool supported;
bool needs_swap;
+ bool disabled;
bool no_aux_samples;
bool immediate;
bool system_wide;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 10/37] perf trace: Drop addr_location refcounts
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (8 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 09/37] perf evsel: Mark a evsel as disabled when asking the kernel do disable it Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 11/37] perf trace: Drop thread refcount in trace__event_handler() Arnaldo Carvalho de Melo
` (27 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
When we use machine__resolve() we grab a reference to
addr_location.thread (and in the future to other elements there) via
machine__findnew_thread(), so we must pair that with
addr_location__put(), else we'll never drop that thread when it exits
and no other remaining data structures have pointers to it. Fix it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ivg9hifzeuokb1f5jxc2wob4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-trace.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 74638034861c..77b8748ad5ed 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1814,12 +1814,14 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
int max_stack = evsel->attr.sample_max_stack ?
evsel->attr.sample_max_stack :
trace->max_stack;
+ int err;
- if (machine__resolve(trace->host, &al, sample) < 0 ||
- thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
+ if (machine__resolve(trace->host, &al, sample) < 0)
return -1;
- return 0;
+ err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
+ addr_location__put(&al);
+ return err;
}
static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 11/37] perf trace: Drop thread refcount in trace__event_handler()
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (9 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 10/37] perf trace: Drop addr_location refcounts Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 12/37] perf stat: Poll for monitored tasks being alive Arnaldo Carvalho de Melo
` (26 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
We must pair:
thread = machine__findnew_thread();
with thread__put(thread). Fix it.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: c4191e55b874 ("perf trace: Show comm and tid for tracepoint events")
Link: https://lkml.kernel.org/n/tip-dkxsb8cwg87rmkrzrbns1o4z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-trace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 77b8748ad5ed..589e0412652a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2152,8 +2152,8 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
- thread__put(thread);
out:
+ thread__put(thread);
return 0;
}
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 12/37] perf stat: Poll for monitored tasks being alive
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (10 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 11/37] perf trace: Drop thread refcount in trace__event_handler() Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 13/37] perf script: Allow extended console debug output Arnaldo Carvalho de Melo
` (25 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Jiri Olsa,
Alexander Shishkin, Jin Yao, Namhyung Kim, Peter Zijlstra,
Arnaldo Carvalho de Melo
From: Jiri Olsa <jolsa@kernel.org>
Adding the check for tasks we monitor via -p/-t options, and finish stat
if there's no longer task to monitor.
Requested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181022093015.9106-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b86aba1c8028..d1028d7755bb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -409,6 +409,28 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
return leader;
}
+static bool is_target_alive(struct target *_target,
+ struct thread_map *threads)
+{
+ struct stat st;
+ int i;
+
+ if (!target__has_task(_target))
+ return true;
+
+ for (i = 0; i < threads->nr; i++) {
+ char path[PATH_MAX];
+
+ scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
+ threads->map[i].pid);
+
+ if (!stat(path, &st))
+ return true;
+ }
+
+ return false;
+}
+
static int __run_perf_stat(int argc, const char **argv, int run_idx)
{
int interval = stat_config.interval;
@@ -579,6 +601,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
enable_counters();
while (!done) {
nanosleep(&ts, NULL);
+ if (!is_target_alive(&target, evsel_list->threads))
+ break;
if (timeout)
break;
if (interval) {
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 13/37] perf script: Allow extended console debug output
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (11 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 12/37] perf stat: Poll for monitored tasks being alive Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 14/37] perf script: Flush output stream after events in verbose mode Arnaldo Carvalho de Melo
` (24 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Milian Wolff,
Arnaldo Carvalho de Melo
From: Milian Wolff <milian.wolff@kdab.com>
The script tool isn't using a browser, yet use_browser wasn't set
explicitly to zero. This in turn lead to confusing output such as:
```
$ perf script -vvv ...
...
overlapping maps in /home/milian/foobar (disable tui for more info)
...
```
Explicitly set use_browser to 0 now, which gives us the extended
debug information now in perf script as expected.
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181021191424.16183-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4da5e32b9e03..bd468b90801b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3417,8 +3417,10 @@ int cmd_script(int argc, const char **argv)
exit(-1);
}
- if (!script_name)
+ if (!script_name) {
setup_pager();
+ use_browser = 0;
+ }
session = perf_session__new(&data, false, &script.tool);
if (session == NULL)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 14/37] perf script: Flush output stream after events in verbose mode
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (12 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 13/37] perf script: Allow extended console debug output Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 15/37] perf trace: Introduce per-event maximum number of events property Arnaldo Carvalho de Melo
` (23 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Milian Wolff,
Arnaldo Carvalho de Melo
From: Milian Wolff <milian.wolff@kdab.com>
When the perf script output is written to a terminal stream, the normal
output of `perf script` would get buffered, but its debug output would
be written directly. This made it quite hard to figure out where a given
debug output is coming from.
We can improve on this by flushing the output buffer after processing an
event. To see the value, compare the following output for a `perf script
-v` run:
Before this patch:
```
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
... lots and lots of verbose debug output
cpp-inlining 24617 90229.122036534: 1 cycles:uppp:
7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
cpp-inlining 24617 90229.122043974: 1 cycles:uppp:
7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```
After this patch:
```
...
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122036534: 1 cycles:uppp:
7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122043974: 1 cycles:uppp:
7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```
This new output format makes it much easier to use perf script output
for debugging purposes, e.g. to investigate broken dwarf unwinding.
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181021191424.16183-2-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index bd468b90801b..ca09b7d2adb7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1737,6 +1737,9 @@ static void process_event(struct perf_script *script,
if (PRINT_FIELD(METRIC))
perf_sample__fprint_metric(script, thread, evsel, sample, fp);
+
+ if (verbose)
+ fflush(fp);
}
static struct scripting_ops *scripting_ops;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 15/37] perf trace: Introduce per-event maximum number of events property
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (13 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 14/37] perf script: Flush output stream after events in verbose mode Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 16/37] perf scripts python: call-graph-from-sql.py: Use SPDX license identifier Arnaldo Carvalho de Melo
` (22 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, David Ahern, Jiri Olsa,
Namhyung Kim, Wang Nan
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Call it 'nr', as in this context it should be expressive enough, i.e.:
# perf trace -e sched:*waking/nr=8,call-graph=fp/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
try_to_wake_up ([kernel.kallsyms])
try_to_wake_up ([kernel.kallsyms])
wake_up_q ([kernel.kallsyms])
futex_wake ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
#
# perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
__dev_queue_xmit ([kernel.kallsyms])
1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
__dev_queue_xmit ([kernel.kallsyms])
3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
__dev_queue_xmit ([kernel.kallsyms])
4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
#
The global --max-events has precendence:
# trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
__dev_queue_xmit ([kernel.kallsyms])
__libc_send (/usr/lib64/libpthread-2.26.so)
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-trace.txt | 20 ++++++++++++++++++++
tools/perf/builtin-trace.c | 19 +++++++++++++++++--
tools/perf/util/evsel.h | 1 +
3 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 0d1a1cd4d328..e113450503d2 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -285,6 +285,26 @@ Trace the next min page page fault to take place on the first CPU:
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
#
+Trace the next two sched:sched_switch events, four block:*_plug events, the
+next block:*_unplug and the next three net:*dev_queue events, this last one
+with a backtrace of at most 16 entries, system wide:
+
+ # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
+ 0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
+ 0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
+ 254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
+ __dev_queue_xmit ([kernel.kallsyms])
+ 273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
+ __dev_queue_xmit ([kernel.kallsyms])
+ 274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
+ __dev_queue_xmit ([kernel.kallsyms])
+ 2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
+ 2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
+ 4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
+ 8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+ 8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+ #
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 589e0412652a..7081d7ea12e5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2092,8 +2092,18 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
- struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+ struct thread *thread;
int callchain_ret = 0;
+ /*
+ * Check if we called perf_evsel__disable(evsel) due to, for instance,
+ * this event's max_events having been hit and this is an entry coming
+ * from the ring buffer that we should discard, since the max events
+ * have already been considered/printed.
+ */
+ if (evsel->disabled)
+ return 0;
+
+ thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
if (sample->callchain) {
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
@@ -2142,6 +2152,11 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
sample->raw_data, sample->raw_size,
trace->output);
++trace->nr_events_printed;
+
+ if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+ perf_evsel__disable(evsel);
+ perf_evsel__close(evsel);
+ }
}
}
@@ -2726,7 +2741,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
int timeout = done ? 100 : -1;
if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
- if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+ if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
draining = true;
goto again;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4ef50f157b50..3147ca76c6fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,6 +102,7 @@ struct perf_evsel {
int idx;
u32 ids;
unsigned long max_events;
+ unsigned long nr_events_printed;
char *name;
double scale;
const char *unit;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 16/37] perf scripts python: call-graph-from-sql.py: Use SPDX license identifier
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (14 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 15/37] perf trace: Introduce per-event maximum number of events property Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 17/37] perf scripts python: call-graph-from-sql.py: Provide better default column sizes Arnaldo Carvalho de Melo
` (21 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Use SPDX license identifier in call-graph-from-sql.py.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 14 +++-----------
1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index b494a67a1c67..ce1b91fcd6b8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -1,15 +1,7 @@
#!/usr/bin/python2
-# call-graph-from-sql.py: create call-graph from sql database
-# Copyright (c) 2014-2017, Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
# To use this script you will need to have exported data using either the
# export-to-sqlite.py or the export-to-postgresql.py script. Refer to those
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 17/37] perf scripts python: call-graph-from-sql.py: Provide better default column sizes
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (15 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 16/37] perf scripts python: call-graph-from-sql.py: Use SPDX license identifier Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 18/37] perf scripts python: call-graph-from-sql.py: Set a minimum window size Arnaldo Carvalho de Melo
` (20 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Set initial column sizes to improve initial display.
Committer testing:
Extended instructions on testing this, using the sqlite variant:
Make sure you have the SQLite glue for python+Qt installed, on fedora 27
I used:
# dnf install python-pyside
Collect some PT samples, say 5-secs worth, system wide:
# perf record -r 10 -e intel_pt//u -a sleep 5
[ perf record: Woken up 49 times to write data ]
[ perf record: Captured and wrote 96.131 MB perf.data ]
This results in this perf.data file:
# ls -larth perf.data
-rw-------. 1 root root 97M Oct 23 10:11 perf.data
With the following attributes:
# perf evlist -v
intel_pt//u: type: 8, size: 112, config: 0x300e601, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 1, exclude_hv: 1, sample_id_all: 1
dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1, context_switch: 1
#
Then generate the "pt_example" tables using:
# perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
2018-10-23 10:56:59.177711 Creating database...
2018-10-23 10:56:59.195842 Writing records...
instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x263984516750 code 5: Failed to get instruction
instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e116fd20 code 6: Trace doesn't match instruction
instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e162c9ee code 6: Trace doesn't match instruction
instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e9ce831a code 6: Trace doesn't match instruction
<SNIP>
instruction trace error type 1 cpu 0 pid 1644 tid 1644 ip 0x7f26e13d07b4 code 6: Trace doesn't match instruction
Warning:
132 instruction trace errors
2018-10-23 11:25:25.015717 Adding indexes
2018-10-23 11:25:28.788061 Done
#
In my example, that perf.data file generated this db:
# file pt_example
pt_example: SQLite 3.x database, last written using SQLite version 3020001
[root@seventh perf]# ls -lah pt_example
-rw-r--r--. 1 root root 6.6G Oct 23 11:25 pt_example
#
Then use this python script to use that db and provide a GUI:
$ python tools/perf/scripts/python/call-graph-from-sql.py pt_example branches calls
I compared the column widths before this patch and after applying it,
the visual results match the patch intent.
The following patches will refer to this set of instructions in the "Committer
Testing" section.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ce1b91fcd6b8..e1014f2628a7 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -280,6 +280,9 @@ class MainWindow(QMainWindow):
self.view = QTreeView()
self.view.setModel(self.model)
+ for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+ self.view.setColumnWidth(c, w)
+
self.setCentralWidget(self.view)
if __name__ == '__main__':
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 18/37] perf scripts python: call-graph-from-sql.py: Set a minimum window size
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (16 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 17/37] perf scripts python: call-graph-from-sql.py: Provide better default column sizes Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 19/37] perf scripts python: call-graph-from-sql.py: Change icon Arnaldo Carvalho de Melo
` (19 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Prevent weirdly small window size.
Committer testing:
Seems to work, but even before this patch, on my system, it always
started with:
xwininfo: Window id: 0x1e00002 "Call Graph: pt_example"
<SNIP>
Width: 800
Height: 600
<SNIP>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index e1014f2628a7..68153fa1b4d1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -274,6 +274,7 @@ class MainWindow(QMainWindow):
style = self.style()
icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
self.setWindowIcon(icon);
+ self.setMinimumSize(200, 100)
self.model = TreeModel(db)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 19/37] perf scripts python: call-graph-from-sql.py: Change icon
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (17 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 18/37] perf scripts python: call-graph-from-sql.py: Set a minimum window size Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 20/37] perf scripts python: call-graph-from-sql.py: Make a "Main" function Arnaldo Carvalho de Melo
` (18 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
There are not many standard icons, but the computer icon looks slightly
better than the information icon.
