* [PATCH] Minor improvements for perf script flamegraph
@ 2025-06-03 7:10 Tianyou Li
2025-06-10 1:19 ` Namhyung Kim
0 siblings, 1 reply; 3+ messages in thread
From: Tianyou Li @ 2025-06-03 7:10 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim
Cc: Mark Rutland, Alexander Shishkin, Jiri Olsa, Ian Rogers,
Adrian Hunter, Kan Liang, tianyou.li, wangyang.guo, pan.deng,
zhiguo.zhou, tim.c.chen, tim.c.chen, linux-perf-users,
linux-kernel
When processing the perf data file generated with multiple events,
the flamegraph script will count all the events regardless of
different event names. If specify the perf data file with -i option,
the script will try to read the header information regardless of
the file name specified, instead it will try to access the perf.data.
This patch tries to add a -e option to specify the event name that
the flamegraph will be generated accordingly. If the -e option omitted,
the behavior remains unchanged. If the -i option specified, the header
information will be read from that file.
Signed-off-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Pan Deng <pan.deng@intel.com>
Reviewed-by: Zhiguo Zhou <zhiguo.zhou@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
---
tools/perf/scripts/python/flamegraph.py | 21 +++++++++++++++++++--
1 file changed, 19 insertions(+), 2 deletions(-)
diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py
index cf7ce8229a..eb78b93925 100755
--- a/tools/perf/scripts/python/flamegraph.py
+++ b/tools/perf/scripts/python/flamegraph.py
@@ -94,6 +94,11 @@ class FlameGraphCLI:
return child
def process_event(self, event):
+ # ignore events where the event name does not match
+ # the one specified by the user
+ if self.args.event_name and event.get("ev_name") != self.args.event_name:
+ return
+
pid = event.get("sample", {}).get("pid", 0)
# event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
# for user-space processes; let's use pid for kernel or user-space distinction
@@ -123,8 +128,15 @@ class FlameGraphCLI:
return ""
try:
- output = subprocess.check_output(["perf", "report", "--header-only"])
- return output.decode("utf-8")
+ if self.args.input:
+ output = subprocess.check_output(["perf", "script", "--header-only", "-i", self.args.input])
+ else:
+ output = subprocess.check_output(["perf", "report", "--header-only"])
+
+ result = output.decode("utf-8")
+ if self.args.event_name:
+ result += "\nFocused event: " + self.args.event_name
+ return result
except Exception as err: # pylint: disable=broad-except
print("Error reading report header: {}".format(err), file=sys.stderr)
return ""
@@ -235,6 +247,11 @@ if __name__ == "__main__":
default=False,
action="store_true",
help="allow unprompted downloading of HTML template")
+ parser.add_argument("-e", "--event",
+ default="",
+ dest="event_name",
+ type=str,
+ help="specify the event to generate flamegraph for")
cli_args = parser.parse_args()
cli = FlameGraphCLI(cli_args)
--
2.43.5
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] Minor improvements for perf script flamegraph
2025-06-03 7:10 [PATCH] Minor improvements for perf script flamegraph Tianyou Li
@ 2025-06-10 1:19 ` Namhyung Kim
2025-06-10 3:20 ` Li, Tianyou
0 siblings, 1 reply; 3+ messages in thread
From: Namhyung Kim @ 2025-06-10 1:19 UTC (permalink / raw)
To: Tianyou Li
Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Mark Rutland, Alexander Shishkin, Jiri Olsa, Ian Rogers,
Adrian Hunter, Kan Liang, wangyang.guo, pan.deng, zhiguo.zhou,
tim.c.chen, tim.c.chen, linux-perf-users, linux-kernel
Hello,
On Tue, Jun 03, 2025 at 03:10:48PM +0800, Tianyou Li wrote:
> When processing the perf data file generated with multiple events,
> the flamegraph script will count all the events regardless of
> different event names. If specify the perf data file with -i option,
> the script will try to read the header information regardless of
> the file name specified, instead it will try to access the perf.data.
>
> This patch tries to add a -e option to specify the event name that
> the flamegraph will be generated accordingly. If the -e option omitted,
> the behavior remains unchanged. If the -i option specified, the header
> information will be read from that file.
Looks like two separate changes. Can you please split them?
