Re: Potential issues (security and otherwise) with the current cgroup-bpf API

On 12/19/16 6:56 PM, Andy Lutomirski wrote: > On Mon, Dec 19, 2016 at 5:44 PM, David Ahern wrote: >> On 12/19/16 5:25 PM, Andy Lutomirski wrote: >>> net.socket_create_filter = "none": no filter >>> net.socket_create_filter = "bpf:baadf00d": bpf

Re: Potential issues (security and otherwise) with the current cgroup-bpf API

On 12/19/16 5:25 PM, Andy Lutomirski wrote: > net.socket_create_filter = "none": no filter > net.socket_create_filter = "bpf:baadf00d": bpf filter > net.socket_create_filter = "disallow": no sockets created period > net.socket_create_filter = "iptables:foobar": some iptables thingy >

Re: Potential issues (security and otherwise) with the current cgroup-bpf API

On 12/19/16 5:25 PM, Andy Lutomirski wrote: > net.socket_create_filter = "none": no filter > net.socket_create_filter = "bpf:baadf00d": bpf filter > net.socket_create_filter = "disallow": no sockets created period > net.socket_create_filter = "iptables:foobar": some iptables thingy >

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

of context switches: 2337 > Total run time (msec): 3718.048 > Total scheduling time (msec): 1001.131 > > Suggested-by: David Ahern <dsah...@gmail.com> > Signed-off-by: Namhyung Kim <namhy...@kernel.org> > --- > tools/perf/builtin-sched.c | 19 +++

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

2337 > Total run time (msec): 3718.048 > Total scheduling time (msec): 1001.131 > > Suggested-by: David Ahern > Signed-off-by: Namhyung Kim > --- > tools/perf/builtin-sched.c | 19 --- > 1 file changed, 16 insertions(+), 3 deletions(-) >

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

On 12/12/16 10:26 AM, Namhyung Kim wrote: > Do you mean adding an elapsed time so that it can see the cpu utilization (or > something similar)? Then we need to expose the elapsed time during record or > maybe just use time difference between first and last sample? I was thinking tstart = time of

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

On 12/12/16 10:26 AM, Namhyung Kim wrote: > Do you mean adding an elapsed time so that it can see the cpu utilization (or > something similar)? Then we need to expose the elapsed time during record or > maybe just use time difference between first and last sample? I was thinking tstart = time of

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

: Add -I/--idle-hist option > perf sched timehist: Show callchains for idle stat > > tools/perf/Documentation/perf-sched.txt | 4 + > tools/perf/builtin-sched.c | 252 > +++- > 2 files changed, 222 insertions(+), 34 deletions(-) > L

Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

: Add -I/--idle-hist option > perf sched timehist: Show callchains for idle stat > > tools/perf/Documentation/perf-sched.txt | 4 + > tools/perf/builtin-sched.c | 252 > +++- > 2 files changed, 222 insertions(+), 34 deletions(-) >

[tip:perf/core] perf sched timehist: Improve error message when analyzing wrong file

Commit-ID: f45bf8d3939d8f32f06ec12e56d2b8651c5437b4 Gitweb: http://git.kernel.org/tip/f45bf8d3939d8f32f06ec12e56d2b8651c5437b4 Author: David Ahern <dsah...@gmail.com> AuthorDate: Tue, 29 Nov 2016 13:39:48 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> CommitDate

[tip:perf/core] perf sched timehist: Improve error message when analyzing wrong file

Commit-ID: f45bf8d3939d8f32f06ec12e56d2b8651c5437b4 Gitweb: http://git.kernel.org/tip/f45bf8d3939d8f32f06ec12e56d2b8651c5437b4 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 13:39:48 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Wed, 7 Dec 2016 12:00:32 -0300 perf sched

Re: [PATCHSET 00/10] perf sched timehist: Introduce --idle-hist option (v1)

On 12/6/16 11:44 AM, Arnaldo Carvalho de Melo wrote: > Em Tue, Dec 06, 2016 at 12:40:00PM +0900, Namhyung Kim escreveu: >> Hi, >> >> This patchset implements the idle hist feature which analyze reason of system >> idle. Sometimes I need to investigate what makes CPUs to go idle even though >> I

Re: [PATCHSET 00/10] perf sched timehist: Introduce --idle-hist option (v1)