Committer testing:
Noticed the change on the icon on the gnome menu right next to the
"Activities" menu, looks nicer indeed.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 68153fa1b4d1..2e33540f3de0 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -271,9 +271,7 @@ class MainWindow(QMainWindow):
self.setWindowTitle("Call Graph: " + dbname)
self.move(100, 100)
self.resize(800, 600)
- style = self.style()
- icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
- self.setWindowIcon(icon);
+ self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
self.setMinimumSize(200, 100)
self.model = TreeModel(db)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 20/37] perf scripts python: call-graph-from-sql.py: Make a "Main" function
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (18 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 19/37] perf scripts python: call-graph-from-sql.py: Change icon Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 21/37] perf scripts python: call-graph-from-sql.py: Separate the database details into a class Arnaldo Carvalho de Melo
` (17 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Make a "Main" function so that the variables used do not pollute the global
namespace.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2e33540f3de0..2b74b94eeccc 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,7 +284,9 @@ class MainWindow(QMainWindow):
self.setCentralWidget(self.view)
-if __name__ == '__main__':
+# Main
+
+def Main():
if (len(sys.argv) < 2):
print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
raise Exception("Too few arguments")
@@ -331,3 +333,6 @@ if __name__ == '__main__':
err = app.exec_()
db.close()
sys.exit(err)
+
+if __name__ == "__main__":
+ Main()
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 21/37] perf scripts python: call-graph-from-sql.py: Separate the database details into a class
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (19 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 20/37] perf scripts python: call-graph-from-sql.py: Make a "Main" function Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 22/37] perf scripts python: call-graph-from-sql.py: Add a class for global data Arnaldo Carvalho de Melo
` (16 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Separate the database details into a class that can provide different
connections using the same connection information. That paves the way
for sub-processes that require their own connection.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 63 ++++++++++++++----------
1 file changed, 38 insertions(+), 25 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2b74b94eeccc..9d056deab2b1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,6 +284,42 @@ class MainWindow(QMainWindow):
self.setCentralWidget(self.view)
+# Database reference
+
+class DBRef():
+
+ def __init__(self, is_sqlite3, dbname):
+ self.is_sqlite3 = is_sqlite3
+ self.dbname = dbname
+
+ def Open(self, connection_name):
+ dbname = self.dbname
+ if self.is_sqlite3:
+ db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+ else:
+ db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+ opts = dbname.split()
+ for opt in opts:
+ if "=" in opt:
+ opt = opt.split("=")
+ if opt[0] == "hostname":
+ db.setHostName(opt[1])
+ elif opt[0] == "port":
+ db.setPort(int(opt[1]))
+ elif opt[0] == "username":
+ db.setUserName(opt[1])
+ elif opt[0] == "password":
+ db.setPassword(opt[1])
+ elif opt[0] == "dbname":
+ dbname = opt[1]
+ else:
+ dbname = opt
+
+ db.setDatabaseName(dbname)
+ if not db.open():
+ raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+ return db, dbname
+
# Main
def Main():
@@ -302,31 +338,8 @@ def Main():
except:
pass
- if is_sqlite3:
- db = QSqlDatabase.addDatabase('QSQLITE')
- else:
- db = QSqlDatabase.addDatabase('QPSQL')
- opts = dbname.split()
- for opt in opts:
- if '=' in opt:
- opt = opt.split('=')
- if opt[0] == 'hostname':
- db.setHostName(opt[1])
- elif opt[0] == 'port':
- db.setPort(int(opt[1]))
- elif opt[0] == 'username':
- db.setUserName(opt[1])
- elif opt[0] == 'password':
- db.setPassword(opt[1])
- elif opt[0] == 'dbname':
- dbname = opt[1]
- else:
- dbname = opt
-
- db.setDatabaseName(dbname)
- if not db.open():
- raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-
+ dbref = DBRef(is_sqlite3, dbname)
+ db, dbname = dbref.Open("main")
app = QApplication(sys.argv)
window = MainWindow(db, dbname)
window.show()
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 22/37] perf scripts python: call-graph-from-sql.py: Add a class for global data
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (20 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 21/37] perf scripts python: call-graph-from-sql.py: Separate the database details into a class Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 23/37] perf scripts python: call-graph-from-sql.py: Remove use of setObjectName() Arnaldo Carvalho de Melo
` (15 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Keep global data in a single object that is easy to pass around as
needed, without polluting the global namespace.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 26 +++++++++++++++++++-----
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 9d056deab2b1..0a4dc13d4818 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -264,17 +264,19 @@ class TreeModel(QAbstractItemModel):
class MainWindow(QMainWindow):
- def __init__(self, db, dbname, parent=None):
+ def __init__(self, glb, parent=None):
super(MainWindow, self).__init__(parent)
+ self.glb = glb
+
self.setObjectName("MainWindow")
- self.setWindowTitle("Call Graph: " + dbname)
+ self.setWindowTitle("Call Graph: " + glb.dbname)
self.move(100, 100)
self.resize(800, 600)
self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
self.setMinimumSize(200, 100)
- self.model = TreeModel(db)
+ self.model = TreeModel(glb.db)
self.view = QTreeView()
self.view.setModel(self.model)
@@ -284,6 +286,17 @@ class MainWindow(QMainWindow):
self.setCentralWidget(self.view)
+# Global data
+
+class Glb():
+
+ def __init__(self, dbref, db, dbname):
+ self.dbref = dbref
+ self.db = db
+ self.dbname = dbname
+ self.app = None
+ self.mainwindow = None
+
# Database reference
class DBRef():
@@ -340,9 +353,12 @@ def Main():
dbref = DBRef(is_sqlite3, dbname)
db, dbname = dbref.Open("main")
+ glb = Glb(dbref, db, dbname)
app = QApplication(sys.argv)
- window = MainWindow(db, dbname)
- window.show()
+ glb.app = app
+ mainwindow = MainWindow(glb)
+ glb.mainwindow = mainwindow
+ mainwindow.show()
err = app.exec_()
db.close()
sys.exit(err)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 23/37] perf scripts python: call-graph-from-sql.py: Remove use of setObjectName()
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (21 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 22/37] perf scripts python: call-graph-from-sql.py: Add a class for global data Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 24/37] perf scripts python: call-graph-from-sql.py: Factor out CallGraphModel from TreeModel Arnaldo Carvalho de Melo
` (14 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
The object name is never used, so don't bother setting it.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 1 -
1 file changed, 1 deletion(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 0a4dc13d4818..65c18e351bc4 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -269,7 +269,6 @@ class MainWindow(QMainWindow):
self.glb = glb
- self.setObjectName("MainWindow")
self.setWindowTitle("Call Graph: " + glb.dbname)
self.move(100, 100)
self.resize(800, 600)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 24/37] perf scripts python: call-graph-from-sql.py: Factor out CallGraphModel from TreeModel
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (22 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 23/37] perf scripts python: call-graph-from-sql.py: Remove use of setObjectName() Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 25/37] perf scripts python: call-graph-from-sql.py: Add data helper functions Arnaldo Carvalho de Melo
` (13 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Factor out CallGraphModel from TreeModel, which paves the way to reuse
TreeModel in future reports.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 90 ++++++++++++++++--------
1 file changed, 61 insertions(+), 29 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 65c18e351bc4..ada486048ad8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -201,42 +201,47 @@ class TreeItem():
self.selectCalls()
return self.child_count
- def columnCount(self):
- return 7
-
- def columnHeader(self, column):
- headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
- return headers[column]
+ def hasChildren(self):
+ if not self.query_done:
+ return True
+ return self.child_count > 0
def getData(self, column):
return self.data[column]
+# Tree data model
+
class TreeModel(QAbstractItemModel):
- def __init__(self, db, parent=None):
+ def __init__(self, root, parent=None):
super(TreeModel, self).__init__(parent)
- self.db = db
- self.root = TreeItem(db, 0, None)
+ self.root = root
+ self.last_row_read = 0
- def columnCount(self, parent):
- return self.root.columnCount()
-
- def rowCount(self, parent):
+ def Item(self, parent):
if parent.isValid():
- parent_item = parent.internalPointer()
+ return parent.internalPointer()
else:
- parent_item = self.root
- return parent_item.childCount()
+ return self.root
+
+ def rowCount(self, parent):
+ result = self.Item(parent).childCount()
+ if result < 0:
+ result = 0
+ self.dataChanged.emit(parent, parent)
+ return result
+
+ def hasChildren(self, parent):
+ return self.Item(parent).hasChildren()
def headerData(self, section, orientation, role):
if role == Qt.TextAlignmentRole:
- if section > 1:
- return Qt.AlignRight
+ return self.columnAlignment(section)
if role != Qt.DisplayRole:
return None
if orientation != Qt.Horizontal:
return None
- return self.root.columnHeader(section)
+ return self.columnHeader(section)
def parent(self, child):
child_item = child.internalPointer()
@@ -246,21 +251,48 @@ class TreeModel(QAbstractItemModel):
return self.createIndex(parent_item.getRow(), 0, parent_item)
def index(self, row, column, parent):
- if parent.isValid():
- parent_item = parent.internalPointer()
- else:
- parent_item = self.root
- child_item = parent_item.getChildItem(row)
+ child_item = self.Item(parent).getChildItem(row)
return self.createIndex(row, column, child_item)
+ def DisplayData(self, item, index):
+ return item.getData(index.column())
+
+ def columnAlignment(self, column):
+ return Qt.AlignLeft
+
+ def columnFont(self, column):
+ return None
+
def data(self, index, role):
if role == Qt.TextAlignmentRole:
- if index.column() > 1:
- return Qt.AlignRight
+ return self.columnAlignment(index.column())
+ if role == Qt.FontRole:
+ return self.columnFont(index.column())
if role != Qt.DisplayRole:
return None
- index_item = index.internalPointer()
- return index_item.getData(index.column())
+ item = index.internalPointer()
+ return self.DisplayData(item, index)
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+ def __init__(self, glb, parent=None):
+ super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+ self.glb = glb
+
+ def columnCount(self, parent=None):
+ return 7
+
+ def columnHeader(self, column):
+ headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+ return headers[column]
+
+ def columnAlignment(self, column):
+ alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+ return alignment[column]
+
+# Main window
class MainWindow(QMainWindow):
@@ -275,7 +307,7 @@ class MainWindow(QMainWindow):
self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
self.setMinimumSize(200, 100)
- self.model = TreeModel(glb.db)
+ self.model = CallGraphModel(glb)
self.view = QTreeView()
self.view.setModel(self.model)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 25/37] perf scripts python: call-graph-from-sql.py: Add data helper functions
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (23 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 24/37] perf scripts python: call-graph-from-sql.py: Factor out CallGraphModel from TreeModel Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 26/37] perf scripts python: call-graph-from-sql.py: Refactor TreeItem class Arnaldo Carvalho de Melo
` (12 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Add helper functions for a few common cases.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-11-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 54 +++++++++++++-----------
1 file changed, 29 insertions(+), 25 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ada486048ad8..7f2eabe7dacd 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -52,6 +52,28 @@ from PySide.QtGui import *
from PySide.QtSql import *
from decimal import *
+# Data formatting helpers
+
+def dsoname(name):
+ if name == "[kernel.kallsyms]":
+ return "[kernel]"
+ return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+ if not d:
+ return "0.0"
+ x = (n * Decimal(100)) / d
+ return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+ ret = query.exec_(stmt)
+ if not ret:
+ raise Exception("Query failed: " + query.lastError().text())
+
class TreeItem():
def __init__(self, db, row, parent_item):
@@ -73,9 +95,7 @@ class TreeItem():
def setUpRoot(self):
self.query_done = True
query = QSqlQuery(self.db)
- ret = query.exec_('SELECT id, comm FROM comms')
- if not ret:
- raise Exception("Query failed: " + query.lastError().text())
+ QueryExec(query, 'SELECT id, comm FROM comms')
while query.next():
if not query.value(0):
continue
@@ -91,9 +111,7 @@ class TreeItem():
self.child_items = []
self.child_count = 0
query = QSqlQuery(self.db)
- ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
- if not ret:
- raise Exception("Query failed: " + query.lastError().text())
+ QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
while query.next():
child_item = TreeItem(self.db, self.child_count, self)
self.child_items.append(child_item)
@@ -114,18 +132,6 @@ class TreeItem():
def getRow(self):
return self.row
- def timePercent(self, b):
- if not self.time:
- return "0.0"
- x = (b * Decimal(100)) / self.time
- return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
- def branchPercent(self, b):
- if not self.branch_count:
- return "0.0"
- x = (b * Decimal(100)) / self.branch_count
- return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
def addChild(self, call_path_id, name, dso, count, time, branch_count):
child_item = TreeItem(self.db, self.child_count, self)
child_item.comm_id = self.comm_id
@@ -134,14 +140,12 @@ class TreeItem():
child_item.branch_count = branch_count
child_item.time = time
child_item.data[0] = name
- if dso == "[kernel.kallsyms]":
- dso = "[kernel]"
- child_item.data[1] = dso
+ child_item.data[1] = dsoname(dso)
child_item.data[2] = str(count)
child_item.data[3] = str(time)
- child_item.data[4] = self.timePercent(time)
+ child_item.data[4] = PercentToOneDP(time, self.time)
child_item.data[5] = str(branch_count)
- child_item.data[6] = self.branchPercent(branch_count)
+ child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
self.child_items.append(child_item)
self.child_count += 1
@@ -189,12 +193,12 @@ class TreeItem():
self.branch_count = total_branch_count
if self.branch_count:
for child_item in self.child_items:
- child_item.data[6] = self.branchPercent(child_item.branch_count)
+ child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
if total_time > self.time:
self.time = total_time
if self.time:
for child_item in self.child_items:
- child_item.data[4] = self.timePercent(child_item.time)
+ child_item.data[4] = PercentToOneDP(child_item.time, self.time)
def childCount(self):
if not self.query_done:
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 26/37] perf scripts python: call-graph-from-sql.py: Refactor TreeItem class
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (24 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 25/37] perf scripts python: call-graph-from-sql.py: Add data helper functions Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 27/37] perf scripts python: call-graph-from-sql.py: Rename to exported-sql-viewer.py Arnaldo Carvalho de Melo
` (11 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
class TreeItem represents items at all levels of the call-graph tree.
However, not all the levels represent the same data i.e. the top-level is
comms, the next level is threads, and subsequent levels are functions.
Consequently it is simpler to have separate classes for different levels
with commonality in a base class. Refactor TreeItem class accordingly.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-12-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/call-graph-from-sql.py | 273 +++++++++++------------
1 file changed, 133 insertions(+), 140 deletions(-)
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 7f2eabe7dacd..ee1085169a3e 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -74,145 +74,6 @@ def QueryExec(query, stmt):
if not ret:
raise Exception("Query failed: " + query.lastError().text())
-class TreeItem():
-
- def __init__(self, db, row, parent_item):
- self.db = db
- self.row = row
- self.parent_item = parent_item
- self.query_done = False;
- self.child_count = 0
- self.child_items = []
- self.data = ["", "", "", "", "", "", ""]
- self.comm_id = 0
- self.thread_id = 0
- self.call_path_id = 1
- self.branch_count = 0
- self.time = 0
- if not parent_item:
- self.setUpRoot()
-
- def setUpRoot(self):
- self.query_done = True
- query = QSqlQuery(self.db)
- QueryExec(query, 'SELECT id, comm FROM comms')
- while query.next():
- if not query.value(0):
- continue
- child_item = TreeItem(self.db, self.child_count, self)
- self.child_items.append(child_item)
- self.child_count += 1
- child_item.setUpLevel1(query.value(0), query.value(1))
-
- def setUpLevel1(self, comm_id, comm):
- self.query_done = True;
- self.comm_id = comm_id
- self.data[0] = comm
- self.child_items = []
- self.child_count = 0
- query = QSqlQuery(self.db)
- QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
- while query.next():
- child_item = TreeItem(self.db, self.child_count, self)
- self.child_items.append(child_item)
- self.child_count += 1
- child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
-
- def setUpLevel2(self, comm_id, thread_id, pid, tid):
- self.comm_id = comm_id
- self.thread_id = thread_id
- self.data[0] = str(pid) + ":" + str(tid)
-
- def getChildItem(self, row):
- return self.child_items[row]
-
- def getParentItem(self):
- return self.parent_item
-
- def getRow(self):
- return self.row
-
- def addChild(self, call_path_id, name, dso, count, time, branch_count):
- child_item = TreeItem(self.db, self.child_count, self)
- child_item.comm_id = self.comm_id
- child_item.thread_id = self.thread_id
- child_item.call_path_id = call_path_id
- child_item.branch_count = branch_count
- child_item.time = time
- child_item.data[0] = name
- child_item.data[1] = dsoname(dso)
- child_item.data[2] = str(count)
- child_item.data[3] = str(time)
- child_item.data[4] = PercentToOneDP(time, self.time)
- child_item.data[5] = str(branch_count)
- child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
- self.child_items.append(child_item)
- self.child_count += 1
-
- def selectCalls(self):
- self.query_done = True;
- query = QSqlQuery(self.db)
- ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
- '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
- '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
- '( SELECT ip FROM call_paths where id = call_path_id ) '
- 'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
- ' ORDER BY call_path_id')
- if not ret:
- raise Exception("Query failed: " + query.lastError().text())
- last_call_path_id = 0
- name = ""
- dso = ""
- count = 0
- branch_count = 0
- total_branch_count = 0
- time = 0
- total_time = 0
- while query.next():
- if query.value(1) == last_call_path_id:
- count += 1
- branch_count += query.value(2)
- time += query.value(4) - query.value(3)
- else:
- if count:
- self.addChild(last_call_path_id, name, dso, count, time, branch_count)
- last_call_path_id = query.value(1)
- name = query.value(5)
- dso = query.value(6)
- count = 1
- total_branch_count += branch_count
- total_time += time
- branch_count = query.value(2)
- time = query.value(4) - query.value(3)
- if count:
- self.addChild(last_call_path_id, name, dso, count, time, branch_count)
- total_branch_count += branch_count
- total_time += time
- # Top level does not have time or branch count, so fix that here
- if total_branch_count > self.branch_count:
- self.branch_count = total_branch_count
- if self.branch_count:
- for child_item in self.child_items:
- child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
- if total_time > self.time:
- self.time = total_time
- if self.time:
- for child_item in self.child_items:
- child_item.data[4] = PercentToOneDP(child_item.time, self.time)
-
- def childCount(self):
- if not self.query_done:
- self.selectCalls()
- return self.child_count
-
- def hasChildren(self):
- if not self.query_done:
- return True
- return self.child_count > 0
-
- def getData(self, column):
- return self.data[column]
-
# Tree data model
class TreeModel(QAbstractItemModel):
@@ -277,12 +138,144 @@ class TreeModel(QAbstractItemModel):
item = index.internalPointer()
return self.DisplayData(item, index)
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+ def __init__(self, glb, row, parent_item):
+ self.glb = glb
+ self.row = row
+ self.parent_item = parent_item
+ self.query_done = False;
+ self.child_count = 0
+ self.child_items = []
+
+ def getChildItem(self, row):
+ return self.child_items[row]
+
+ def getParentItem(self):
+ return self.parent_item
+
+ def getRow(self):
+ return self.row
+
+ def childCount(self):
+ if not self.query_done:
+ self.Select()
+ if not self.child_count:
+ return -1
+ return self.child_count
+
+ def hasChildren(self):
+ if not self.query_done:
+ return True
+ return self.child_count > 0
+
+ def getData(self, column):
+ return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+ def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+ super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+ self.comm_id = comm_id
+ self.thread_id = thread_id
+ self.call_path_id = call_path_id
+ self.branch_count = branch_count
+ self.time = time
+
+ def Select(self):
+ self.query_done = True;
+ query = QSqlQuery(self.glb.db)
+ QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+ " FROM calls"
+ " INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+ " INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+ " INNER JOIN dsos ON symbols.dso_id = dsos.id"
+ " WHERE parent_call_path_id = " + str(self.call_path_id) +
+ " AND comm_id = " + str(self.comm_id) +
+ " AND thread_id = " + str(self.thread_id) +
+ " GROUP BY call_path_id, name, short_name"
+ " ORDER BY call_path_id")
+ while query.next():
+ child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+ self.child_items.append(child_item)
+ self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+ def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+ super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+ dso = dsoname(dso)
+ self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+ self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+ def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+ super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+ self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+ self.dbid = thread_id
+
+ def Select(self):
+ super(CallGraphLevelTwoItem, self).Select()
+ for child_item in self.child_items:
+ self.time += child_item.time
+ self.branch_count += child_item.branch_count
+ for child_item in self.child_items:
+ child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+ child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+ def __init__(self, glb, row, comm_id, comm, parent_item):
+ super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+ self.data = [comm, "", "", "", "", "", ""]
+ self.dbid = comm_id
+
+ def Select(self):
+ self.query_done = True;
+ query = QSqlQuery(self.glb.db)
+ QueryExec(query, "SELECT thread_id, pid, tid"
+ " FROM comm_threads"
+ " INNER JOIN threads ON thread_id = threads.id"
+ " WHERE comm_id = " + str(self.dbid))
+ while query.next():
+ child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+ self.child_items.append(child_item)
+ self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+ def __init__(self, glb):
+ super(CallGraphRootItem, self).__init__(glb, 0, None)
+ self.dbid = 0
+ self.query_done = True;
+ query = QSqlQuery(glb.db)
+ QueryExec(query, "SELECT id, comm FROM comms")
+ while query.next():
+ if not query.value(0):
+ continue
+ child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+ self.child_items.append(child_item)
+ self.child_count += 1
+
# Context-sensitive call graph data model
class CallGraphModel(TreeModel):
def __init__(self, glb, parent=None):
- super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+ super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
self.glb = glb
def columnCount(self, parent=None):
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 27/37] perf scripts python: call-graph-from-sql.py: Rename to exported-sql-viewer.py
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (25 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 26/37] perf scripts python: call-graph-from-sql.py: Refactor TreeItem class Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 28/37] perf scripts python: exported-sql-viewer.py: Add support for multiple sub-windows Arnaldo Carvalho de Melo
` (10 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Additional reports will be added to the script so rename to reflect the
more general purpose.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-13-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/intel-pt.txt | 2 +-
tools/perf/scripts/python/export-to-postgresql.py | 2 +-
tools/perf/scripts/python/export-to-sqlite.py | 2 +-
.../python/{call-graph-from-sql.py => exported-sql-viewer.py} | 6 +++---
4 files changed, 6 insertions(+), 6 deletions(-)
rename tools/perf/scripts/python/{call-graph-from-sql.py => exported-sql-viewer.py} (98%)
mode change 100644 => 100755
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 76971d2e4164..115eaacc455f 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -106,7 +106,7 @@ in transaction, respectively.