Thanks,
Namhyung
>
> Signed-off-by: Tianyou Li <tianyou.li@intel.com>
> Reviewed-by: Pan Deng <pan.deng@intel.com>
> Reviewed-by: Zhiguo Zhou <zhiguo.zhou@intel.com>
> Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
> ---
> tools/perf/scripts/python/flamegraph.py | 21 +++++++++++++++++++--
> 1 file changed, 19 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py
> index cf7ce8229a..eb78b93925 100755
> --- a/tools/perf/scripts/python/flamegraph.py
> +++ b/tools/perf/scripts/python/flamegraph.py
> @@ -94,6 +94,11 @@ class FlameGraphCLI:
> return child
>
> def process_event(self, event):
> + # ignore events where the event name does not match
> + # the one specified by the user
> + if self.args.event_name and event.get("ev_name") != self.args.event_name:
> + return
> +
> pid = event.get("sample", {}).get("pid", 0)
> # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
> # for user-space processes; let's use pid for kernel or user-space distinction
> @@ -123,8 +128,15 @@ class FlameGraphCLI:
> return ""
>
> try:
> - output = subprocess.check_output(["perf", "report", "--header-only"])
> - return output.decode("utf-8")
> + if self.args.input:
> + output = subprocess.check_output(["perf", "script", "--header-only", "-i", self.args.input])
> + else:
> + output = subprocess.check_output(["perf", "report", "--header-only"])
> +
> + result = output.decode("utf-8")
> + if self.args.event_name:
> + result += "\nFocused event: " + self.args.event_name
> + return result
> except Exception as err: # pylint: disable=broad-except
> print("Error reading report header: {}".format(err), file=sys.stderr)
> return ""
> @@ -235,6 +247,11 @@ if __name__ == "__main__":
> default=False,
> action="store_true",
> help="allow unprompted downloading of HTML template")
> + parser.add_argument("-e", "--event",
> + default="",
> + dest="event_name",
> + type=str,
> + help="specify the event to generate flamegraph for")
>
> cli_args = parser.parse_args()
> cli = FlameGraphCLI(cli_args)
> --
> 2.43.5
>
^ permalink raw reply [flat|nested] 3+ messages in thread
* RE: [PATCH] Minor improvements for perf script flamegraph
2025-06-10 1:19 ` Namhyung Kim
@ 2025-06-10 3:20 ` Li, Tianyou
0 siblings, 0 replies; 3+ messages in thread
From: Li, Tianyou @ 2025-06-10 3:20 UTC (permalink / raw)
To: Namhyung Kim
Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Mark Rutland, Alexander Shishkin, Jiri Olsa, Ian Rogers,
Hunter, Adrian, Kan Liang, Guo, Wangyang, Deng, Pan, Zhou, Zhiguo,
Chen, Tim C, tim.c.chen@linux.intel.com,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Hi Namhyung,
Thanks for your review and suggestions. I have split the patch into two patches. Please let me know if anything else is needed. Thanks.
Regards,
Tianyou
-----Original Message-----
From: Namhyung Kim <namhyung@kernel.org>
Sent: Tuesday, June 10, 2025 9:20 AM
To: Li, Tianyou <tianyou.li@intel.com>
Cc: 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@kernel.org>; Ian Rogers <irogers@google.com>; Hunter, Adrian <adrian.hunter@intel.com>; Kan Liang <kan.liang@linux.intel.com>; Guo, Wangyang <wangyang.guo@intel.com>; Deng, Pan <pan.deng@intel.com>; Zhou, Zhiguo <zhiguo.zhou@intel.com>; Chen, Tim C <tim.c.chen@intel.com>; tim.c.chen@linux.intel.com; linux-perf-users@vger.kernel.org; linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Minor improvements for perf script flamegraph
Hello,
On Tue, Jun 03, 2025 at 03:10:48PM +0800, Tianyou Li wrote:
> When processing the perf data file generated with multiple events, the
> flamegraph script will count all the events regardless of different
> event names. If specify the perf data file with -i option, the script
> will try to read the header information regardless of the file name
> specified, instead it will try to access the perf.data.
>
> This patch tries to add a -e option to specify the event name that the
> flamegraph will be generated accordingly. If the -e option omitted,
> the behavior remains unchanged. If the -i option specified, the header
> information will be read from that file.
Looks like two separate changes. Can you please split them?
Thanks,
Namhyung
>
> Signed-off-by: Tianyou Li <tianyou.li@intel.com>
> Reviewed-by: Pan Deng <pan.deng@intel.com>
> Reviewed-by: Zhiguo Zhou <zhiguo.zhou@intel.com>
> Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
> ---
> tools/perf/scripts/python/flamegraph.py | 21 +++++++++++++++++++--
> 1 file changed, 19 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/scripts/python/flamegraph.py
> b/tools/perf/scripts/python/flamegraph.py
> index cf7ce8229a..eb78b93925 100755
> --- a/tools/perf/scripts/python/flamegraph.py
> +++ b/tools/perf/scripts/python/flamegraph.py
> @@ -94,6 +94,11 @@ class FlameGraphCLI:
> return child
>
> def process_event(self, event):
> + # ignore events where the event name does not match
> + # the one specified by the user
> + if self.args.event_name and event.get("ev_name") != self.args.event_name:
> + return
> +
> pid = event.get("sample", {}).get("pid", 0)
> # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux
> # for user-space processes; let's use pid for kernel or
> user-space distinction @@ -123,8 +128,15 @@ class FlameGraphCLI:
> return ""
>
> try:
> - output = subprocess.check_output(["perf", "report", "--header-only"])
> - return output.decode("utf-8")
> + if self.args.input:
> + output = subprocess.check_output(["perf", "script", "--header-only", "-i", self.args.input])
> + else:
> + output = subprocess.check_output(["perf", "report",
> + "--header-only"])
> +
> + result = output.decode("utf-8")
> + if self.args.event_name:
> + result += "\nFocused event: " + self.args.event_name
> + return result
> except Exception as err: # pylint: disable=broad-except
> print("Error reading report header: {}".format(err), file=sys.stderr)
> return ""
> @@ -235,6 +247,11 @@ if __name__ == "__main__":
> default=False,
> action="store_true",
> help="allow unprompted downloading of HTML
> template")
> + parser.add_argument("-e", "--event",
> + default="",
> + dest="event_name",
> + type=str,
> + help="specify the event to generate
> + flamegraph for")
>
> cli_args = parser.parse_args()
> cli = FlameGraphCLI(cli_args)
> --
> 2.43.5
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2025-06-10 3:20 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-06-03 7:10 [PATCH] Minor improvements for perf script flamegraph Tianyou Li
2025-06-10 1:19 ` Namhyung Kim
2025-06-10 3:20 ` Li, Tianyou
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox