From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Petr Mladek <pmladek@suse.com>,
Andrey Zhizhikin <andrey.z@gmail.com>,
Kefeng Wang <wangkefeng.wang@huawei.com>,
Thomas Gleixner <tglx@linutronix.de>,
Kan Liang <kan.liang@linux.intel.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Cc: Stephane Eranian <eranian@google.com>, Ian Rogers <irogers@google.com>
Subject: [PATCH 5/5] perf synthetic events: Remove use of sscanf from /proc reading
Date: Wed, 1 Apr 2020 16:39:45 -0700 [thread overview]
Message-ID: <20200401233945.133550-6-irogers@google.com> (raw)
In-Reply-To: <20200401233945.133550-1-irogers@google.com>
The synthesize benchmark, run on a single process and thread, shows
perf_event__synthesize_mmap_events as the hottest function with fgets
and sscanf taking the majority of execution time. fscanf performs
similarly well. Replace the scanf call with manual reading of each field
of the /proc/pid/maps line, and remove some unnecessary buffering.
This change also addresses potential, but unlikely, buffer overruns for
the string values read by scanf.
Performance before is:
Average synthesis took: 120.195100 usec
Average data synthesis took: 156.582300 usec
And after is:
Average synthesis took: 67.189100 usec
Average data synthesis took: 102.451600 usec
On a Intel Xeon 6154 compiling with Debian gcc 9.2.1.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/synthetic-events.c | 157 +++++++++++++++++++----------
1 file changed, 105 insertions(+), 52 deletions(-)
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 1f3d8d4bb879..64e010689a5f 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -36,6 +36,7 @@
#include <string.h>
#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include <api/fs/fs.h>
+#include <api/io.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
@@ -272,6 +273,79 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
return 0;
}
+static bool read_proc_maps_line(struct io *io, __u64 *start, __u64 *end,
+ u32 *prot, u32 *flags, __u64 *offset,
+ u32 *maj, u32 *min,
+ __u64 *inode,
+ ssize_t pathname_size, char *pathname)
+{
+ __u64 temp;
+ int ch;
+ char *start_pathname = pathname;
+
+ if (get_hex(io, start) != '-')
+ return false;
+ if (get_hex(io, end) != ' ')
+ return false;
+
+ /* map protection and flags bits */
+ *prot = 0;
+ ch = get_char(io);
+ if (ch == 'r')
+ *prot |= PROT_READ;
+ else if (ch != '-')
+ return false;
+ ch = get_char(io);
+ if (ch == 'w')
+ *prot |= PROT_WRITE;
+ else if (ch != '-')
+ return false;
+ ch = get_char(io);
+ if (ch == 'x')
+ *prot |= PROT_EXEC;
+ else if (ch != '-')
+ return false;
+ ch = get_char(io);
+ if (ch == 's')
+ *flags = MAP_SHARED;
+ else if (ch == 'p')
+ *flags = MAP_PRIVATE;
+ else
+ return false;
+ if (get_char(io) != ' ')
+ return false;
+
+ if (get_hex(io, offset) != ' ')
+ return false;
+
+ if (get_hex(io, &temp) != ':')
+ return false;
+ *maj = temp;
+ if (get_hex(io, &temp) != ' ')
+ return false;
+ *min = temp;
+
+ ch = get_dec(io, inode);
+ if (ch != ' ') {
+ *pathname = '\0';
+ return ch == '\n';
+ }
+ do {
+ ch = get_char(io);
+ } while (ch == ' ');
+ while (true) {
+ if (ch < 0)
+ return false;
+ if (ch == '\0' || ch == '\n' ||
+ (pathname + 1 - start_pathname) >= pathname_size) {
+ *pathname = '\0';
+ return true;
+ }
+ *pathname++ = ch;
+ ch = get_char(io);
+ }
+}
+
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
@@ -279,9 +353,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
struct machine *machine,
bool mmap_data)
{
- FILE *fp;
unsigned long long t;
char bf[BUFSIZ];
+ struct io io;
bool truncation = false;
unsigned long long timeout = proc_map_timeout * 1000000ULL;
int rc = 0;
@@ -294,28 +368,39 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
snprintf(bf, sizeof(bf), "%s/proc/%d/task/%d/maps",
machine->root_dir, pid, pid);
- fp = fopen(bf, "r");
- if (fp == NULL) {
+ io.fd = open(bf, O_RDONLY, 0);
+ if (io.fd < 0) {
/*
* We raced with a task exiting - just return:
*/
pr_debug("couldn't open %s\n", bf);
return -1;
}
+ init_io(&io, io.fd, bf, sizeof(bf));
event->header.type = PERF_RECORD_MMAP2;
t = rdclock();
- while (1) {
- char prot[5];
- char execname[PATH_MAX];
- char anonstr[] = "//anon";
- unsigned int ino;
+ while (!io.eof) {
+ static const char anonstr[] = "//anon";
size_t size;
- ssize_t n;
- if (fgets(bf, sizeof(bf), fp) == NULL)
- break;
+ /* ensure null termination since stack will be reused. */
+ strcpy(event->mmap2.filename, "");
+
+ /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
+ if (!read_proc_maps_line(&io,
+ &event->mmap2.start,
+ &event->mmap2.len,
+ &event->mmap2.prot,
+ &event->mmap2.flags,
+ &event->mmap2.pgoff,
+ &event->mmap2.maj,
+ &event->mmap2.min,
+ &event->mmap2.ino,
+ sizeof(event->mmap2.filename),
+ event->mmap2.filename))
+ continue;
if ((rdclock() - t) > timeout) {
pr_warning("Reading %s/proc/%d/task/%d/maps time out. "
@@ -326,23 +411,6 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
goto out;
}
- /* ensure null termination since stack will be reused. */
- strcpy(execname, "");
-
- /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
- n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
- &event->mmap2.start, &event->mmap2.len, prot,
- &event->mmap2.pgoff, &event->mmap2.maj,
- &event->mmap2.min,
- &ino, execname);
-
- /*
- * Anon maps don't have the execname.