While it is possible to create scripts to analyze the data, an alternative
approach is available to export the data to a sqlite or postgresql database.
Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script call-graph-from-sql.py for an example of using the database.
+and to script exported-sql-viewer.py for an example of using the database.
There is also script intel-pt-events.py which provides an example of how to
unpack the raw data for power events and PTWRITE.
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index e46f51b17513..0564dd7377f2 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
# pt_example=# \q
#
# An example of using the database is provided by the script
-# call-graph-from-sql.py. Refer to that script for details.
+# exported-sql-viewer.py. Refer to that script for details.
#
# Tables:
#
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index e4bb82c8aba9..245caf2643ed 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -40,7 +40,7 @@ import datetime
# sqlite> .quit
#
# An example of using the database is provided by the script
-# call-graph-from-sql.py. Refer to that script for details.
+# exported-sql-viewer.py. Refer to that script for details.
#
# The database structure is practically the same as created by the script
# export-to-postgresql.py. Refer to that script for details. A notable
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/exported-sql-viewer.py
old mode 100644
new mode 100755
similarity index 98%
rename from tools/perf/scripts/python/call-graph-from-sql.py
rename to tools/perf/scripts/python/exported-sql-viewer.py
index ee1085169a3e..03e7a1de7f31
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -10,12 +10,12 @@
# Following on from the example in the export scripts, a
# call-graph can be displayed for the pt_example database like this:
#
-# python tools/perf/scripts/python/call-graph-from-sql.py pt_example
+# python tools/perf/scripts/python/exported-sql-viewer.py pt_example
#
# Note that for PostgreSQL, this script supports connecting to remote databases
# by setting hostname, port, username, password, and dbname e.g.
#
-# python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+# python tools/perf/scripts/python/exported-sql-viewer.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
#
# The result is a GUI window with a tree representing a context-sensitive
# call-graph. Expanding a couple of levels of the tree and adjusting column
@@ -365,7 +365,7 @@ class DBRef():
def Main():
if (len(sys.argv) < 2):
- print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
+ print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
raise Exception("Too few arguments")
dbname = sys.argv[1]
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 28/37] perf scripts python: exported-sql-viewer.py: Add support for multiple sub-windows
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (26 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 27/37] perf scripts python: call-graph-from-sql.py: Rename to exported-sql-viewer.py Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 29/37] perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph Arnaldo Carvalho de Melo
` (9 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Use Qt MDI (multiple document interface) to support multiple sub-windows.
Put the data model in a cache so that each sub-window can share the same
data. This allows mutiple views of the call-graph at the same time and
paves the way to add more reports.
Committer testing:
Starts with a "File Reports Windows" main menu, from the "Reports" I
can get what was available up to now, the "Context-Sensitivi Call Graph"
option.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-14-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/exported-sql-viewer.py | 182 +++++++++++++++++++++--
1 file changed, 173 insertions(+), 9 deletions(-)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 03e7a1de7f31..c2f44351821e 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -47,6 +47,8 @@
# functions that it calls
import sys
+import weakref
+import threading
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
@@ -138,6 +140,23 @@ class TreeModel(QAbstractItemModel):
item = index.internalPointer()
return self.DisplayData(item, index)
+# Model cache
+
+model_cache = weakref.WeakValueDictionary()
+model_cache_lock = threading.Lock()
+
+def LookupCreateModel(model_name, create_fn):
+ model_cache_lock.acquire()
+ try:
+ model = model_cache[model_name]
+ except:
+ model = None
+ if model is None:
+ model = create_fn()
+ model_cache[model_name] = model
+ model_cache_lock.release()
+ return model
+
# Context-sensitive call graph data model item base
class CallGraphLevelItemBase(object):
@@ -289,6 +308,144 @@ class CallGraphModel(TreeModel):
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
+# Context-sensitive call graph window
+
+class CallGraphWindow(QMdiSubWindow):
+
+ def __init__(self, glb, parent=None):
+ super(CallGraphWindow, self).__init__(parent)
+
+ self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x))
+
+ self.view = QTreeView()
+ self.view.setModel(self.model)
+
+ for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+ self.view.setColumnWidth(c, w)
+
+ self.setWidget(self.view)
+
+ AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
+
+# Action Definition
+
+def CreateAction(label, tip, callback, parent=None, shortcut=None):
+ action = QAction(label, parent)
+ if shortcut != None:
+ action.setShortcuts(shortcut)
+ action.setStatusTip(tip)
+ action.triggered.connect(callback)
+ return action
+
+# Typical application actions
+
+def CreateExitAction(app, parent=None):
+ return CreateAction("&Quit", "Exit the application", app.closeAllWindows, parent, QKeySequence.Quit)
+
+# Typical MDI actions
+
+def CreateCloseActiveWindowAction(mdi_area):
+ return CreateAction("Cl&ose", "Close the active window", mdi_area.closeActiveSubWindow, mdi_area)
+
+def CreateCloseAllWindowsAction(mdi_area):
+ return CreateAction("Close &All", "Close all the windows", mdi_area.closeAllSubWindows, mdi_area)
+
+def CreateTileWindowsAction(mdi_area):
+ return CreateAction("&Tile", "Tile the windows", mdi_area.tileSubWindows, mdi_area)
+
+def CreateCascadeWindowsAction(mdi_area):
+ return CreateAction("&Cascade", "Cascade the windows", mdi_area.cascadeSubWindows, mdi_area)
+
+def CreateNextWindowAction(mdi_area):
+ return CreateAction("Ne&xt", "Move the focus to the next window", mdi_area.activateNextSubWindow, mdi_area, QKeySequence.NextChild)
+
+def CreatePreviousWindowAction(mdi_area):
+ return CreateAction("Pre&vious", "Move the focus to the previous window", mdi_area.activatePreviousSubWindow, mdi_area, QKeySequence.PreviousChild)
+
+# Typical MDI window menu
+
+class WindowMenu():
+
+ def __init__(self, mdi_area, menu):
+ self.mdi_area = mdi_area
+ self.window_menu = menu.addMenu("&Windows")
+ self.close_active_window = CreateCloseActiveWindowAction(mdi_area)
+ self.close_all_windows = CreateCloseAllWindowsAction(mdi_area)
+ self.tile_windows = CreateTileWindowsAction(mdi_area)
+ self.cascade_windows = CreateCascadeWindowsAction(mdi_area)
+ self.next_window = CreateNextWindowAction(mdi_area)
+ self.previous_window = CreatePreviousWindowAction(mdi_area)
+ self.window_menu.aboutToShow.connect(self.Update)
+
+ def Update(self):
+ self.window_menu.clear()
+ sub_window_count = len(self.mdi_area.subWindowList())
+ have_sub_windows = sub_window_count != 0
+ self.close_active_window.setEnabled(have_sub_windows)
+ self.close_all_windows.setEnabled(have_sub_windows)
+ self.tile_windows.setEnabled(have_sub_windows)
+ self.cascade_windows.setEnabled(have_sub_windows)
+ self.next_window.setEnabled(have_sub_windows)
+ self.previous_window.setEnabled(have_sub_windows)
+ self.window_menu.addAction(self.close_active_window)
+ self.window_menu.addAction(self.close_all_windows)
+ self.window_menu.addSeparator()
+ self.window_menu.addAction(self.tile_windows)
+ self.window_menu.addAction(self.cascade_windows)
+ self.window_menu.addSeparator()
+ self.window_menu.addAction(self.next_window)
+ self.window_menu.addAction(self.previous_window)
+ if sub_window_count == 0:
+ return
+ self.window_menu.addSeparator()
+ nr = 1
+ for sub_window in self.mdi_area.subWindowList():
+ label = str(nr) + " " + sub_window.name
+ if nr < 10:
+ label = "&" + label
+ action = self.window_menu.addAction(label)
+ action.setCheckable(True)
+ action.setChecked(sub_window == self.mdi_area.activeSubWindow())
+ action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
+ self.window_menu.addAction(action)
+ nr += 1
+
+ def setActiveSubWindow(self, nr):
+ self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
+
+# Unique name for sub-windows
+
+def NumberedWindowName(name, nr):
+ if nr > 1:
+ name += " <" + str(nr) + ">"
+ return name
+
+def UniqueSubWindowName(mdi_area, name):
+ nr = 1
+ while True:
+ unique_name = NumberedWindowName(name, nr)
+ ok = True
+ for sub_window in mdi_area.subWindowList():
+ if sub_window.name == unique_name:
+ ok = False
+ break
+ if ok:
+ return unique_name
+ nr += 1
+
+# Add a sub-window
+
+def AddSubWindow(mdi_area, sub_window, name):
+ unique_name = UniqueSubWindowName(mdi_area, name)
+ sub_window.setMinimumSize(200, 100)
+ sub_window.resize(800, 600)
+ sub_window.setWindowTitle(unique_name)
+ sub_window.setAttribute(Qt.WA_DeleteOnClose)
+ sub_window.setWindowIcon(sub_window.style().standardIcon(QStyle.SP_FileIcon))
+ sub_window.name = unique_name
+ mdi_area.addSubWindow(sub_window)
+ sub_window.show()
+
# Main window
class MainWindow(QMainWindow):
@@ -298,21 +455,28 @@ class MainWindow(QMainWindow):
self.glb = glb
- self.setWindowTitle("Call Graph: " + glb.dbname)
- self.move(100, 100)
- self.resize(800, 600)
+ self.setWindowTitle("Exported SQL Viewer: " + glb.dbname)
self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
self.setMinimumSize(200, 100)
- self.model = CallGraphModel(glb)
+ self.mdi_area = QMdiArea()
+ self.mdi_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
+ self.mdi_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
- self.view = QTreeView()
- self.view.setModel(self.model)
+ self.setCentralWidget(self.mdi_area)
- for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
- self.view.setColumnWidth(c, w)
+ menu = self.menuBar()
+
+ file_menu = menu.addMenu("&File")
+ file_menu.addAction(CreateExitAction(glb.app, self))
+
+ reports_menu = menu.addMenu("&Reports")
+ reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+
+ self.window_menu = WindowMenu(self.mdi_area, menu)
- self.setCentralWidget(self.view)
+ def NewCallGraph(self):
+ CallGraphWindow(self.glb, self)
# Global data
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 29/37] perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (27 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 28/37] perf scripts python: exported-sql-viewer.py: Add support for multiple sub-windows Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 30/37] perf scripts python: exported-sql-viewer.py: Add ability to shrink / enlarge font Arnaldo Carvalho de Melo
` (8 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Add a Find bar that appears at the bottom of the call-graph window.
Committer testing:
Using:
python tools/perf/scripts/python/exported-sql-viewer.py pt_example branches calls
Using the database built in the first "Committer Testing" section in
this patch series I was able to:
"Reports"
"Context-Sensitive Call Graphs"
Control+F or select "Edit" in the top menu then "Find"
__poll<ENTER>
and find the first place where the "__poll" function appears, then
press the down arrow in the lower right corner and go to the next, etc.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-15-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/exported-sql-viewer.py | 306 ++++++++++++++++++++++-
1 file changed, 305 insertions(+), 1 deletion(-)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index c2f44351821e..0386a600ffc7 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -49,6 +49,7 @@
import sys
import weakref
import threading
+import string
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
@@ -76,6 +77,27 @@ def QueryExec(query, stmt):
if not ret:
raise Exception("Query failed: " + query.lastError().text())
+# Background thread
+
+class Thread(QThread):
+
+ done = Signal(object)
+
+ def __init__(self, task, param=None, parent=None):
+ super(Thread, self).__init__(parent)
+ self.task = task
+ self.param = param
+
+ def run(self):
+ while True:
+ if self.param is None:
+ done, result = self.task()
+ else:
+ done, result = self.task(self.param)
+ self.done.emit(result)
+ if done:
+ break
+
# Tree data model
class TreeModel(QAbstractItemModel):
@@ -157,6 +179,125 @@ def LookupCreateModel(model_name, create_fn):
model_cache_lock.release()
return model
+# Find bar
+
+class FindBar():
+
+ def __init__(self, parent, finder, is_reg_expr=False):
+ self.finder = finder
+ self.context = []
+ self.last_value = None
+ self.last_pattern = None
+
+ label = QLabel("Find:")
+ label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+ self.textbox = QComboBox()
+ self.textbox.setEditable(True)
+ self.textbox.currentIndexChanged.connect(self.ValueChanged)
+
+ self.progress = QProgressBar()
+ self.progress.setRange(0, 0)
+ self.progress.hide()
+
+ if is_reg_expr:
+ self.pattern = QCheckBox("Regular Expression")
+ else:
+ self.pattern = QCheckBox("Pattern")
+ self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+ self.next_button = QToolButton()
+ self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown))
+ self.next_button.released.connect(lambda: self.NextPrev(1))
+
+ self.prev_button = QToolButton()
+ self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp))
+ self.prev_button.released.connect(lambda: self.NextPrev(-1))
+
+ self.close_button = QToolButton()
+ self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+ self.close_button.released.connect(self.Deactivate)
+
+ self.hbox = QHBoxLayout()
+ self.hbox.setContentsMargins(0, 0, 0, 0)
+
+ self.hbox.addWidget(label)
+ self.hbox.addWidget(self.textbox)
+ self.hbox.addWidget(self.progress)
+ self.hbox.addWidget(self.pattern)
+ self.hbox.addWidget(self.next_button)
+ self.hbox.addWidget(self.prev_button)
+ self.hbox.addWidget(self.close_button)
+
+ self.bar = QWidget()
+ self.bar.setLayout(self.hbox);
+ self.bar.hide()
+
+ def Widget(self):
+ return self.bar
+
+ def Activate(self):
+ self.bar.show()
+ self.textbox.setFocus()
+
+ def Deactivate(self):
+ self.bar.hide()
+
+ def Busy(self):
+ self.textbox.setEnabled(False)
+ self.pattern.hide()
+ self.next_button.hide()
+ self.prev_button.hide()
+ self.progress.show()
+
+ def Idle(self):
+ self.textbox.setEnabled(True)
+ self.progress.hide()
+ self.pattern.show()
+ self.next_button.show()
+ self.prev_button.show()
+
+ def Find(self, direction):
+ value = self.textbox.currentText()
+ pattern = self.pattern.isChecked()
+ self.last_value = value
+ self.last_pattern = pattern
+ self.finder.Find(value, direction, pattern, self.context)
+
+ def ValueChanged(self):
+ value = self.textbox.currentText()
+ pattern = self.pattern.isChecked()
+ index = self.textbox.currentIndex()
+ data = self.textbox.itemData(index)
+ # Store the pattern in the combo box to keep it with the text value
+ if data == None:
+ self.textbox.setItemData(index, pattern)
+ else:
+ self.pattern.setChecked(data)
+ self.Find(0)
+
+ def NextPrev(self, direction):
+ value = self.textbox.currentText()
+ pattern = self.pattern.isChecked()
+ if value != self.last_value:
+ index = self.textbox.findText(value)
+ # Allow for a button press before the value has been added to the combo box
+ if index < 0:
+ index = self.textbox.count()
+ self.textbox.addItem(value, pattern)
+ self.textbox.setCurrentIndex(index)
+ return
+ else:
+ self.textbox.setItemData(index, pattern)
+ elif pattern != self.last_pattern:
+ # Keep the pattern recorded in the combo box up to date
+ index = self.textbox.currentIndex()
+ self.textbox.setItemData(index, pattern)
+ self.Find(direction)
+
+ def NotFound(self):
+ QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found")
+
# Context-sensitive call graph data model item base
class CallGraphLevelItemBase(object):
@@ -308,6 +449,123 @@ class CallGraphModel(TreeModel):
alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
return alignment[column]
+ def FindSelect(self, value, pattern, query):
+ if pattern:
+ # postgresql and sqlite pattern patching differences:
+ # postgresql LIKE is case sensitive but sqlite LIKE is not
+ # postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not
+ # postgresql supports ILIKE which is case insensitive
+ # sqlite supports GLOB (text only) which uses * and ? and is case sensitive
+ if not self.glb.dbref.is_sqlite3:
+ # Escape % and _
+ s = value.replace("%", "\%")
+ s = s.replace("_", "\_")
+ # Translate * and ? into SQL LIKE pattern characters % and _
+ trans = string.maketrans("*?", "%_")
+ match = " LIKE '" + str(s).translate(trans) + "'"
+ else:
+ match = " GLOB '" + str(value) + "'"
+ else:
+ match = " = '" + str(value) + "'"
+ QueryExec(query, "SELECT call_path_id, comm_id, thread_id"
+ " FROM calls"
+ " INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+ " INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+ " WHERE symbols.name" + match +
+ " GROUP BY comm_id, thread_id, call_path_id"
+ " ORDER BY comm_id, thread_id, call_path_id")
+
+ def FindPath(self, query):
+ # Turn the query result into a list of ids that the tree view can walk
+ # to open the tree at the right place.
+ ids = []
+ parent_id = query.value(0)
+ while parent_id:
+ ids.insert(0, parent_id)
+ q2 = QSqlQuery(self.glb.db)
+ QueryExec(q2, "SELECT parent_id"
+ " FROM call_paths"
+ " WHERE id = " + str(parent_id))
+ if not q2.next():
+ break
+ parent_id = q2.value(0)
+ # The call path root is not used
+ if ids[0] == 1:
+ del ids[0]
+ ids.insert(0, query.value(2))
+ ids.insert(0, query.value(1))
+ return ids
+
+ def Found(self, query, found):
+ if found:
+ return self.FindPath(query)
+ return []
+
+ def FindValue(self, value, pattern, query, last_value, last_pattern):
+ if last_value == value and pattern == last_pattern:
+ found = query.first()
+ else:
+ self.FindSelect(value, pattern, query)
+ found = query.next()
+ return self.Found(query, found)
+
+ def FindNext(self, query):
+ found = query.next()
+ if not found:
+ found = query.first()
+ return self.Found(query, found)
+
+ def FindPrev(self, query):
+ found = query.previous()
+ if not found:
+ found = query.last()
+ return self.Found(query, found)
+
+ def FindThread(self, c):
+ if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern:
+ ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern)
+ elif c.direction > 0:
+ ids = self.FindNext(c.query)
+ else:
+ ids = self.FindPrev(c.query)
+ return (True, ids)
+
+ def Find(self, value, direction, pattern, context, callback):
+ class Context():
+ def __init__(self, *x):
+ self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x
+ def Update(self, *x):
+ self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern)
+ if len(context):
+ context[0].Update(value, direction, pattern)
+ else:
+ context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None))
+ # Use a thread so the UI is not blocked during the SELECT
+ thread = Thread(self.FindThread, context[0])
+ thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection)
+ thread.start()
+
+ def FindDone(self, thread, callback, ids):
+ callback(ids)
+
+# Vertical widget layout
+
+class VBox():
+
+ def __init__(self, w1, w2, w3=None):
+ self.vbox = QWidget()
+ self.vbox.setLayout(QVBoxLayout());
+
+ self.vbox.layout().setContentsMargins(0, 0, 0, 0)
+
+ self.vbox.layout().addWidget(w1)
+ self.vbox.layout().addWidget(w2)
+ if w3:
+ self.vbox.layout().addWidget(w3)
+
+ def Widget(self):
+ return self.vbox
+
# Context-sensitive call graph window
class CallGraphWindow(QMdiSubWindow):
@@ -323,10 +581,45 @@ class CallGraphWindow(QMdiSubWindow):
for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
self.view.setColumnWidth(c, w)
- self.setWidget(self.view)
+ self.find_bar = FindBar(self, self)
+
+ self.vbox = VBox(self.view, self.find_bar.Widget())
+
+ self.setWidget(self.vbox.Widget())
AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
+ def DisplayFound(self, ids):
+ if not len(ids):
+ return False
+ parent = QModelIndex()
+ for dbid in ids:
+ found = False
+ n = self.model.rowCount(parent)
+ for row in xrange(n):
+ child = self.model.index(row, 0, parent)
+ if child.internalPointer().dbid == dbid:
+ found = True
+ self.view.setCurrentIndex(child)
+ parent = child
+ break
+ if not found:
+ break
+ return found
+
+ def Find(self, value, direction, pattern, context):
+ self.view.setFocus()
+ self.find_bar.Busy()
+ self.model.Find(value, direction, pattern, context, self.FindDone)
+
+ def FindDone(self, ids):
+ found = True
+ if not self.DisplayFound(ids):
+ found = False
+ self.find_bar.Idle()
+ if not found:
+ self.find_bar.NotFound()
+
# Action Definition
def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -470,11 +763,22 @@ class MainWindow(QMainWindow):
file_menu = menu.addMenu("&File")
file_menu.addAction(CreateExitAction(glb.app, self))
+ edit_menu = menu.addMenu("&Edit")
+ edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+
reports_menu = menu.addMenu("&Reports")
reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
self.window_menu = WindowMenu(self.mdi_area, menu)
+ def Find(self):
+ win = self.mdi_area.activeSubWindow()
+ if win:
+ try:
+ win.find_bar.Activate()
+ except:
+ pass
+
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 30/37] perf scripts python: exported-sql-viewer.py: Add ability to shrink / enlarge font
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (28 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 29/37] perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 31/37] perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables Arnaldo Carvalho de Melo
` (7 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Shrinking the font allows more information to display.
Committer testing:
Works, tested with the convenient Control+Shift+'+' and Control+'-' as
well with the more cumbersome top menu "Edit" + "Enlarge/Shrink font"
options.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-16-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/exported-sql-viewer.py | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 0386a600ffc7..310ba7147583 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -706,6 +706,20 @@ class WindowMenu():
def setActiveSubWindow(self, nr):
self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
+# Font resize
+
+def ResizeFont(widget, diff):
+ font = widget.font()
+ sz = font.pointSize()
+ font.setPointSize(sz + diff)
+ widget.setFont(font)
+
+def ShrinkFont(widget):
+ ResizeFont(widget, -1)
+
+def EnlargeFont(widget):
+ ResizeFont(widget, 1)
+
# Unique name for sub-windows
def NumberedWindowName(name, nr):
@@ -765,6 +779,8 @@ class MainWindow(QMainWindow):
edit_menu = menu.addMenu("&Edit")
edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+ edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
+ edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
reports_menu = menu.addMenu("&Reports")
reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
@@ -779,6 +795,14 @@ class MainWindow(QMainWindow):
except:
pass
+ def ShrinkFont(self):
+ win = self.mdi_area.activeSubWindow()
+ ShrinkFont(win.view)
+
+ def EnlargeFont(self):
+ win = self.mdi_area.activeSubWindow()
+ EnlargeFont(win.view)
+
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 31/37] perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (29 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 30/37] perf scripts python: exported-sql-viewer.py: Add ability to shrink / enlarge font Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 32/37] perf scripts python: exported-sql-viewer.py: Add All branches report Arnaldo Carvalho de Melo
` (6 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Displaying all the database tables can help make the database easier to
understand.
Committer testing:
Opened all the tables, even the sqlite master table, which I selected
everything and used control+C, lets see if it works...
CREATE VIEW threads_view AS SELECT id,machine_id,(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,process_id,pid,tid FROM threads
Humm, nope, just one of the cells got copied, even with everything selected :-)
Anyway, works as advertised, useful for perusing the data.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-17-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/exported-sql-viewer.py | 694 +++++++++++++++++++++++
1 file changed, 694 insertions(+)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 310ba7147583..ef822d850109 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -50,10 +50,15 @@ import sys
import weakref
import threading
import string
+import cPickle
+import re
+import os
from PySide.QtCore import *
from PySide.QtGui import *
from PySide.QtSql import *
from decimal import *
+from ctypes import *
+from multiprocessing import Process, Array, Value, Event
# Data formatting helpers
@@ -146,6 +151,68 @@ class TreeModel(QAbstractItemModel):
def DisplayData(self, item, index):
return item.getData(index.column())
+ def FetchIfNeeded(self, row):
+ if row > self.last_row_read:
+ self.last_row_read = row
+ if row + 10 >= self.root.child_count:
+ self.fetcher.Fetch(glb_chunk_sz)
+
+ def columnAlignment(self, column):
+ return Qt.AlignLeft
+
+ def columnFont(self, column):
+ return None
+
+ def data(self, index, role):
+ if role == Qt.TextAlignmentRole:
+ return self.columnAlignment(index.column())
+ if role == Qt.FontRole:
+ return self.columnFont(index.column())
+ if role != Qt.DisplayRole:
+ return None
+ item = index.internalPointer()
+ return self.DisplayData(item, index)
+
+# Table data model
+
+class TableModel(QAbstractTableModel):
+
+ def __init__(self, parent=None):
+ super(TableModel, self).__init__(parent)
+ self.child_count = 0
+ self.child_items = []
+ self.last_row_read = 0
+
+ def Item(self, parent):
+ if parent.isValid():
+ return parent.internalPointer()
+ else:
+ return self
+
+ def rowCount(self, parent):
+ return self.child_count
+
+ def headerData(self, section, orientation, role):
+ if role == Qt.TextAlignmentRole:
+ return self.columnAlignment(section)
+ if role != Qt.DisplayRole:
+ return None
+ if orientation != Qt.Horizontal:
+ return None
+ return self.columnHeader(section)
+
+ def index(self, row, column, parent):
+ return self.createIndex(row, column, self.child_items[row])
+
+ def DisplayData(self, item, index):
+ return item.getData(index.column())
+
+ def FetchIfNeeded(self, row):
+ if row > self.last_row_read:
+ self.last_row_read = row
+ if row + 10 >= self.child_count:
+ self.fetcher.Fetch(glb_chunk_sz)
+
def columnAlignment(self, column):
return Qt.AlignLeft
@@ -620,6 +687,601 @@ class CallGraphWindow(QMdiSubWindow):
if not found:
self.find_bar.NotFound()
+# Child data item finder
+
+class ChildDataItemFinder():
+
+ def __init__(self, root):
+ self.root = root
+ self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5
+ self.rows = []
+ self.pos = 0
+
+ def FindSelect(self):
+ self.rows = []
+ if self.pattern:
+ pattern = re.compile(self.value)
+ for child in self.root.child_items:
+ for column_data in child.data:
+ if re.search(pattern, str(column_data)) is not None:
+ self.rows.append(child.row)
+ break
+ else:
+ for child in self.root.child_items:
+ for column_data in child.data:
+ if self.value in str(column_data):
+ self.rows.append(child.row)
+ break
+
+ def FindValue(self):
+ self.pos = 0
+ if self.last_value != self.value or self.pattern != self.last_pattern:
+ self.FindSelect()
+ if not len(self.rows):
+ return -1
+ return self.rows[self.pos]
+
+ def FindThread(self):
+ if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern:
+ row = self.FindValue()
+ elif len(self.rows):
+ if self.direction > 0:
+ self.pos += 1
+ if self.pos >= len(self.rows):
+ self.pos = 0
+ else:
+ self.pos -= 1
+ if self.pos < 0:
+ self.pos = len(self.rows) - 1
+ row = self.rows[self.pos]
+ else:
+ row = -1
+ return (True, row)
+
+ def Find(self, value, direction, pattern, context, callback):
+ self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern)
+ # Use a thread so the UI is not blocked
+ thread = Thread(self.FindThread)
+ thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection)
+ thread.start()
+
+ def FindDone(self, thread, callback, row):
+ callback(row)
+
+# Number of database records to fetch in one go
+
+glb_chunk_sz = 10000
+
+# size of pickled integer big enough for record size
+
+glb_nsz = 8
+
+# Background process for SQL data fetcher
+
+class SQLFetcherProcess():
+
+ def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep):
+ # Need a unique connection name
+ conn_name = "SQLFetcher" + str(os.getpid())
+ self.db, dbname = dbref.Open(conn_name)
+ self.sql = sql
+ self.buffer = buffer
+ self.head = head
+ self.tail = tail
+ self.fetch_count = fetch_count
+ self.fetching_done = fetching_done
+ self.process_target = process_target
+ self.wait_event = wait_event
+ self.fetched_event = fetched_event
+ self.prep = prep
+ self.query = QSqlQuery(self.db)
+ self.query_limit = 0 if "$$last_id$$" in sql else 2
+ self.last_id = -1
+ self.fetched = 0
+ self.more = True
+ self.local_head = self.head.value
+ self.local_tail = self.tail.value
+
+ def Select(self):
+ if self.query_limit:
+ if self.query_limit == 1:
+ return
+ self.query_limit -= 1
+ stmt = self.sql.replace("$$last_id$$", str(self.last_id))
+ QueryExec(self.query, stmt)
+
+ def Next(self):
+ if not self.query.next():
+ self.Select()
+ if not self.query.next():
+ return None
+ self.last_id = self.query.value(0)
+ return self.prep(self.query)
+
+ def WaitForTarget(self):
+ while True:
+ self.wait_event.clear()
+ target = self.process_target.value
+ if target > self.fetched or target < 0:
+ break
+ self.wait_event.wait()
+ return target
+
+ def HasSpace(self, sz):
+ if self.local_tail <= self.local_head:
+ space = len(self.buffer) - self.local_head
+ if space > sz:
+ return True
+ if space >= glb_nsz:
+ # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer
+ nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL)
+ self.buffer[self.local_head : self.local_head + len(nd)] = nd
+ self.local_head = 0
+ if self.local_tail - self.local_head > sz:
+ return True
+ return False
+
+ def WaitForSpace(self, sz):
+ if self.HasSpace(sz):
+ return
+ while True:
+ self.wait_event.clear()
+ self.local_tail = self.tail.value
+ if self.HasSpace(sz):
+ return
+ self.wait_event.wait()
+
+ def AddToBuffer(self, obj):
+ d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL)
+ n = len(d)
+ nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL)
+ sz = n + glb_nsz
+ self.WaitForSpace(sz)
+ pos = self.local_head
+ self.buffer[pos : pos + len(nd)] = nd
+ self.buffer[pos + glb_nsz : pos + sz] = d
+ self.local_head += sz
+
+ def FetchBatch(self, batch_size):
+ fetched = 0
+ while batch_size > fetched:
+ obj = self.Next()
+ if obj is None:
+ self.more = False
+ break
+ self.AddToBuffer(obj)
+ fetched += 1
+ if fetched:
+ self.fetched += fetched
+ with self.fetch_count.get_lock():
+ self.fetch_count.value += fetched
+ self.head.value = self.local_head
+ self.fetched_event.set()
+
+ def Run(self):
+ while self.more:
+ target = self.WaitForTarget()
+ if target < 0:
+ break
+ batch_size = min(glb_chunk_sz, target - self.fetched)
+ self.FetchBatch(batch_size)
+ self.fetching_done.value = True
+ self.fetched_event.set()
+
+def SQLFetcherFn(*x):
+ process = SQLFetcherProcess(*x)
+ process.Run()
+
+# SQL data fetcher
+
+class SQLFetcher(QObject):
+
+ done = Signal(object)
+
+ def __init__(self, glb, sql, prep, process_data, parent=None):
+ super(SQLFetcher, self).__init__(parent)
+ self.process_data = process_data
+ self.more = True
+ self.target = 0
+ self.last_target = 0
+ self.fetched = 0
+ self.buffer_size = 16 * 1024 * 1024
+ self.buffer = Array(c_char, self.buffer_size, lock=False)
+ self.head = Value(c_longlong)
+ self.tail = Value(c_longlong)
+ self.local_tail = 0
+ self.fetch_count = Value(c_longlong)
+ self.fetching_done = Value(c_bool)
+ self.last_count = 0
+ self.process_target = Value(c_longlong)
+ self.wait_event = Event()
+ self.fetched_event = Event()
+ glb.AddInstanceToShutdownOnExit(self)
+ self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep))
+ self.process.start()
+ self.thread = Thread(self.Thread)
+ self.thread.done.connect(self.ProcessData, Qt.QueuedConnection)
+ self.thread.start()
+
+ def Shutdown(self):
+ # Tell the thread and process to exit
+ self.process_target.value = -1
+ self.wait_event.set()
+ self.more = False
+ self.fetching_done.value = True
+ self.fetched_event.set()
+
+ def Thread(self):
+ if not self.more:
+ return True, 0
+ while True:
+ self.fetched_event.clear()
+ fetch_count = self.fetch_count.value
+ if fetch_count != self.last_count:
+ break
+ if self.fetching_done.value:
+ self.more = False
+ return True, 0
+ self.fetched_event.wait()
+ count = fetch_count - self.last_count
+ self.last_count = fetch_count
+ self.fetched += count
+ return False, count
+
+ def Fetch(self, nr):
+ if not self.more:
+ # -1 inidcates there are no more
+ return -1
+ result = self.fetched
+ extra = result + nr - self.target
+ if extra > 0:
+ self.target += extra
+ # process_target < 0 indicates shutting down
+ if self.process_target.value >= 0:
+ self.process_target.value = self.target
+ self.wait_event.set()
+ return result
+
+ def RemoveFromBuffer(self):
+ pos = self.local_tail
+ if len(self.buffer) - pos < glb_nsz:
+ pos = 0
+ n = cPickle.loads(self.buffer[pos : pos + glb_nsz])
+ if n == 0:
+ pos = 0
+ n = cPickle.loads(self.buffer[0 : glb_nsz])
+ pos += glb_nsz
+ obj = cPickle.loads(self.buffer[pos : pos + n])
+ self.local_tail = pos + n
+ return obj
+
+ def ProcessData(self, count):
+ for i in xrange(count):
+ obj = self.RemoveFromBuffer()
+ self.process_data(obj)
+ self.tail.value = self.local_tail
+ self.wait_event.set()
+ self.done.emit(count)
+
+# Fetch more records bar
+
+class FetchMoreRecordsBar():
+
+ def __init__(self, model, parent):
+ self.model = model
+
+ self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:")
+ self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+ self.fetch_count = QSpinBox()
+ self.fetch_count.setRange(1, 1000000)
+ self.fetch_count.setValue(10)
+ self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+ self.fetch = QPushButton("Go!")