On 12/6/16 11:44 AM, Arnaldo Carvalho de Melo wrote: > Em Tue, Dec 06, 2016 at 12:40:00PM +0900, Namhyung Kim escreveu: >> Hi, >> >> This patchset implements the idle hist feature which analyze reason of system >> idle. Sometimes I need to investigate what makes CPUs to go idle even though >> I

Re: [PATCH 06/10] perf sched timehist: Introduce struct idle_time_data

On 12/5/16 7:40 PM, Namhyung Kim wrote: > The struct idle_time_data is to keep idle stats with callchains entering > to the idle task. The normal thread_runtime calculation is done > transparently since it extends the struct thread_runtime. > > Signed-off-by: Namhyung Kim >

Re: [PATCH 06/10] perf sched timehist: Introduce struct idle_time_data

On 12/5/16 7:40 PM, Namhyung Kim wrote: > The struct idle_time_data is to keep idle stats with callchains entering > to the idle task. The normal thread_runtime calculation is done > transparently since it extends the struct thread_runtime. > > Signed-off-by: Namhyung Kim > --- >

Re: [PATCH 03/10] perf sched timehist: Handle zero sample->tid properly

On 12/5/16 7:59 PM, Namhyung Kim wrote: > No, I didn't investigate it yet. Looking at the original code, you > seemed to have same issue and workaround like checking prev_pid or > callchains, right? most likely. As I responded on another patch, the sched timehist command has been used for years

Re: [PATCH 03/10] perf sched timehist: Handle zero sample->tid properly

On 12/5/16 7:59 PM, Namhyung Kim wrote: > No, I didn't investigate it yet. Looking at the original code, you > seemed to have same issue and workaround like checking prev_pid or > callchains, right? most likely. As I responded on another patch, the sched timehist command has been used for years

Re: [PATCH 05/10] perf sched timehist: Cleanup idle_max_cpu handling

insertions(+), 5 deletions(-) > Seems correct. I've lost track of how idle_max_cpu ended up like that. Acked-by: David Ahern <dsah...@gmail.com>

Re: [PATCH 05/10] perf sched timehist: Cleanup idle_max_cpu handling

t; Seems correct. I've lost track of how idle_max_cpu ended up like that. Acked-by: David Ahern

Re: [PATCH 01/10] perf sched: Cleanup option processing

ls/perf/builtin-sched.c | 7 ++- > 1 file changed, 2 insertions(+), 5 deletions(-) > Acked-by: David Ahern <dsah...@gmail.com>

Re: [PATCH 01/10] perf sched: Cleanup option processing

| 7 ++- > 1 file changed, 2 insertions(+), 5 deletions(-) > Acked-by: David Ahern

Re: [PATCH 04/10] perf sched timehist: Split is_idle_sample()

On 12/5/16 7:40 PM, Namhyung Kim wrote: > The is_idle_sample() function actually does more than determining > whether sample come from idle task. Split the callchain part into > save_task_callchain() to make it clearer. Also checking prev_pid from > trace data looks unnecessary since it should

Re: [PATCH 04/10] perf sched timehist: Split is_idle_sample()

On 12/5/16 7:40 PM, Namhyung Kim wrote: > The is_idle_sample() function actually does more than determining > whether sample come from idle task. Split the callchain part into > save_task_callchain() to make it clearer. Also checking prev_pid from > trace data looks unnecessary since it should

Re: [PATCH 03/10] perf sched timehist: Handle zero sample->tid properly

On 12/5/16 7:40 PM, Namhyung Kim wrote: > Sometimes samples have tid of 0 but non-0 pid. It ends up having a Any idea how that happens? > new thread of 0 tid/pid (instead of referring idle task) since tid is > used to search matching task. But I guess it's wrong to use 0 as a > tid when pid is

Re: [PATCH 03/10] perf sched timehist: Handle zero sample->tid properly

On 12/5/16 7:40 PM, Namhyung Kim wrote: > Sometimes samples have tid of 0 but non-0 pid. It ends up having a Any idea how that happens? > new thread of 0 tid/pid (instead of referring idle task) since tid is > used to search matching task. But I guess it's wrong to use 0 as a > tid when pid is

Re: [PATCH v2] perf sched timehist: Improve error message when analyzing wrong file

On 11/29/16 9:31 PM, Namhyung Kim wrote: > On 11/30/16, David Ahern <dsah...@gmail.com> wrote: >> Arnaldo reported an unhelpful error message when running perf sched >> timehist on a file that did not contain sched tracepoints: >> >> [root@jouet ~]# perf sche