- */
- if (n < 7)
- continue;
-
- event->mmap2.ino = (u64)ino;
event->mmap2.ino_generation = 0;
/*
@@ -353,23 +421,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
else
event->header.misc = PERF_RECORD_MISC_GUEST_USER;
- /* map protection and flags bits */
- event->mmap2.prot = 0;
- event->mmap2.flags = 0;
- if (prot[0] == 'r')
- event->mmap2.prot |= PROT_READ;
- if (prot[1] == 'w')
- event->mmap2.prot |= PROT_WRITE;
- if (prot[2] == 'x')
- event->mmap2.prot |= PROT_EXEC;
-
- if (prot[3] == 's')
- event->mmap2.flags |= MAP_SHARED;
- else
- event->mmap2.flags |= MAP_PRIVATE;
-
- if (prot[2] != 'x') {
- if (!mmap_data || prot[0] != 'r')
+ if ((event->mmap2.prot & PROT_EXEC) == 0) {
+ if (!mmap_data || (event->mmap2.prot & PROT_READ) == 0)
continue;
event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -379,17 +432,17 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
if (truncation)
event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
- if (!strcmp(execname, ""))
- strcpy(execname, anonstr);
+ if (!strcmp(event->mmap2.filename, ""))
+ strcpy(event->mmap2.filename, anonstr);
if (hugetlbfs_mnt_len &&
- !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
- strcpy(execname, anonstr);
+ !strncmp(event->mmap2.filename, hugetlbfs_mnt,
+ hugetlbfs_mnt_len)) {
+ strcpy(event->mmap2.filename, anonstr);
event->mmap2.flags |= MAP_HUGETLB;
}
- size = strlen(execname) + 1;
- memcpy(event->mmap2.filename, execname, size);
+ size = strlen(event->mmap2.filename) + 1;
size = PERF_ALIGN(size, sizeof(u64));
event->mmap2.len -= event->mmap.start;
event->mmap2.header.size = (sizeof(event->mmap2) -
@@ -408,7 +461,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
break;
}
- fclose(fp);
+ close(io.fd);
return rc;
}
--
2.26.0.rc2.310.g2932bb562d-goog
next prev parent reply other threads:[~2020-04-01 23:40 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-01 23:39 [PATCH 0/5] Benchmark and improve event synthesis performance Ian Rogers
2020-04-01 23:39 ` [PATCH 1/5] perf bench: add event synthesis benchmark Ian Rogers
2020-04-02 13:41 ` Jiri Olsa
2020-04-01 23:39 ` [PATCH 2/5] tools api fs: make xxx__mountpoint() more scalable Ian Rogers
2020-04-01 23:39 ` [PATCH 3/5] perf synthetic-events: save 4kb from 2 stack frames Ian Rogers
2020-04-01 23:39 ` [PATCH 4/5] tools api: add a lightweight buffered reading api Ian Rogers
2020-04-02 13:41 ` Jiri Olsa
2020-04-01 23:39 ` Ian Rogers [this message]
2020-04-02 13:40 ` [PATCH 5/5] perf synthetic events: Remove use of sscanf from /proc reading Jiri Olsa
2020-04-02 13:41 ` Jiri Olsa
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200401233945.133550-6-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=andrey.z@gmail.com \
--cc=eranian@google.com \
--cc=jolsa@redhat.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
--cc=tglx@linutronix.de \
--cc=wangkefeng.wang@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).