+ self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+ self.fetch.released.connect(self.FetchMoreRecords)
+
+ self.progress = QProgressBar()
+ self.progress.setRange(0, 100)
+ self.progress.hide()
+
+ self.done_label = QLabel("All records fetched")
+ self.done_label.hide()
+
+ self.spacer = QLabel("")
+
+ self.close_button = QToolButton()
+ self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+ self.close_button.released.connect(self.Deactivate)
+
+ self.hbox = QHBoxLayout()
+ self.hbox.setContentsMargins(0, 0, 0, 0)
+
+ self.hbox.addWidget(self.label)
+ self.hbox.addWidget(self.fetch_count)
+ self.hbox.addWidget(self.fetch)
+ self.hbox.addWidget(self.spacer)
+ self.hbox.addWidget(self.progress)
+ self.hbox.addWidget(self.done_label)
+ self.hbox.addWidget(self.close_button)
+
+ self.bar = QWidget()
+ self.bar.setLayout(self.hbox);
+ self.bar.show()
+
+ self.in_progress = False
+ self.model.progress.connect(self.Progress)
+
+ self.done = False
+
+ if not model.HasMoreRecords():
+ self.Done()
+
+ def Widget(self):
+ return self.bar
+
+ def Activate(self):
+ self.bar.show()
+ self.fetch.setFocus()
+
+ def Deactivate(self):
+ self.bar.hide()
+
+ def Enable(self, enable):
+ self.fetch.setEnabled(enable)
+ self.fetch_count.setEnabled(enable)
+
+ def Busy(self):
+ self.Enable(False)
+ self.fetch.hide()
+ self.spacer.hide()
+ self.progress.show()
+
+ def Idle(self):
+ self.in_progress = False
+ self.Enable(True)
+ self.progress.hide()
+ self.fetch.show()
+ self.spacer.show()
+
+ def Target(self):
+ return self.fetch_count.value() * glb_chunk_sz
+
+ def Done(self):
+ self.done = True
+ self.Idle()
+ self.label.hide()
+ self.fetch_count.hide()
+ self.fetch.hide()
+ self.spacer.hide()
+ self.done_label.show()
+
+ def Progress(self, count):
+ if self.in_progress:
+ if count:
+ percent = ((count - self.start) * 100) / self.Target()
+ if percent >= 100:
+ self.Idle()
+ else:
+ self.progress.setValue(percent)
+ if not count:
+ # Count value of zero means no more records
+ self.Done()
+
+ def FetchMoreRecords(self):
+ if self.done:
+ return
+ self.progress.setValue(0)
+ self.Busy()
+ self.in_progress = True
+ self.start = self.model.FetchMoreRecords(self.Target())
+
+# SQL data preparation
+
+def SQLTableDataPrep(query, count):
+ data = []
+ for i in xrange(count):
+ data.append(query.value(i))
+ return data
+
+# SQL table data model item
+
+class SQLTableItem():
+
+ def __init__(self, row, data):
+ self.row = row
+ self.data = data
+
+ def getData(self, column):
+ return self.data[column]
+
+# SQL table data model
+
+class SQLTableModel(TableModel):
+
+ progress = Signal(object)
+
+ def __init__(self, glb, sql, column_count, parent=None):
+ super(SQLTableModel, self).__init__(parent)
+ self.glb = glb
+ self.more = True
+ self.populated = 0
+ self.fetcher = SQLFetcher(glb, sql, lambda x, y=column_count: SQLTableDataPrep(x, y), self.AddSample)
+ self.fetcher.done.connect(self.Update)
+ self.fetcher.Fetch(glb_chunk_sz)
+
+ def DisplayData(self, item, index):
+ self.FetchIfNeeded(item.row)
+ return item.getData(index.column())
+
+ def AddSample(self, data):
+ child = SQLTableItem(self.populated, data)
+ self.child_items.append(child)
+ self.populated += 1
+
+ def Update(self, fetched):
+ if not fetched:
+ self.more = False
+ self.progress.emit(0)
+ child_count = self.child_count
+ count = self.populated - child_count
+ if count > 0:
+ parent = QModelIndex()
+ self.beginInsertRows(parent, child_count, child_count + count - 1)
+ self.insertRows(child_count, count, parent)
+ self.child_count += count
+ self.endInsertRows()
+ self.progress.emit(self.child_count)
+
+ def FetchMoreRecords(self, count):
+ current = self.child_count
+ if self.more:
+ self.fetcher.Fetch(count)
+ else:
+ self.progress.emit(0)
+ return current
+
+ def HasMoreRecords(self):
+ return self.more
+
+# SQL automatic table data model
+
+class SQLAutoTableModel(SQLTableModel):
+
+ def __init__(self, glb, table_name, parent=None):
+ sql = "SELECT * FROM " + table_name + " WHERE id > $$last_id$$ ORDER BY id LIMIT " + str(glb_chunk_sz)
+ if table_name == "comm_threads_view":
+ # For now, comm_threads_view has no id column
+ sql = "SELECT * FROM " + table_name + " WHERE comm_id > $$last_id$$ ORDER BY comm_id LIMIT " + str(glb_chunk_sz)
+ self.column_headers = []
+ query = QSqlQuery(glb.db)
+ if glb.dbref.is_sqlite3:
+ QueryExec(query, "PRAGMA table_info(" + table_name + ")")
+ while query.next():
+ self.column_headers.append(query.value(1))
+ if table_name == "sqlite_master":
+ sql = "SELECT * FROM " + table_name
+ else:
+ if table_name[:19] == "information_schema.":
+ sql = "SELECT * FROM " + table_name
+ select_table_name = table_name[19:]
+ schema = "information_schema"
+ else:
+ select_table_name = table_name
+ schema = "public"
+ QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
+ while query.next():
+ self.column_headers.append(query.value(0))
+ super(SQLAutoTableModel, self).__init__(glb, sql, len(self.column_headers), parent)
+
+ def columnCount(self, parent=None):
+ return len(self.column_headers)
+
+ def columnHeader(self, column):
+ return self.column_headers[column]
+
+# Base class for custom ResizeColumnsToContents
+
+class ResizeColumnsToContentsBase(QObject):
+
+ def __init__(self, parent=None):
+ super(ResizeColumnsToContentsBase, self).__init__(parent)
+
+ def ResizeColumnToContents(self, column, n):
+ # Using the view's resizeColumnToContents() here is extrememly slow
+ # so implement a crude alternative
+ font = self.view.font()
+ metrics = QFontMetrics(font)
+ max = 0
+ for row in xrange(n):
+ val = self.data_model.child_items[row].data[column]
+ len = metrics.width(str(val) + "MM")
+ max = len if len > max else max
+ val = self.data_model.columnHeader(column)
+ len = metrics.width(str(val) + "MM")
+ max = len if len > max else max
+ self.view.setColumnWidth(column, max)
+
+ def ResizeColumnsToContents(self):
+ n = min(self.data_model.child_count, 100)
+ if n < 1:
+ # No data yet, so connect a signal to notify when there is
+ self.data_model.rowsInserted.connect(self.UpdateColumnWidths)
+ return
+ columns = self.data_model.columnCount()
+ for i in xrange(columns):
+ self.ResizeColumnToContents(i, n)
+
+ def UpdateColumnWidths(self, *x):
+ # This only needs to be done once, so disconnect the signal now
+ self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths)
+ self.ResizeColumnsToContents()
+
+# Table window
+
+class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
+
+ def __init__(self, glb, table_name, parent=None):
+ super(TableWindow, self).__init__(parent)
+
+ self.data_model = LookupCreateModel(table_name + " Table", lambda: SQLAutoTableModel(glb, table_name))
+
+ self.model = QSortFilterProxyModel()
+ self.model.setSourceModel(self.data_model)
+
+ self.view = QTableView()
+ self.view.setModel(self.model)
+ self.view.setEditTriggers(QAbstractItemView.NoEditTriggers)
+ self.view.verticalHeader().setVisible(False)
+ self.view.sortByColumn(-1, Qt.AscendingOrder)
+ self.view.setSortingEnabled(True)
+
+ self.ResizeColumnsToContents()
+
+ self.find_bar = FindBar(self, self, True)
+
+ self.finder = ChildDataItemFinder(self.data_model)
+
+ self.fetch_bar = FetchMoreRecordsBar(self.data_model, self)
+
+ self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+ self.setWidget(self.vbox.Widget())
+
+ AddSubWindow(glb.mainwindow.mdi_area, self, table_name + " Table")
+
+ def Find(self, value, direction, pattern, context):
+ self.view.setFocus()
+ self.find_bar.Busy()
+ self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+ def FindDone(self, row):
+ self.find_bar.Idle()
+ if row >= 0:
+ self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+ else:
+ self.find_bar.NotFound()
+
+# Table list
+
+def GetTableList(glb):
+ tables = []
+ query = QSqlQuery(glb.db)
+ if glb.dbref.is_sqlite3:
+ QueryExec(query, "SELECT name FROM sqlite_master WHERE type IN ( 'table' , 'view' ) ORDER BY name")
+ else:
+ QueryExec(query, "SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type IN ( 'BASE TABLE' , 'VIEW' ) ORDER BY table_name")
+ while query.next():
+ tables.append(query.value(0))
+ if glb.dbref.is_sqlite3:
+ tables.append("sqlite_master")
+ else:
+ tables.append("information_schema.tables")
+ tables.append("information_schema.views")
+ tables.append("information_schema.columns")
+ return tables
+
# Action Definition
def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -779,12 +1441,15 @@ class MainWindow(QMainWindow):
edit_menu = menu.addMenu("&Edit")
edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+ edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)]))
edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
reports_menu = menu.addMenu("&Reports")
reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+ self.TableMenu(GetTableList(glb), menu)
+
self.window_menu = WindowMenu(self.mdi_area, menu)
def Find(self):
@@ -795,6 +1460,14 @@ class MainWindow(QMainWindow):
except:
pass
+ def FetchMoreRecords(self):
+ win = self.mdi_area.activeSubWindow()
+ if win:
+ try:
+ win.fetch_bar.Activate()
+ except:
+ pass
+
def ShrinkFont(self):
win = self.mdi_area.activeSubWindow()
ShrinkFont(win.view)
@@ -803,9 +1476,17 @@ class MainWindow(QMainWindow):
win = self.mdi_area.activeSubWindow()
EnlargeFont(win.view)
+ def TableMenu(self, tables, menu):
+ table_menu = menu.addMenu("&Tables")
+ for table in tables:
+ table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
+
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
+ def NewTableView(self, table_name):
+ TableWindow(self.glb, table_name, self)
+
# Global data
class Glb():
@@ -816,6 +1497,18 @@ class Glb():
self.dbname = dbname
self.app = None
self.mainwindow = None
+ self.instances_to_shutdown_on_exit = weakref.WeakSet()
+
+ def AddInstanceToShutdownOnExit(self, instance):
+ self.instances_to_shutdown_on_exit.add(instance)
+
+ # Shutdown any background processes or threads
+ def ShutdownInstances(self):
+ for x in self.instances_to_shutdown_on_exit:
+ try:
+ x.Shutdown()
+ except:
+ pass
# Database reference
@@ -880,6 +1573,7 @@ def Main():
glb.mainwindow = mainwindow
mainwindow.show()
err = app.exec_()
+ glb.ShutdownInstances()
db.close()
sys.exit(err)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 32/37] perf scripts python: exported-sql-viewer.py: Add All branches report
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (30 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 31/37] perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 33/37] perf script: Add --insn-trace for instruction decoding Arnaldo Carvalho de Melo
` (5 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Andi Kleen, Jiri Olsa, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Add a report to display branches in a similar fashion to perf script. The
main purpose of this report is to display disassembly, however, presently,
the only supported disassembler is Intel XED, and additionally the object
code must be present in perf build ID cache.