Re: [PATCH v2] perf sched timehist: Improve error message when analyzing wrong file

On 11/29/16 9:31 PM, Namhyung Kim wrote: > On 11/30/16, David Ahern wrote: >> Arnaldo reported an unhelpful error message when running perf sched >> timehist on a file that did not contain sched tracepoints: >> >> [root@jouet ~]# perf sched timehist >>

[tip:perf/core] perf kmem: Add option to specify time window of interest

Commit-ID: 2a865bd844315c88bf922761e4fd3374d046 Gitweb: http://git.kernel.org/tip/2a865bd844315c88bf922761e4fd3374d046 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:45 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf tools: Move parse_nsec_time to time-utils.c

Commit-ID: c284d669a20d408b70ce0dc9b2d995971f5fe0c7 Gitweb: http://git.kernel.org/tip/c284d669a20d408b70ce0dc9b2d995971f5fe0c7 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:42 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf report: Add option to specify time window of interest

Commit-ID: 46690a8051e4b5901a49080443a17a270e0bd8a2 Gitweb: http://git.kernel.org/tip/46690a8051e4b5901a49080443a17a270e0bd8a2 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:46 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf kmem: Add option to specify time window of interest

Commit-ID: 2a865bd844315c88bf922761e4fd3374d046 Gitweb: http://git.kernel.org/tip/2a865bd844315c88bf922761e4fd3374d046 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:45 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:03:02 -0300 perf kmem: Add

[tip:perf/core] perf tools: Move parse_nsec_time to time-utils.c

Commit-ID: c284d669a20d408b70ce0dc9b2d995971f5fe0c7 Gitweb: http://git.kernel.org/tip/c284d669a20d408b70ce0dc9b2d995971f5fe0c7 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:42 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:02:39 -0300 perf tools

[tip:perf/core] perf report: Add option to specify time window of interest

Commit-ID: 46690a8051e4b5901a49080443a17a270e0bd8a2 Gitweb: http://git.kernel.org/tip/46690a8051e4b5901a49080443a17a270e0bd8a2 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:46 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:03:10 -0300 perf report

[tip:perf/core] perf tools: Add time-based utility functions

Commit-ID: fdf9dc4b34f5f40919370c4601eccfd0db726aa5 Gitweb: http://git.kernel.org/tip/fdf9dc4b34f5f40919370c4601eccfd0db726aa5 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:41 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf script: Add option to specify time window of interest

Commit-ID: a91f4c473fa1655a2a5f1ceba46f76a95eef35bb Gitweb: http://git.kernel.org/tip/a91f4c473fa1655a2a5f1ceba46f76a95eef35bb Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:43 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf tools: Add time-based utility functions

Commit-ID: fdf9dc4b34f5f40919370c4601eccfd0db726aa5 Gitweb: http://git.kernel.org/tip/fdf9dc4b34f5f40919370c4601eccfd0db726aa5 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:41 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:02:32 -0300 perf tools: Add

[tip:perf/core] perf script: Add option to specify time window of interest

Commit-ID: a91f4c473fa1655a2a5f1ceba46f76a95eef35bb Gitweb: http://git.kernel.org/tip/a91f4c473fa1655a2a5f1ceba46f76a95eef35bb Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:43 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:02:45 -0300 perf script

[tip:perf/core] perf sched timehist: Add option to specify time window of interest

Commit-ID: 853b74071110bed344bad1ca9d8de27731b1c574 Gitweb: http://git.kernel.org/tip/853b74071110bed344bad1ca9d8de27731b1c574 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Tue, 29 Nov 2016 10:15:44 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf sched timehist: Add option to specify time window of interest

Commit-ID: 853b74071110bed344bad1ca9d8de27731b1c574 Gitweb: http://git.kernel.org/tip/853b74071110bed344bad1ca9d8de27731b1c574 Author: David Ahern AuthorDate: Tue, 29 Nov 2016 10:15:44 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Thu, 1 Dec 2016 13:02:52 -0300 perf sched

[tip:perf/core] perf kmem stat: Track memory freed

Commit-ID: aa58e9afb613fab74f33292705bb43beb0f1828d Gitweb: http://git.kernel.org/tip/aa58e9afb613fab74f33292705bb43beb0f1828d Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Fri, 25 Nov 2016 14:42:13 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf script: Add option to stop printing callchain

