[PATCH 1/3] perf script: Fix --max-blocks man page description

[PATCH 1/3] perf script: Fix --max-blocks man page description

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

The --max-blocks description was using the old name brstackasm.
Use brstackinsn instead.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index d4e2e18a5881..042b9e5dcc32 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -384,7 +384,7 @@ include::itrace.txt[]
 	perf script --time 0%-10%,30%-40%
 
 --max-blocks::
-	Set the maximum number of program blocks to print with brstackasm for
+	Set the maximum number of program blocks to print with brstackinsn for
 	each sample.
 
 --reltime::
-- 
2.20.1

[PATCH 2/3] perf script: Fix off by one in brstackinsn IPC computation

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When we hit the end of a program block, need to count the last instruction
too for the IPC computation. This caused large errors for small blocks.

% perf script -b ls / > /dev/null

Before:

% perf script -F +brstackinsn --xed
...
        00007f94c9ac70d8                        jz 0x7f94c9ac70e3                       # PRED 3 cycles [36] 4.33 IPC
        00007f94c9ac70e3                        testb  $0x20, 0x31d(%rbx)
        00007f94c9ac70ea                        jnz 0x7f94c9ac70b0
        00007f94c9ac70ec                        testb  $0x8, 0x205ad(%rip)
        00007f94c9ac70f3                        jz 0x7f94c9ac6ff0               # PRED 1 cycles [37] 3.00 IPC

After:

% perf script -F +brstackinsn --xed
...
        00007f94c9ac70d8                        jz 0x7f94c9ac70e3                       # PRED 3 cycles [15] 4.67 IPC
        00007f94c9ac70e3                        testb  $0x20, 0x31d(%rbx)
        00007f94c9ac70ea                        jnz 0x7f94c9ac70b0
        00007f94c9ac70ec                        testb  $0x8, 0x205ad(%rip)
        00007f94c9ac70f3                        jz 0x7f94c9ac6ff0               # PRED 1 cycles [16] 4.00 IPC

Suggested-by: Denis Bakhvalov <denis.bakhvalov@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-script.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f6232f1bfdc..9a63cb3442a9 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1059,7 +1059,7 @@ 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);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
-- 
2.20.1

[PATCH 3/3] perf script: Improve man page description of metrics

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Clarify that a metric is based on events, not referring
to itself. Also some improvements with the sentences.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 042b9e5dcc32..caaab28f8400 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -228,11 +228,11 @@ OPTIONS
 
 	With the metric option perf script can compute metrics for
 	sampling periods, similar to perf stat. This requires
-	specifying a group with multiple metrics with the :S option
+	specifying a group with multiple events defining metrics with the :S option
 	for perf record. perf will sample on the first event, and
-	compute metrics for all the events in the group. Please note
+	print computed metrics for all the events in the group. Please note
 	that the metric computed is averaged over the whole sampling
-	period, not just for the sample point.
+	period (since the last sample), not just for the sample point.
 
 	For sample events it's possible to display misc field with -F +misc option,
 	following letters are displayed for each bit:
-- 
2.20.1

Re: [PATCH 1/3] perf script: Fix --max-blocks man page description

[Arnaldo Carvalho de Melo]

Em Thu, Jul 11, 2019 at 11:19:20AM -0700, Andi Kleen escreveu:
> From: Andi Kleen <ak@linux.intel.com>
> 
> The --max-blocks description was using the old name brstackasm.
> Use brstackinsn instead.

Thanks, applied.

- Arnaldo

Re: [PATCH 2/3] perf script: Fix off by one in brstackinsn IPC computation

[Arnaldo Carvalho de Melo]

Em Thu, Jul 11, 2019 at 11:19:21AM -0700, Andi Kleen escreveu:
> From: Andi Kleen <ak@linux.intel.com>
> 
> When we hit the end of a program block, need to count the last instruction
> too for the IPC computation. This caused large errors for small blocks.
> 
> % perf script -b ls / > /dev/null
> 
> Before:

Thanks, applied.

- Arnaldo

Re: [PATCH 3/3] perf script: Improve man page description of metrics

[Arnaldo Carvalho de Melo]

Em Thu, Jul 11, 2019 at 11:19:22AM -0700, Andi Kleen escreveu:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Clarify that a metric is based on events, not referring
> to itself. Also some improvements with the sentences.

Thanks, applied.