To use Intel XED, libxed.so must be present. To build and install
libxed.so:
git clone https://github.com/intelxed/mbuild.git mbuild
git clone https://github.com/intelxed/xed
cd xed
./mfile.py --share
sudo ./mfile.py --prefix=/usr/local install
sudo ldconfig
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181023075949.18920-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/exported-sql-viewer.py | 547 +++++++++++++++++++++++
1 file changed, 547 insertions(+)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index ef822d850109..24cb0bd56afa 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -46,6 +46,48 @@
# 'Branch Count' is the total number of branches for that function and all
# functions that it calls
+# There is also a "All branches" report, which displays branches and
+# possibly disassembly. However, presently, the only supported disassembler is
+# Intel XED, and additionally the object code must be present in perf build ID
+# cache. To use Intel XED, libxed.so must be present. To build and install
+# libxed.so:
+# git clone https://github.com/intelxed/mbuild.git mbuild
+# git clone https://github.com/intelxed/xed
+# cd xed
+# ./mfile.py --share
+# sudo ./mfile.py --prefix=/usr/local install
+# sudo ldconfig
+#
+# Example report:
+#
+# Time CPU Command PID TID Branch Type In Tx Branch
+# 8107675239590 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+# 7fab593ea260 48 89 e7 mov %rsp, %rdi
+# 8107675239899 2 ls 22011 22011 hardware interrupt No 7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675241900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+# 7fab593ea260 48 89 e7 mov %rsp, %rdi
+# 7fab593ea263 e8 c8 06 00 00 callq 0x7fab593ea930
+# 8107675241900 2 ls 22011 22011 call No 7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so)
+# 7fab593ea930 55 pushq %rbp
+# 7fab593ea931 48 89 e5 mov %rsp, %rbp
+# 7fab593ea934 41 57 pushq %r15
+# 7fab593ea936 41 56 pushq %r14
+# 7fab593ea938 41 55 pushq %r13
+# 7fab593ea93a 41 54 pushq %r12
+# 7fab593ea93c 53 pushq %rbx
+# 7fab593ea93d 48 89 fb mov %rdi, %rbx
+# 7fab593ea940 48 83 ec 68 sub $0x68, %rsp
+# 7fab593ea944 0f 31 rdtsc
+# 7fab593ea946 48 c1 e2 20 shl $0x20, %rdx
+# 7fab593ea94a 89 c0 mov %eax, %eax
+# 7fab593ea94c 48 09 c2 or %rax, %rdx
+# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax
+# 8107675242232 2 ls 22011 22011 hardware interrupt No 7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675242900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so)
+# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax
+# 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip)
+# 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+
import sys
import weakref
import threading
@@ -62,6 +104,16 @@ from multiprocessing import Process, Array, Value, Event
# Data formatting helpers
+def tohex(ip):
+ if ip < 0:
+ ip += 1 << 64
+ return "%x" % ip
+
+def offstr(offset):
+ if offset:
+ return "+0x%x" % offset
+ return ""
+
def dsoname(name):
if name == "[kernel.kallsyms]":
return "[kernel]"
@@ -1077,6 +1129,351 @@ class FetchMoreRecordsBar():
self.in_progress = True
self.start = self.model.FetchMoreRecords(self.Target())
+# Brance data model level two item
+
+class BranchLevelTwoItem():
+
+ def __init__(self, row, text, parent_item):
+ self.row = row
+ self.parent_item = parent_item
+ self.data = [""] * 8
+ self.data[7] = text
+ self.level = 2
+
+ def getParentItem(self):
+ return self.parent_item
+
+ def getRow(self):
+ return self.row
+
+ def childCount(self):
+ return 0
+
+ def hasChildren(self):
+ return False
+
+ def getData(self, column):
+ return self.data[column]
+
+# Brance data model level one item
+
+class BranchLevelOneItem():
+
+ def __init__(self, glb, row, data, parent_item):
+ self.glb = glb
+ self.row = row
+ self.parent_item = parent_item
+ self.child_count = 0
+ self.child_items = []
+ self.data = data[1:]
+ self.dbid = data[0]
+ self.level = 1
+ self.query_done = False
+
+ def getChildItem(self, row):
+ return self.child_items[row]
+
+ def getParentItem(self):
+ return self.parent_item
+
+ def getRow(self):
+ return self.row
+
+ def Select(self):
+ self.query_done = True
+
+ if not self.glb.have_disassembler:
+ return
+
+ query = QSqlQuery(self.glb.db)
+
+ QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip"
+ " FROM samples"
+ " INNER JOIN dsos ON samples.to_dso_id = dsos.id"
+ " INNER JOIN symbols ON samples.to_symbol_id = symbols.id"
+ " WHERE samples.id = " + str(self.dbid))
+ if not query.next():
+ return
+ cpu = query.value(0)
+ dso = query.value(1)
+ sym = query.value(2)
+ if dso == 0 or sym == 0:
+ return
+ off = query.value(3)
+ short_name = query.value(4)
+ long_name = query.value(5)
+ build_id = query.value(6)
+ sym_start = query.value(7)
+ ip = query.value(8)
+
+ QueryExec(query, "SELECT samples.dso_id, symbol_id, sym_offset, sym_start"
+ " FROM samples"
+ " INNER JOIN symbols ON samples.symbol_id = symbols.id"
+ " WHERE samples.id > " + str(self.dbid) + " AND cpu = " + str(cpu) +
+ " ORDER BY samples.id"
+ " LIMIT 1")
+ if not query.next():
+ return
+ if query.value(0) != dso:
+ # Cannot disassemble from one dso to another
+ return
+ bsym = query.value(1)
+ boff = query.value(2)
+ bsym_start = query.value(3)
+ if bsym == 0:
+ return
+ tot = bsym_start + boff + 1 - sym_start - off
+ if tot <= 0 or tot > 16384:
+ return
+
+ inst = self.glb.disassembler.Instruction()
+ f = self.glb.FileFromNamesAndBuildId(short_name, long_name, build_id)
+ if not f:
+ return
+ mode = 0 if Is64Bit(f) else 1
+ self.glb.disassembler.SetMode(inst, mode)
+
+ buf_sz = tot + 16
+ buf = create_string_buffer(tot + 16)
+ f.seek(sym_start + off)
+ buf.value = f.read(buf_sz)
+ buf_ptr = addressof(buf)
+ i = 0
+ while tot > 0:
+ cnt, text = self.glb.disassembler.DisassembleOne(inst, buf_ptr, buf_sz, ip)
+ if cnt:
+ byte_str = tohex(ip).rjust(16)
+ for k in xrange(cnt):
+ byte_str += " %02x" % ord(buf[i])
+ i += 1
+ while k < 15:
+ byte_str += " "
+ k += 1
+ self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
+ self.child_count += 1
+ else:
+ return
+ buf_ptr += cnt
+ tot -= cnt
+ buf_sz -= cnt
+ ip += cnt
+
+ def childCount(self):
+ if not self.query_done:
+ self.Select()
+ if not self.child_count:
+ return -1
+ return self.child_count
+
+ def hasChildren(self):
+ if not self.query_done:
+ return True
+ return self.child_count > 0
+
+ def getData(self, column):
+ return self.data[column]
+
+# Brance data model root item
+
+class BranchRootItem():
+
+ def __init__(self):
+ self.child_count = 0
+ self.child_items = []
+ self.level = 0
+
+ def getChildItem(self, row):
+ return self.child_items[row]
+
+ def getParentItem(self):
+ return None
+
+ def getRow(self):
+ return 0
+
+ def childCount(self):
+ return self.child_count
+
+ def hasChildren(self):
+ return self.child_count > 0
+
+ def getData(self, column):
+ return ""
+
+# Branch data preparation
+
+def BranchDataPrep(query):
+ data = []
+ for i in xrange(0, 8):
+ data.append(query.value(i))
+ data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+ " (" + dsoname(query.value(11)) + ")" + " -> " +
+ tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+ " (" + dsoname(query.value(15)) + ")")
+ return data
+
+# Branch data model
+
+class BranchModel(TreeModel):
+
+ progress = Signal(object)
+
+ def __init__(self, glb, event_id, where_clause, parent=None):
+ super(BranchModel, self).__init__(BranchRootItem(), parent)
+ self.glb = glb
+ self.event_id = event_id
+ self.more = True
+ self.populated = 0
+ sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
+ " CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
+ " ip, symbols.name, sym_offset, dsos.short_name,"
+ " to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+ " FROM samples"
+ " INNER JOIN comms ON comm_id = comms.id"
+ " INNER JOIN threads ON thread_id = threads.id"
+ " INNER JOIN branch_types ON branch_type = branch_types.id"
+ " INNER JOIN symbols ON symbol_id = symbols.id"
+ " INNER JOIN symbols to_symbols ON to_symbol_id = to_symbols.id"
+ " INNER JOIN dsos ON samples.dso_id = dsos.id"
+ " INNER JOIN dsos AS to_dsos ON samples.to_dso_id = to_dsos.id"
+ " WHERE samples.id > $$last_id$$" + where_clause +
+ " AND evsel_id = " + str(self.event_id) +
+ " ORDER BY samples.id"
+ " LIMIT " + str(glb_chunk_sz))
+ self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+ self.fetcher.done.connect(self.Update)
+ self.fetcher.Fetch(glb_chunk_sz)
+
+ def columnCount(self, parent=None):
+ return 8
+
+ def columnHeader(self, column):
+ return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
+
+ def columnFont(self, column):
+ if column != 7:
+ return None
+ return QFont("Monospace")
+
+ def DisplayData(self, item, index):
+ if item.level == 1:
+ self.FetchIfNeeded(item.row)
+ return item.getData(index.column())
+
+ def AddSample(self, data):
+ child = BranchLevelOneItem(self.glb, self.populated, data, self.root)
+ self.root.child_items.append(child)
+ self.populated += 1
+
+ def Update(self, fetched):
+ if not fetched:
+ self.more = False
+ self.progress.emit(0)
+ child_count = self.root.child_count
+ count = self.populated - child_count
+ if count > 0:
+ parent = QModelIndex()
+ self.beginInsertRows(parent, child_count, child_count + count - 1)
+ self.insertRows(child_count, count, parent)
+ self.root.child_count += count
+ self.endInsertRows()
+ self.progress.emit(self.root.child_count)
+
+ def FetchMoreRecords(self, count):
+ current = self.root.child_count
+ if self.more:
+ self.fetcher.Fetch(count)
+ else:
+ self.progress.emit(0)
+ return current
+
+ def HasMoreRecords(self):
+ return self.more
+
+# Branch window
+
+class BranchWindow(QMdiSubWindow):
+
+ def __init__(self, glb, event_id, name, where_clause, parent=None):
+ super(BranchWindow, self).__init__(parent)
+
+ model_name = "Branch Events " + str(event_id)
+ if len(where_clause):
+ model_name = where_clause + " " + model_name
+
+ self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, where_clause))
+
+ self.view = QTreeView()
+ self.view.setUniformRowHeights(True)
+ self.view.setModel(self.model)
+
+ self.ResizeColumnsToContents()
+
+ self.find_bar = FindBar(self, self, True)
+
+ self.finder = ChildDataItemFinder(self.model.root)
+
+ self.fetch_bar = FetchMoreRecordsBar(self.model, self)
+
+ self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+ self.setWidget(self.vbox.Widget())
+
+ AddSubWindow(glb.mainwindow.mdi_area, self, name + " Branch Events")
+
+ def ResizeColumnToContents(self, column, n):
+ # Using the view's resizeColumnToContents() here is extrememly slow
+ # so implement a crude alternative
+ mm = "MM" if column else "MMMM"
+ font = self.view.font()
+ metrics = QFontMetrics(font)
+ max = 0
+ for row in xrange(n):
+ val = self.model.root.child_items[row].data[column]
+ len = metrics.width(str(val) + mm)
+ max = len if len > max else max
+ val = self.model.columnHeader(column)
+ len = metrics.width(str(val) + mm)
+ max = len if len > max else max
+ self.view.setColumnWidth(column, max)
+
+ def ResizeColumnsToContents(self):
+ n = min(self.model.root.child_count, 100)
+ if n < 1:
+ # No data yet, so connect a signal to notify when there is
+ self.model.rowsInserted.connect(self.UpdateColumnWidths)
+ return
+ columns = self.model.columnCount()
+ for i in xrange(columns):
+ self.ResizeColumnToContents(i, n)
+
+ def UpdateColumnWidths(self, *x):
+ # This only needs to be done once, so disconnect the signal now
+ self.model.rowsInserted.disconnect(self.UpdateColumnWidths)
+ self.ResizeColumnsToContents()
+
+ def Find(self, value, direction, pattern, context):
+ self.view.setFocus()
+ self.find_bar.Busy()
+ self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+ def FindDone(self, row):
+ self.find_bar.Idle()
+ if row >= 0:
+ self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+ else:
+ self.find_bar.NotFound()
+
+# Event list
+
+def GetEventList(db):
+ events = []
+ query = QSqlQuery(db)
+ QueryExec(query, "SELECT name FROM selected_events WHERE id > 0 ORDER BY id")
+ while query.next():
+ events.append(query.value(0))
+ return events
+
# SQL data preparation
def SQLTableDataPrep(query, count):
@@ -1448,6 +1845,8 @@ class MainWindow(QMainWindow):
reports_menu = menu.addMenu("&Reports")
reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+ self.EventMenu(GetEventList(glb.db), reports_menu)
+
self.TableMenu(GetTableList(glb), menu)
self.window_menu = WindowMenu(self.mdi_area, menu)
@@ -1476,6 +1875,20 @@ class MainWindow(QMainWindow):
win = self.mdi_area.activeSubWindow()
EnlargeFont(win.view)
+ def EventMenu(self, events, reports_menu):
+ branches_events = 0
+ for event in events:
+ event = event.split(":")[0]
+ if event == "branches":
+ branches_events += 1
+ dbid = 0
+ for event in events:
+ dbid += 1
+ event = event.split(":")[0]
+ if event == "branches":
+ label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
+ reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+
def TableMenu(self, tables, menu):
table_menu = menu.addMenu("&Tables")
for table in tables:
@@ -1484,9 +1897,112 @@ class MainWindow(QMainWindow):
def NewCallGraph(self):
CallGraphWindow(self.glb, self)
+ def NewBranchView(self, event_id):
+ BranchWindow(self.glb, event_id, "", "", self)
+
def NewTableView(self, table_name):
TableWindow(self.glb, table_name, self)
+# XED Disassembler
+
+class xed_state_t(Structure):
+
+ _fields_ = [
+ ("mode", c_int),
+ ("width", c_int)
+ ]
+
+class XEDInstruction():
+
+ def __init__(self, libxed):
+ # Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
+ xedd_t = c_byte * 512
+ self.xedd = xedd_t()
+ self.xedp = addressof(self.xedd)
+ libxed.xed_decoded_inst_zero(self.xedp)
+ self.state = xed_state_t()
+ self.statep = addressof(self.state)
+ # Buffer for disassembled instruction text
+ self.buffer = create_string_buffer(256)
+ self.bufferp = addressof(self.buffer)
+
+class LibXED():
+
+ def __init__(self):
+ self.libxed = CDLL("libxed.so")
+
+ self.xed_tables_init = self.libxed.xed_tables_init
+ self.xed_tables_init.restype = None
+ self.xed_tables_init.argtypes = []
+
+ self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
+ self.xed_decoded_inst_zero.restype = None
+ self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
+
+ self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
+ self.xed_operand_values_set_mode.restype = None
+ self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
+
+ self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
+ self.xed_decoded_inst_zero_keep_mode.restype = None
+ self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
+
+ self.xed_decode = self.libxed.xed_decode
+ self.xed_decode.restype = c_int
+ self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
+
+ self.xed_format_context = self.libxed.xed_format_context
+ self.xed_format_context.restype = c_uint
+ self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
+
+ self.xed_tables_init()
+
+ def Instruction(self):
+ return XEDInstruction(self)
+
+ def SetMode(self, inst, mode):
+ if mode:
+ inst.state.mode = 4 # 32-bit
+ inst.state.width = 4 # 4 bytes
+ else:
+ inst.state.mode = 1 # 64-bit
+ inst.state.width = 8 # 8 bytes
+ self.xed_operand_values_set_mode(inst.xedp, inst.statep)
+
+ def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
+ self.xed_decoded_inst_zero_keep_mode(inst.xedp)
+ err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
+ if err:
+ return 0, ""
+ # Use AT&T mode (2), alternative is Intel (3)
+ ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
+ if not ok:
+ return 0, ""
+ # Return instruction length and the disassembled instruction text
+ # For now, assume the length is in byte 166
+ return inst.xedd[166], inst.buffer.value
+
+def TryOpen(file_name):
+ try:
+ return open(file_name, "rb")
+ except:
+ return None
+
+def Is64Bit(f):
+ result = sizeof(c_void_p)
+ # ELF support only
+ pos = f.tell()
+ f.seek(0)
+ header = f.read(7)
+ f.seek(pos)
+ magic = header[0:4]
+ eclass = ord(header[4])
+ encoding = ord(header[5])
+ version = ord(header[6])
+ if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
+ result = True if eclass == 2 else False
+ return result
+
# Global data
class Glb():
@@ -1495,9 +2011,40 @@ class Glb():
self.dbref = dbref
self.db = db
self.dbname = dbname
+ self.home_dir = os.path.expanduser("~")
+ self.buildid_dir = os.getenv("PERF_BUILDID_DIR")
+ if self.buildid_dir:
+ self.buildid_dir += "/.build-id/"
+ else:
+ self.buildid_dir = self.home_dir + "/.debug/.build-id/"
self.app = None
self.mainwindow = None
self.instances_to_shutdown_on_exit = weakref.WeakSet()
+ try:
+ self.disassembler = LibXED()
+ self.have_disassembler = True
+ except:
+ self.have_disassembler = False
+
+ def FileFromBuildId(self, build_id):
+ file_name = self.buildid_dir + build_id[0:2] + "/" + build_id[2:] + "/elf"
+ return TryOpen(file_name)
+
+ def FileFromNamesAndBuildId(self, short_name, long_name, build_id):
+ # Assume current machine i.e. no support for virtualization
+ if short_name[0:7] == "[kernel" and os.path.basename(long_name) == "kcore":
+ file_name = os.getenv("PERF_KCORE")
+ f = TryOpen(file_name) if file_name else None
+ if f:
+ return f
+ # For now, no special handling if long_name is /proc/kcore
+ f = TryOpen(long_name)
+ if f:
+ return f
+ f = self.FileFromBuildId(build_id)
+ if f:
+ return f
+ return None
def AddInstanceToShutdownOnExit(self, instance):
self.instances_to_shutdown_on_exit.add(instance)
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 33/37] perf script: Add --insn-trace for instruction decoding
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (31 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 32/37] perf scripts python: exported-sql-viewer.py: Add All branches report Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 34/37] perf script: Make itrace script default to all calls Arnaldo Carvalho de Melo
` (4 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Andi Kleen,
Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Add a --insn-trace short hand option for decoding and disassembling
instruction streams for intel_pt. This automatically pipes the output
into the xed disassembler to generate disassembled instructions. This
just makes this use model much nicer to use.