Commit-ID: 64eff7d9c4469b7e24fb7e5416a67ee5959c3f76 Gitweb: http://git.kernel.org/tip/64eff7d9c4469b7e24fb7e5416a67ee5959c3f76 Author: David Ahern <d...@cumulusnetworks.com> AuthorDate: Fri, 25 Nov 2016 13:00:21 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> Com

[tip:perf/core] perf kmem stat: Track memory freed

Commit-ID: aa58e9afb613fab74f33292705bb43beb0f1828d Gitweb: http://git.kernel.org/tip/aa58e9afb613fab74f33292705bb43beb0f1828d Author: David Ahern AuthorDate: Fri, 25 Nov 2016 14:42:13 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Tue, 29 Nov 2016 12:50:32 -0300 perf kmem stat

[tip:perf/core] perf script: Add option to stop printing callchain

Commit-ID: 64eff7d9c4469b7e24fb7e5416a67ee5959c3f76 Gitweb: http://git.kernel.org/tip/64eff7d9c4469b7e24fb7e5416a67ee5959c3f76 Author: David Ahern AuthorDate: Fri, 25 Nov 2016 13:00:21 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Tue, 29 Nov 2016 13:06:19 -0300 perf script

[tip:perf/core] perf sched timehist: Handle cpu migration events

Commit-ID: 350f54fab2afd7f819e64fbeecdf980086fa59f2 Gitweb: http://git.kernel.org/tip/350f54fab2afd7f819e64fbeecdf980086fa59f2 Author: David Ahern <dsah...@gmail.com> AuthorDate: Fri, 25 Nov 2016 09:28:41 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> CommitDate:

[tip:perf/core] perf trace: Update tid/pid filtering option to leverage symbol_conf

Commit-ID: aa07df6eb5061eed3f5d0820dc646d7f6ddface2 Gitweb: http://git.kernel.org/tip/aa07df6eb5061eed3f5d0820dc646d7f6ddface2 Author: David Ahern <dsah...@gmail.com> AuthorDate: Fri, 25 Nov 2016 09:29:52 -0700 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> CommitDate:

[tip:perf/core] perf trace: Update tid/pid filtering option to leverage symbol_conf

Commit-ID: aa07df6eb5061eed3f5d0820dc646d7f6ddface2 Gitweb: http://git.kernel.org/tip/aa07df6eb5061eed3f5d0820dc646d7f6ddface2 Author: David Ahern AuthorDate: Fri, 25 Nov 2016 09:29:52 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Fri, 25 Nov 2016 16:04:22 -0300 perf trace

[tip:perf/core] perf sched timehist: Handle cpu migration events

Commit-ID: 350f54fab2afd7f819e64fbeecdf980086fa59f2 Gitweb: http://git.kernel.org/tip/350f54fab2afd7f819e64fbeecdf980086fa59f2 Author: David Ahern AuthorDate: Fri, 25 Nov 2016 09:28:41 -0700 Committer: Arnaldo Carvalho de Melo CommitDate: Fri, 25 Nov 2016 16:00:22 -0300 perf sched

[PATCH v2] perf sched timehist: Improve error message when analyzing wrong file

sched timehist requires at least this event. Now when analyzing a file without sched tracepoints you get: root@f21-vbox:/tmp$ perf sched timehist No sched_switch events found. Have you run 'perf sched record'? Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/builtin-s

[PATCH v2] perf sched timehist: Improve error message when analyzing wrong file

sched timehist requires at least this event. Now when analyzing a file without sched tracepoints you get: root@f21-vbox:/tmp$ perf sched timehist No sched_switch events found. Have you run 'perf sched record'? Signed-off-by: David Ahern --- tools/perf/builtin-sched.c | 6 +- 1 file

Re: [PATCH] perf sched timehist: Improve error message when analyzing wrong file

On 11/29/16 1:14 PM, Arnaldo Carvalho de Melo wrote: > It uses things like: > > if (kmem_page) { > struct perf_evsel *evsel; > > evsel = perf_evlist__find_tracepoint_by_name(session->evlist, > >

Re: [PATCH] perf sched timehist: Improve error message when analyzing wrong file

On 11/29/16 1:14 PM, Arnaldo Carvalho de Melo wrote: > It uses things like: > > if (kmem_page) { > struct perf_evsel *evsel; > > evsel = perf_evlist__find_tracepoint_by_name(session->evlist, > >