Before
% perf record -e intel_pt// ...
% perf script --itrace=i0ns --ns -F +insn,-event,-period | xed -F insn: -A -64
swapper 0 [000] 17276.429606186: ffffffff81010486 pt_config ([kernel.kallsyms]) nopl %eax, (%rax,%rax,1)
swapper 0 [000] 17276.429606186: ffffffff8101048b pt_config ([kernel.kallsyms]) add $0x10, %rsp
swapper 0 [000] 17276.429606186: ffffffff8101048f pt_config ([kernel.kallsyms]) popq %rbx
swapper 0 [000] 17276.429606186: ffffffff81010490 pt_config ([kernel.kallsyms]) popq %rbp
swapper 0 [000] 17276.429606186: ffffffff81010491 pt_config ([kernel.kallsyms]) popq %r12
swapper 0 [000] 17276.429606186: ffffffff81010493 pt_config ([kernel.kallsyms]) popq %r13
swapper 0 [000] 17276.429606186: ffffffff81010495 pt_config ([kernel.kallsyms]) popq %r14
swapper 0 [000] 17276.429606186: ffffffff81010497 pt_config ([kernel.kallsyms]) popq %r15
swapper 0 [000] 17276.429606186: ffffffff81010499 pt_config ([kernel.kallsyms]) retq
swapper 0 [000] 17276.429606186: ffffffff8101063e pt_event_add ([kernel.kallsyms]) cmpl $0x1, 0x1b0(%rbx)
swapper 0 [000] 17276.429606186: ffffffff81010645 pt_event_add ([kernel.kallsyms]) mov $0xffffffea, %eax
swapper 0 [000] 17276.429606186: ffffffff8101064a pt_event_add ([kernel.kallsyms]) mov $0x0, %edx
swapper 0 [000] 17276.429606186: ffffffff8101064f pt_event_add ([kernel.kallsyms]) popq %rbx
swapper 0 [000] 17276.429606186: ffffffff81010650 pt_event_add ([kernel.kallsyms]) cmovnz %edx, %eax
swapper 0 [000] 17276.429606186: ffffffff81010653 pt_event_add ([kernel.kallsyms]) jmp 0xffffffff81010635
swapper 0 [000] 17276.429606186: ffffffff81010635 pt_event_add ([kernel.kallsyms]) retq
swapper 0 [000] 17276.429606186: ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms]) test %eax, %eax
Now:
% perf record -e intel_pt// ...
% perf script --insn-trace --xed
... same output ...
XED needs to be installed with:
$ git clone https://github.com/intelxed/mbuild.git mbuild
$ git clone https://github.com/intelxed/xed
$ cd xed
$ ./mfile.py
$ ./mfile.py examples
$ sudo ./mfile.py --prefix=/usr/local install
$ sudo cp obj/examples/xed /usr/local/bin
$ xed | head -3
ERROR: required argument(s) were missing
Copyright (C) 2017, Intel Corporation. All rights reserved.
XED version: [v10.0-328-g7d62c8c49b7b]
$
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-2-andi@firstfloor.org
[ Fixed up whitespace damage, added the 'mfile.py examples + cp obj/examples/xed ... ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/build-xed.txt | 19 +++++++++++++++++++
tools/perf/Documentation/perf-script.txt | 7 +++++++
tools/perf/builtin-script.c | 23 +++++++++++++++++++++++
3 files changed, 49 insertions(+)
create mode 100644 tools/perf/Documentation/build-xed.txt
diff --git a/tools/perf/Documentation/build-xed.txt b/tools/perf/Documentation/build-xed.txt
new file mode 100644
index 000000000000..6222c1e7231f
--- /dev/null
+++ b/tools/perf/Documentation/build-xed.txt
@@ -0,0 +1,19 @@
+
+For --xed the xed tool is needed. Here is how to install it:
+
+ $ git clone https://github.com/intelxed/mbuild.git mbuild
+ $ git clone https://github.com/intelxed/xed
+ $ cd xed
+ $ ./mfile.py --share
+ $ ./mfile.py examples
+ $ sudo ./mfile.py --prefix=/usr/local install
+ $ sudo ldconfig
+ $ sudo cp obj/examples/xed /usr/local/bin
+
+Basic xed testing:
+
+ $ xed | head -3
+ ERROR: required argument(s) were missing
+ Copyright (C) 2017, Intel Corporation. All rights reserved.
+ XED version: [v10.0-328-g7d62c8c49b7b]
+ $
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index afdafe2110a1..00c655ab4968 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -383,6 +383,13 @@ include::itrace.txt[]
will be printed. Each entry has function name and file/line. Enabled by
default, disable with --no-inline.
+--insn-trace::
+ Show instruction stream for intel_pt traces. Combine with --xed to
+ show disassembly.
+
+--xed::
+ Run xed disassembler on output. Requires installing the xed disassembler.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ca09b7d2adb7..411ea175bcaf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -44,6 +44,7 @@
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
+#include <subcmd/pager.h>
#include "sane_ctype.h"
@@ -3103,6 +3104,24 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
#define perf_script__process_auxtrace_info 0
#endif
+static int parse_insn_trace(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ parse_output_fields(NULL, "+insn,-event,-period", 0);
+ itrace_parse_synth_opts(opt, "i0ns", 0);
+ nanosecs = true;
+ return 0;
+}
+
+static int parse_xed(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ force_pager("xed -F insn: -A -64 | less");
+ return 0;
+}
+
int cmd_script(int argc, const char **argv)
{
bool show_full_info = false;
@@ -3187,6 +3206,10 @@ int cmd_script(int argc, const char **argv)
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
+ OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+ "Decode instructions from itrace", parse_insn_trace),
+ OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
+ "Run xed disassembler on output", parse_xed),
OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
"Stop display of callgraph at these symbols"),
OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 34/37] perf script: Make itrace script default to all calls
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (32 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 33/37] perf script: Add --insn-trace for instruction decoding Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 35/37] tools script: Add --call-trace and --call-ret-trace Arnaldo Carvalho de Melo
` (3 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Andi Kleen,
Kim Phillips, Leo Yan, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
By default 'perf script' for itrace outputs sampled instructions or
branches. In my experience this is confusing to users because it's hard
to correlate with real program behavior. The sampling makes sense for
tools like 'perf report' that actually sample to reduce the run time,
but run time is normally not a problem for 'perf script'. It's better
to give an accurate representation of the program flow.
Default 'perf script' to output all calls for itrace. That's a much saner
default. The old behavior can be still requested with 'perf script'
--itrace=ibxwpe100000
v2: Fix ETM build failure
v3: Really fix ETM build failure (Kim Phillips)
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-3-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/itrace.txt | 7 ++++---
tools/perf/builtin-script.c | 5 ++++-
tools/perf/util/auxtrace.c | 17 ++++++++++++-----
tools/perf/util/auxtrace.h | 5 ++++-
tools/perf/util/cs-etm.c | 3 ++-
tools/perf/util/intel-bts.c | 3 ++-
tools/perf/util/intel-pt.c | 3 ++-
7 files changed, 30 insertions(+), 13 deletions(-)
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a3abe04c779d..c2182cbabde3 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,10 +11,11 @@
l synthesize last branch entries (use with i or x)
s skip initial number of events
- The default is all events i.e. the same as --itrace=ibxwpe
+ The default is all events i.e. the same as --itrace=ibxwpe,
+ except for perf script where it is --itrace=ce
- In addition, the period (default 100000) for instructions events
- can be specified in units of:
+ In addition, the period (default 100000, except for perf script where it is 1)
+ for instructions events can be specified in units of:
i instructions
t ticks
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 411ea175bcaf..6099c722a679 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3131,7 +3131,10 @@ int cmd_script(int argc, const char **argv)
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
- struct itrace_synth_opts itrace_synth_opts = { .set = false, };
+ struct itrace_synth_opts itrace_synth_opts = {
+ .set = false,
+ .default_no_sample = true,
+ };
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4617bcfd521..72d5ba2479bf 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -962,16 +962,23 @@ s64 perf_event__process_auxtrace(struct perf_session *session,
#define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ 64
#define PERF_ITRACE_MAX_LAST_BRANCH_SZ 1024
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+ bool no_sample)
{
- synth_opts->instructions = true;
synth_opts->branches = true;
synth_opts->transactions = true;
synth_opts->ptwrites = true;
synth_opts->pwr_events = true;
synth_opts->errors = true;
- synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
- synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ if (no_sample) {
+ synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+ synth_opts->period = 1;
+ synth_opts->calls = true;
+ } else {
+ synth_opts->instructions = true;
+ synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ }
synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
synth_opts->initial_skip = 0;
@@ -999,7 +1006,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
}
if (!str) {
- itrace_synth_opts__set_default(synth_opts);
+ itrace_synth_opts__set_default(synth_opts, false);
return 0;
}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d88f6e9eb461..8e50f96d4b23 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -58,6 +58,7 @@ enum itrace_period_type {
/**
* struct itrace_synth_opts - AUX area tracing synthesis options.
* @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
* @inject: indicates the event (not just the sample) must be fully synthesized
* because 'perf inject' will write it out
* @instructions: whether to synthesize 'instructions' events
@@ -82,6 +83,7 @@ enum itrace_period_type {
*/
struct itrace_synth_opts {
bool set;
+ bool default_no_sample;
bool inject;
bool instructions;
bool branches;
@@ -528,7 +530,8 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
union perf_event *event);
int itrace_parse_synth_opts(const struct option *opt, const char *str,
int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+ bool no_sample);
size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
void perf_session__auxtrace_error_inc(struct perf_session *session,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 2ae640257fdb..3b37d66dc533 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1432,7 +1432,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
etm->synth_opts = *session->itrace_synth_opts;
} else {
- itrace_synth_opts__set_default(&etm->synth_opts);
+ itrace_synth_opts__set_default(&etm->synth_opts,
+ session->itrace_synth_opts->default_no_sample);
etm->synth_opts.callchain = false;
}
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7f0c83b6332b..3b3a3d55dca1 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -910,7 +910,8 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
bts->synth_opts = *session->itrace_synth_opts;
} else {
- itrace_synth_opts__set_default(&bts->synth_opts);
+ itrace_synth_opts__set_default(&bts->synth_opts,
+ session->itrace_synth_opts->default_no_sample);
if (session->itrace_synth_opts)
bts->synth_opts.thread_stack =
session->itrace_synth_opts->thread_stack;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 48c1d415c6b0..ffa385a029b3 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2559,7 +2559,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
pt->synth_opts = *session->itrace_synth_opts;
} else {
- itrace_synth_opts__set_default(&pt->synth_opts);
+ itrace_synth_opts__set_default(&pt->synth_opts,
+ session->itrace_synth_opts->default_no_sample);
if (use_browser != -1) {
pt->synth_opts.branches = false;
pt->synth_opts.callchain = true;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 35/37] tools script: Add --call-trace and --call-ret-trace
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (33 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 34/37] perf script: Make itrace script default to all calls Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 36/37] perf script: Implement --graph-function Arnaldo Carvalho de Melo
` (2 subsequent siblings)
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Andi Kleen,
Kim Phillips, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Add short cut options to print PT call trace and call-ret-trace, for
calls and call and returns. Roughly corresponds to ftrace function
tracer and function graph tracer.
Just makes these common use cases nicer to use.
% perf record -a -e intel_pt// sleep 1
% perf script --call-trace
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage
% perf script --call-ret-trace
perf 900 [000] 194167.205652203: tr strt ([unknown]) pt_config
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_config
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_event_add
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_pmu_enable
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_void
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_int
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_txn
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_event_set_state.part.71
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-script.txt | 7 +++++++
tools/perf/builtin-script.c | 24 ++++++++++++++++++++++++
2 files changed, 31 insertions(+)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 00c655ab4968..805baabd238e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -390,6 +390,13 @@ include::itrace.txt[]
--xed::
Run xed disassembler on output. Requires installing the xed disassembler.
+--call-trace::
+ Show call stream for intel_pt traces. The CPUs are interleaved, but
+ can be filtered with -C.
+
+--call-ret-trace::
+ Show call and return stream for intel_pt traces.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6099c722a679..566e1450898a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3122,6 +3122,26 @@ static int parse_xed(const struct option *opt __maybe_unused,
return 0;
}
+static int parse_call_trace(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+ itrace_parse_synth_opts(opt, "cewp", 0);
+ nanosecs = true;
+ return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+ itrace_parse_synth_opts(opt, "crewp", 0);
+ nanosecs = true;
+ return 0;
+}
+
int cmd_script(int argc, const char **argv)
{
bool show_full_info = false;
@@ -3213,6 +3233,10 @@ int cmd_script(int argc, const char **argv)
"Decode instructions from itrace", parse_insn_trace),
OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
"Run xed disassembler on output", parse_xed),
+ OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+ "Decode calls from from itrace", parse_call_trace),
+ OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+ "Decode calls and returns from itrace", parse_callret_trace),
OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
"Stop display of callgraph at these symbols"),
OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 36/37] perf script: Implement --graph-function
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (34 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 35/37] tools script: Add --call-trace and --call-ret-trace Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-25 11:10 ` [PATCH 37/37] perf script: Support total cycles count Arnaldo Carvalho de Melo
2018-10-26 7:25 ` [PATCH 00/37] perf/core improvements and fixes Ingo Molnar
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Andi Kleen,
Kim Phillips, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Add a ftrace style --graph-function argument to 'perf script' that
allows to print itrace function calls only below a given function. This
makes it easier to find the code of interest in a large trace.