[PATCH] perf sched timehist: Improve error message when analyzing wrong file

-by: David Ahern <dsah...@gmail.com> --- tools/perf/builtin-sched.c | 5 - tools/perf/util/session.c | 12 tools/perf/util/session.h | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 870d94

[PATCH] perf sched timehist: Improve error message when analyzing wrong file

-by: David Ahern --- tools/perf/builtin-sched.c | 5 - tools/perf/util/session.c | 12 tools/perf/util/session.h | 2 ++ 3 files changed, 18 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 870d94cd20ba..7c3c8176f51f 100644

Re: [PATCH v2 4/6] perf sched timehist: Add option to specify time window of interest

On 11/29/16 11:56 AM, Arnaldo Carvalho de Melo wrote: > Em Tue, Nov 29, 2016 at 10:15:44AM -0700, David Ahern escreveu: >> Add option to allow user to control analysis window. e.g., collect data >> for time window and analyze a segment of interest within that window. > Trying

Re: [PATCH v2 4/6] perf sched timehist: Add option to specify time window of interest

On 11/29/16 11:56 AM, Arnaldo Carvalho de Melo wrote: > Em Tue, Nov 29, 2016 at 10:15:44AM -0700, David Ahern escreveu: >> Add option to allow user to control analysis window. e.g., collect data >> for time window and analyze a segment of interest within that window. > Trying

[PATCH v2 1/6] perf tool: Add time-based utility functions

Add function to parse a user time string of the form , where start and stop are time in sec.nsec format. Both start and stop times are optional. Add function to determine if a sample time is within a given time time window of interest. Signed-off-by: David Ahern <dsah...@gmail.com> ---

[PATCH v2 1/6] perf tool: Add time-based utility functions

Add function to parse a user time string of the form , where start and stop are time in sec.nsec format. Both start and stop times are optional. Add function to determine if a sample time is within a given time time window of interest. Signed-off-by: David Ahern --- tools/perf/util/Build

[PATCH v2 2/6] perf tool: Move parse_nsec_time to time-utils.c

Code move only; no functional change intended. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/util/time-utils.c | 35 ++- tools/perf/util/time-utils.h | 2 ++ tools/perf/util/util.c | 33 - tools/per

[PATCH v2 2/6] perf tool: Move parse_nsec_time to time-utils.c

Code move only; no functional change intended. Signed-off-by: David Ahern --- tools/perf/util/time-utils.c | 35 ++- tools/perf/util/time-utils.h | 2 ++ tools/perf/util/util.c | 33 - tools/perf/util/util.h | 2 -- 4

[PATCH v2 3/6] perf script: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for some amount of time and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-script.txt | 7 +++ tools/perf/builtin-sc

[PATCH v2 3/6] perf script: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for some amount of time and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-script.txt | 7 +++ tools/perf/builtin-script.c | 15

[PATCH v2 5/6] perf kmem: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-kmem.txt | 7 +++ tools/perf/builtin-kmem.c

[PATCH v2 4/6] perf sched timehist: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-sched.txt | 8 ++ tools/perf/builtin-sched.c

[PATCH v2 5/6] perf kmem: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-kmem.txt | 7 +++ tools/perf/builtin-kmem.c | 24

[PATCH v2 4/6] perf sched timehist: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-sched.txt | 8 ++ tools/perf/builtin-sched.c | 51

[PATCH v2 6/6] perf report: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-report.txt | 7 +++ tools/perf/builtin-report.c

[PATCH v2 6/6] perf report: Add option to specify time window of interest

Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-report.txt | 7 +++ tools/perf/builtin-report.c | 14 +- 2

[PATCH v2 0/6] perf: Add option to specify time window of interest

This series allows users to collect data and analyze a time window of interest within the file. v2 - renamed perf_time to perf_time_interval - changed ../perf.h to perf.h in patch 1 David Ahern (6): perf tool: Add time-based utility functions perf tool: Move parse_nsec_time to time-utils.c

[PATCH v2 0/6] perf: Add option to specify time window of interest

This series allows users to collect data and analyze a time window of interest within the file. v2 - renamed perf_time to perf_time_interval - changed ../perf.h to perf.h in patch 1 David Ahern (6): perf tool: Add time-based utility functions perf tool: Move parse_nsec_time to time-utils.c

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/29/16 9:02 AM, Arnaldo Carvalho de Melo wrote: > Humm, I'd prefer 'time_interval' or 'perf_time_interval', plain > 'interval' doesn't convey what kind if interval is this, we could be > talking about counter values intervals, etc. agreed, perf_time_interval makes more sense.