% perf record -e intel_pt//k -a sleep 1
% perf script --graph-function group_sched_in --call-trace
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) calc_timer_values
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_cpu
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) arch_perf_update_userpage
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __fentry__
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) using_native_sched_clock
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_stable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) group_sched_in
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) event_sched_in.isra.107
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_set_state.part.71
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_time
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_pmu_disable
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_log_itrace_start
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_userpage
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) calc_timer_values
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_cpu
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) arch_perf_update_userpage
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __fentry__
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) using_native_sched_clock
swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_stable
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-script.txt | 4 ++
tools/perf/builtin-script.c | 96 ++++++++++++++++++++++++++------
tools/perf/util/symbol.h | 3 +-
tools/perf/util/thread.h | 2 +
4 files changed, 86 insertions(+), 19 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 805baabd238e..a2b37ce48094 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -397,6 +397,10 @@ include::itrace.txt[]
--call-ret-trace::
Show call and return stream for intel_pt traces.
+--graph-function::
+ For itrace only show specified functions and their callees for
+ itrace. Multiple functions can be separated by comma.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 566e1450898a..9d2249ea75e3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1105,6 +1105,35 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample,
return printed;
}
+static const char *resolve_branch_sym(struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct addr_location *al,
+ u64 *ip)
+{
+ struct addr_location addr_al;
+ struct perf_event_attr *attr = &evsel->attr;
+ const char *name = NULL;
+
+ if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+ if (sample_addr_correlates_sym(attr)) {
+ thread__resolve(thread, &addr_al, sample);
+ if (addr_al.sym)
+ name = addr_al.sym->name;
+ else
+ *ip = sample->addr;
+ } else {
+ *ip = sample->addr;
+ }
+ } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+ if (al->sym)
+ name = al->sym->name;
+ else
+ *ip = sample->ip;
+ }
+ return name;
+}
+
static int perf_sample__fprintf_callindent(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
@@ -1112,7 +1141,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
{
struct perf_event_attr *attr = &evsel->attr;
size_t depth = thread_stack__depth(thread);
- struct addr_location addr_al;
const char *name = NULL;
static int spacing;
int len = 0;
@@ -1126,22 +1154,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
depth += 1;
- if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
- if (sample_addr_correlates_sym(attr)) {
- thread__resolve(thread, &addr_al, sample);
- if (addr_al.sym)
- name = addr_al.sym->name;
- else
- ip = sample->addr;
- } else {
- ip = sample->addr;
- }
- } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
- if (al->sym)
- name = al->sym->name;
- else
- ip = sample->ip;
- }
+ name = resolve_branch_sym(sample, evsel, thread, al, &ip);
if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
dlen += fprintf(fp, "(");
@@ -1647,6 +1660,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
}
}
+static bool show_event(struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct addr_location *al)
+{
+ int depth = thread_stack__depth(thread);
+
+ if (!symbol_conf.graph_function)
+ return true;
+
+ if (thread->filter) {
+ if (depth <= thread->filter_entry_depth) {
+ thread->filter = false;
+ return false;
+ }
+ return true;
+ } else {
+ const char *s = symbol_conf.graph_function;
+ u64 ip;
+ const char *name = resolve_branch_sym(sample, evsel, thread, al,
+ &ip);
+ unsigned nlen;
+
+ if (!name)
+ return false;
+ nlen = strlen(name);
+ while (*s) {
+ unsigned len = strcspn(s, ",");
+ if (nlen == len && !strncmp(name, s, len)) {
+ thread->filter = true;
+ thread->filter_entry_depth = depth;
+ return true;
+ }
+ s += len;
+ if (*s == ',')
+ s++;
+ }
+ return false;
+ }
+}
+
static void process_event(struct perf_script *script,
struct perf_sample *sample, struct perf_evsel *evsel,
struct addr_location *al,
@@ -1661,6 +1715,9 @@ static void process_event(struct perf_script *script,
if (output[type].fields == 0)
return;
+ if (!show_event(sample, evsel, thread, al))
+ return;
+
++es->samples;
perf_sample__fprintf_start(sample, thread, evsel,
@@ -3237,6 +3294,8 @@ int cmd_script(int argc, const char **argv)
"Decode calls from from itrace", parse_call_trace),
OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
"Decode calls and returns from itrace", parse_callret_trace),
+ OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+ "Only print symbols and callees with --call-trace/--call-ret-trace"),
OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
"Stop display of callgraph at these symbols"),
OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3494,7 +3553,8 @@ int cmd_script(int argc, const char **argv)
script.session = session;
script__setup_sample_type(&script);
- if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+ if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+ symbol_conf.graph_function)
itrace_synth_opts.thread_stack = true;
session->itrace_synth_opts = &itrace_synth_opts;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f25fae4b5743..d726a8a7bb1b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -123,7 +123,8 @@ struct symbol_conf {
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
- *field_sep;
+ *field_sep,
+ *graph_function;
const char *default_guest_vmlinux_name,
*default_guest_kallsyms,
*default_guest_modules;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa6998d..36c09a9904e6 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -42,6 +42,8 @@ struct thread {
void *addr_space;
struct unwind_libunwind_ops *unwind_libunwind_ops;
#endif
+ bool filter;
+ int filter_entry_depth;
};
struct machine;
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* [PATCH 37/37] perf script: Support total cycles count
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (35 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 36/37] perf script: Implement --graph-function Arnaldo Carvalho de Melo
@ 2018-10-25 11:10 ` Arnaldo Carvalho de Melo
2018-10-26 7:25 ` [PATCH 00/37] perf/core improvements and fixes Ingo Molnar
37 siblings, 0 replies; 39+ messages in thread
From: Arnaldo Carvalho de Melo @ 2018-10-25 11:10 UTC (permalink / raw)
To: Ingo Molnar
Cc: Clark Williams, linux-kernel, linux-perf-users, Andi Kleen,
Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
For 'perf script' brstackinsn also print a running cycles count. This
makes it easier to calculate cycle deltas for code sections measured
with LBRs.
% perf record -b -a sleep 1
% perf script -F +brstackinsn
...
00007f73ecc41083 insn: 74 06 # PRED 9 cycles [17] 1.11 IPC
00007f73ecc4108b insn: a8 10
00007f73ecc4108d insn: 74 71 # PRED 1 cycles [18] 1.00 IPC
00007f73ecc41100 insn: 48 8b 46 10
00007f73ecc41104 insn: 4c 8b 38
00007f73ecc41107 insn: 4d 85 ff
00007f73ecc4110a insn: 0f 84 b0 00 00 00
00007f73ecc41110 insn: 83 43 58 01
00007f73ecc41114 insn: 48 89 df
00007f73ecc41117 insn: e8 94 73 04 00 # PRED 6 cycles [24] 1.00 IPC
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9d2249ea75e3..b5bc85bd0bbe 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -913,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
struct perf_insn *x, u8 *inbuf, int len,
- int insn, FILE *fp)
+ int insn, FILE *fp, int *total_cycles)
{
int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
dump_insn(x, ip, inbuf, len, NULL),
@@ -922,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
en->flags.in_tx ? " INTX" : "",
en->flags.abort ? " ABORT" : "");
if (en->flags.cycles) {
- printed += fprintf(fp, " %d cycles", en->flags.cycles);
+ *total_cycles += en->flags.cycles;
+ printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
if (insn)
printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
}
@@ -979,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
u8 buffer[MAXBB];
unsigned off;
struct symbol *lastsym = NULL;
+ int total_cycles = 0;
if (!(br && br->nr))
return 0;
@@ -999,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
x.cpumode, x.cpu, &lastsym, attr, fp);
printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
- &x, buffer, len, 0, fp);
+ &x, buffer, len, 0, fp, &total_cycles);
}
/* Print all blocks */
@@ -1027,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) {
- printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+ printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+ &total_cycles);
break;
} else {
printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
--
2.14.4
^ permalink raw reply related [flat|nested] 39+ messages in thread* Re: [PATCH 00/37] perf/core improvements and fixes
2018-10-25 11:09 [PATCH 00/37] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (36 preceding siblings ...)
2018-10-25 11:10 ` [PATCH 37/37] perf script: Support total cycles count Arnaldo Carvalho de Melo
@ 2018-10-26 7:25 ` Ingo Molnar
37 siblings, 0 replies; 39+ messages in thread
From: Ingo Molnar @ 2018-10-26 7:25 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Clark Williams, linux-kernel, linux-perf-users, Adrian Hunter,
Alexander Shishkin, Alexey Budankov, Alexis Berlemont,
Andi Kleen, David Ahern, David S . Miller, David Tolnay,
Hanjun Guo, Hemant Kumar, Hendrik Brueckner, Hongxu Jia, Jin Yao,
Jiri Olsa, Josh Poimboeuf, Kim Phillips, Leo Yan, Li Bin,
Masami Hiramatsu, Michael Ellerman, Milian Wolff, Namhyung Kim,
Peter Zijlstra, Ravi Bangoria, Rudá Moura,
Sébastien Boisvert, Thomas Richter, Wang Nan, zhangmengting,
Arnaldo Carvalho de Melo
* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
> Hi Ingo,
>
> Please consider pulling,
>
> - Arnaldo
>
> Test results at the end of this message, as usual.
>
> The following changes since commit ce6c9da1113ad681bff27a3e376d2017f7f8a59c:
>
> Merge remote-tracking branch 'tip/perf/urgent' into perf/core (2018-10-18 11:13:01 -0300)
>
> are available in the Git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.20-20181025
>
> for you to fetch changes up to fe57120e18a1f9124ca758c89cc54f91333d1847:
>
> perf script: Support total cycles count (2018-10-24 15:29:56 -0300)
>
> ----------------------------------------------------------------
> perf/core improvements and fixes:
>
> - Introduce 'perf trace --max-events' for stopping 'perf trace' when
> that many syscalls (enter+exit), tracepoints or other events such as
> page faults take place.
>
> Support that as well on a per-event basis, e.g.:
>
> perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
>
> Will stop when 2 context switches, 4 block plugs, 1 block unplug and
> 3 net_dev_queue tracepoints take place. (Arnaldo Carvalho de Melo)
>
> - Poll for monitored tasks being alive in 'perf stat -p/-t', exiting when
> those tasks all terminate (Jiri Olsa)
>
> - Encode -k clockid frequency into perf.data to enable timestamps derived
> metrics conversion into wall clock time on reporting stage. (Alexey Budankov)
>
> - Improve Intel PT call graph from SQL database and GUI python scripts,
> including adopting the Qt MDI interface to allow for multiple subwindows
> for all the tables, helping in better visualizing the data in the SQL
> tables, also uses, when available, the Intel XED disassembler libraries
> to present the Intel PT data as x86 asm mnemonics. This last feature
> is not currently working in some cases, fix is being discussed (Adrian Hunter)
>
> - Implement a ftrace function_graph view in 'perf script' when processing
> hardware trace data such as Intel PT (Andi Kleen)
>
> - Better integration with the Intel XED disassembler, when available, in
> 'perf script' (Andi Kleen)
>
> - Some 'perf trace' drop refcount fixes (Arnaldo Carvalho de Melo)
>
> - Add Sparc support to 'perf annotate', jitdump (David Miller)
>
> - Fix PLT symbols entry/header sizes properly on Sparc (David Miller)
>
> - Fix generation of system call table failure with /tmp mounted with 'noexec'
> in arm64 (Hongxu Jia)
>
> - Allow extended console debug output in 'perf script' (Milian Wolff)
>
> - Flush output stream after events in 'perf script' verbose mode (Milian Wolff)
>
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> ----------------------------------------------------------------
> Adrian Hunter (17):
> perf scripts python: call-graph-from-sql.py: Use SPDX license identifier
> perf scripts python: call-graph-from-sql.py: Provide better default column sizes
> perf scripts python: call-graph-from-sql.py: Set a minimum window size
> perf scripts python: call-graph-from-sql.py: Change icon
> perf scripts python: call-graph-from-sql.py: Make a "Main" function
> perf scripts python: call-graph-from-sql.py: Separate the database details into a class
> perf scripts python: call-graph-from-sql.py: Add a class for global data
> perf scripts python: call-graph-from-sql.py: Remove use of setObjectName()
> perf scripts python: call-graph-from-sql.py: Factor out CallGraphModel from TreeModel
> perf scripts python: call-graph-from-sql.py: Add data helper functions
> perf scripts python: call-graph-from-sql.py: Refactor TreeItem class
> perf scripts python: call-graph-from-sql.py: Rename to exported-sql-viewer.py
> perf scripts python: exported-sql-viewer.py: Add support for multiple sub-windows
> perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph
> perf scripts python: exported-sql-viewer.py: Add ability to shrink / enlarge font
> perf scripts python: exported-sql-viewer.py: Add ability to display all the database tables
> perf scripts python: exported-sql-viewer.py: Add All branches report
>
> Alexey Budankov (1):
> perf record: Encode -k clockid frequency into Perf trace
>
> Andi Kleen (5):
> perf script: Add --insn-trace for instruction decoding
> perf script: Make itrace script default to all calls
> tools script: Add --call-trace and --call-ret-trace
> perf script: Implement --graph-function
> perf script: Support total cycles count
>
> Arnaldo Carvalho de Melo (7):
> tools lib subcmd: Introduce OPTION_ULONG
> perf trace: Introduce --max-events
> perf evsel: Introduce per event max_events property
> perf evsel: Mark a evsel as disabled when asking the kernel do disable it
> perf trace: Drop addr_location refcounts
> perf trace: Drop thread refcount in trace__event_handler()
> perf trace: Introduce per-event maximum number of events property
>
> David Miller (3):
> perf annotate: Add Sparc support
> perf jitdump: Add Sparc support.
> perf symbols: Set PLT entry/header sizes properly on Sparc
>
> Hongxu Jia (1):
> perf arm64: Fix generate system call table failed with /tmp mounted with noexec
>
> Jiri Olsa (1):
> perf stat: Poll for monitored tasks being alive
>
> Milian Wolff (2):
> perf script: Allow extended console debug output
> perf script: Flush output stream after events in verbose mode
>
> tools/lib/subcmd/parse-options.c | 19 +
> tools/lib/subcmd/parse-options.h | 2 +
> tools/perf/Documentation/build-xed.txt | 19 +
> tools/perf/Documentation/intel-pt.txt | 2 +-
> tools/perf/Documentation/itrace.txt | 7 +-
> tools/perf/Documentation/perf-script.txt | 18 +
> tools/perf/Documentation/perf-trace.txt | 67 +
> tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 2 +-
> tools/perf/arch/sparc/Makefile | 2 +
> tools/perf/arch/sparc/annotate/instructions.c | 169 ++
> tools/perf/builtin-record.c | 24 +-
> tools/perf/builtin-script.c | 166 +-
> tools/perf/builtin-stat.c | 24 +
> tools/perf/builtin-trace.c | 50 +-
> tools/perf/perf.h | 1 +
> tools/perf/scripts/python/call-graph-from-sql.py | 339 ----
> tools/perf/scripts/python/export-to-postgresql.py | 2 +-
> tools/perf/scripts/python/export-to-sqlite.py | 2 +-
> tools/perf/scripts/python/exported-sql-viewer.py | 2128 +++++++++++++++++++++
> tools/perf/util/annotate.c | 8 +
> tools/perf/util/auxtrace.c | 17 +-
> tools/perf/util/auxtrace.h | 5 +-
> tools/perf/util/cs-etm.c | 3 +-
> tools/perf/util/env.h | 1 +
> tools/perf/util/evlist.c | 2 +-
> tools/perf/util/evsel.c | 27 +-
> tools/perf/util/evsel.h | 5 +
> tools/perf/util/genelf.h | 6 +
> tools/perf/util/header.c | 23 +
> tools/perf/util/header.h | 1 +
> tools/perf/util/intel-bts.c | 3 +-
> tools/perf/util/intel-pt.c | 3 +-
> tools/perf/util/parse-events.c | 8 +
> tools/perf/util/parse-events.h | 1 +
> tools/perf/util/parse-events.l | 1 +
> tools/perf/util/symbol-elf.c | 12 +-
> tools/perf/util/symbol.h | 3 +-
> tools/perf/util/thread.h | 2 +
> 38 files changed, 2778 insertions(+), 396 deletions(-)
> create mode 100644 tools/perf/Documentation/build-xed.txt
> create mode 100644 tools/perf/arch/sparc/annotate/instructions.c
> delete mode 100644 tools/perf/scripts/python/call-graph-from-sql.py
> create mode 100755 tools/perf/scripts/python/exported-sql-viewer.py
Pulled, thanks a lot Arnaldo!
Ingo
^ permalink raw reply [flat|nested] 39+ messages in thread