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/29/16 9:02 AM, Arnaldo Carvalho de Melo wrote: > Humm, I'd prefer 'time_interval' or 'perf_time_interval', plain > 'interval' doesn't convey what kind if interval is this, we could be > talking about counter values intervals, etc. agreed, perf_time_interval makes more sense.

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 11:14 AM, Jiri Olsa wrote: > there are some time related functions in util.[ch], maybe you > coudl move them as well > > int fetch_current_timestamp(char *buf, size_t sz); > int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); I'd like to defer that to a follow on

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 11:14 AM, Jiri Olsa wrote: > there are some time related functions in util.[ch], maybe you > coudl move them as well > > int fetch_current_timestamp(char *buf, size_t sz); > int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); I'd like to defer that to a follow on

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 6:58 AM, Jiri Olsa wrote: > On Fri, Nov 25, 2016 at 02:39:54PM -0700, David Ahern wrote: >> From: David Ahern <dsah...@gmail.com> >> >> Add function to parse a user time string of the form , >> where start and stop are time in sec.nsec format. Both sta

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 6:58 AM, Jiri Olsa wrote: > On Fri, Nov 25, 2016 at 02:39:54PM -0700, David Ahern wrote: >> From: David Ahern >> >> Add function to parse a user time string of the form , >> where start and stop are time in sec.nsec format. Both start and stop >> times

Re: [PATCH 2/6] perf tool: Move parse_nsec_time to time-utils.c

On 11/28/16 6:58 AM, Jiri Olsa wrote: >> diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h >> index 79662d67891e..1d639e38aa82 100644 >> --- a/tools/perf/util/util.h >> +++ b/tools/perf/util/util.h >> @@ -179,8 +179,6 @@ static inline void *zalloc(size_t size) >> #undef tolower >>

Re: [PATCH 2/6] perf tool: Move parse_nsec_time to time-utils.c

On 11/28/16 6:58 AM, Jiri Olsa wrote: >> diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h >> index 79662d67891e..1d639e38aa82 100644 >> --- a/tools/perf/util/util.h >> +++ b/tools/perf/util/util.h >> @@ -179,8 +179,6 @@ static inline void *zalloc(size_t size) >> #undef tolower >>

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 6:58 AM, Jiri Olsa wrote: > On Fri, Nov 25, 2016 at 02:39:54PM -0700, David Ahern wrote: > > SNIP > >> diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h >> new file mode 100644 >> index ..4368a481251d >> --- /de

Re: [PATCH 1/6] perf tool: Add time-based utility functions

On 11/28/16 6:58 AM, Jiri Olsa wrote: > On Fri, Nov 25, 2016 at 02:39:54PM -0700, David Ahern wrote: > > SNIP > >> diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h >> new file mode 100644 >> index ..4368a481251d >> --- /de

Re: [PATCH 1/3] perf sched timehist: Mark schedule function in callchains

On 11/23/16 11:30 PM, Namhyung Kim wrote: > Hi David, > > On Wed, Nov 23, 2016 at 10:13:46PM -0500, David Ahern wrote: >> On 11/23/16 8:11 PM, Namhyung Kim wrote: >>> The sched_switch event always captured from the scheduler function. So >>> it'd be g

Re: [PATCH 1/3] perf sched timehist: Mark schedule function in callchains

On 11/23/16 11:30 PM, Namhyung Kim wrote: > Hi David, > > On Wed, Nov 23, 2016 at 10:13:46PM -0500, David Ahern wrote: >> On 11/23/16 8:11 PM, Namhyung Kim wrote: >>> The sched_switch event always captured from the scheduler function. So >>> it'd be g

[PATCH] perf kmem stat: Track memory freed

Track freed memory as well as allocations and show the net in the summary. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/builtin-kmem.c | 12 +++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c

[PATCH] perf kmem stat: Track memory freed

Track freed memory as well as allocations and show the net in the summary. Signed-off-by: David Ahern --- tools/perf/builtin-kmem.c | 12 +++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index f184ecf9b0b3

[PATCH 5/6] perf kmem: Add option to specify time window of interest

From: David Ahern <dsah...@gmail.com> Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-kmem.txt | 7 +++

[PATCH 3/6] perf script: Add option to specify time window of interest

From: David Ahern <dsah...@gmail.com> Add option to allow user to control analysis window. e.g., collect data for some amount of time and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-scr

[PATCH 6/6] perf report: Add option to specify time window of interest

From: David Ahern <dsah...@gmail.com> Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-report.txt | 7 ++

[PATCH 4/6] perf sched timehist: Add option to specify time window of interest

From: David Ahern <dsah...@gmail.com> Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/Documentation/perf-sched.txt | 8 ++

[PATCH 5/6] perf kmem: Add option to specify time window of interest

From: David Ahern Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-kmem.txt | 7 +++ tools/perf/builtin-kmem.c | 24

[PATCH 3/6] perf script: Add option to specify time window of interest

From: David Ahern Add option to allow user to control analysis window. e.g., collect data for some amount of time and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-script.txt | 7 +++ tools/perf/builtin-script.c

[PATCH 6/6] perf report: Add option to specify time window of interest

From: David Ahern Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-report.txt | 7 +++ tools/perf/builtin-report.c | 14

[PATCH 4/6] perf sched timehist: Add option to specify time window of interest

From: David Ahern Add option to allow user to control analysis window. e.g., collect data for time window and analyze a segment of interest within that window. Signed-off-by: David Ahern --- tools/perf/Documentation/perf-sched.txt | 8 ++ tools/perf/builtin-sched.c | 51

[PATCH 2/6] perf tool: Move parse_nsec_time to time-utils.c

From: David Ahern <dsah...@gmail.com> Code move only; no functional change intended. Signed-off-by: David Ahern <dsah...@gmail.com> --- tools/perf/util/time-utils.c | 35 ++- tools/perf/util/time-utils.h | 2 ++ tools/perf/util/util.

[PATCH 2/6] perf tool: Move parse_nsec_time to time-utils.c

From: David Ahern Code move only; no functional change intended. Signed-off-by: David Ahern --- tools/perf/util/time-utils.c | 35 ++- tools/perf/util/time-utils.h | 2 ++ tools/perf/util/util.c | 33 - tools/perf/util

[PATCH 0/6] perf: Add option to specify time window of interest

From: David Ahern <dsah...@gmail.com> This series allows users to collect data and analyze a time window of interest within the file. David Ahern (6): perf tool: Add time-based utility functions perf tool: Move parse_nsec_time to time-utils.c perf script: Add option to specify time

[PATCH 1/6] perf tool: Add time-based utility functions

From: David Ahern <dsah...@gmail.com> Add function to parse a user time string of the form , where start and stop are time in sec.nsec format. Both start and stop times are optional. Add function to determine if a sample time is within a given time time window of interest. Signed-off-by:

[PATCH 1/6] perf tool: Add time-based utility functions

From: David Ahern Add function to parse a user time string of the form , where start and stop are time in sec.nsec format. Both start and stop times are optional. Add function to determine if a sample time is within a given time time window of interest. Signed-off-by: David Ahern --- tools

[PATCH 0/6] perf: Add option to specify time window of interest

From: David Ahern This series allows users to collect data and analyze a time window of interest within the file. David Ahern (6): perf tool: Add time-based utility functions perf tool: Move parse_nsec_time to time-utils.c perf script: Add option to specify time window of interest perf

[PATCH v2] perf script: Add option to stop printing callchain

From: David Ahern <d...@cumulusnetworks.com> Allow user to specify list of symbols which cause the dump of callchains to stop at that symbol. Signed-off-by: David Ahern <d...@cumulusnetworks.com> --- v2 - rebased to top of perf/core tree tools/perf/Documentation/perf-script.txt |

[PATCH v2] perf script: Add option to stop printing callchain

From: David Ahern Allow user to specify list of symbols which cause the dump of callchains to stop at that symbol. Signed-off-by: David Ahern --- v2 - rebased to top of perf/core tree tools/perf/Documentation/perf-script.txt | 3 +++ tools/perf/builtin-script.c | 2 ++ tools

[PATCH] perf script: Add option to stop printing callchain

From: David Ahern <d...@cumulusnetworks.com> Allow user to specify list of symbols which cause the dump of callchains to stop at that symbol. Signed-off-by: David Ahern <d...@cumulusnetworks.com> --- tools/perf/Documentation/perf-script.txt | 3 +++ tools/perf/builtin-script.c

<    1   2   3   4   5   6   7   8   9   10   >