| Message ID | cover.1684863094.git.bristot@kernel.org (mailing list archive) |
|---|---|
| Headers | show |
| Series | rtla improvements | expand |
Hi Daniel, Could you make sure to Cc linux-trace-kernel@vger.kernel.org and not linux-trace-devel. The former is for any patch that goes into the kernel repo, the later is for the tracing libraries (like libtracefs). The reason why this matters is that the patchwork that is associated to the Linux kernel tree will not get these (and I will not work on them when I'm working on kernel patches). But it will go into the patchwork for the libraries (and never be processed by the patchwork infrastructure), and I will likely not work on them, because when I look at the library patchwork, I ignore anything that goes into the kernel. Perhaps resend with the proper Cc and it will then be processed. I allowed this to happen before, but that's because I did everything manually and not with my scripts. And I'm tired of doing that. Thanks, -- Steve On Tue, 23 May 2023 19:44:22 +0200 Daniel Bristot de Oliveira <bristot@kernel.org> wrote: > This is a series of improvements for rtla, mainly as a result of our > daily usage of the tool debugging problems at red hat. > > The cgroup support and house keeping options are from our usage > of the tool debugging containers. > > The auto-analysis overhead reduction is needed when we go to > large boxes - but it is really hand in practice, as it gives an idea > of the problem without having to look at the trace. > > Running hwnoise 100 % of CPU time might cause some systems > to slow down too much. Reduce its utilization to 75% by default to > avoid problems for people using it for the first time. > > Finally, it adds support for running timerlat user-space threads, > and to collect the additional field via rtla timerlat top. > > Changes from V1: > - Add the user-space thread support to rtla timerlat top > Link: https://lore.kernel.org/lkml/cover.1683827510.git.bristot@kernel.org/ > > Daniel Bristot de Oliveira (9): > rtla: Add -C cgroup support > rtla: Add --house-keeping option > rtla: Change monitored_cpus from char * to cpu_set_t > rtla: Automatically move rtla to a house-keeping cpu > rtla/timerlat: Give timerlat auto analysis its own instance > rtla/timerlat_hist: Add auto-analysis support > rtla: Start the tracers after creating all instances > rtla/hwnoise: Reduce runtime to 75% > rtla: Add timerlat user-space support for timerlat top > > Documentation/tools/rtla/common_options.rst | 8 + > .../tools/rtla/common_timerlat_aa.rst | 7 - > .../tools/rtla/rtla-timerlat-hist.rst | 7 +- > .../tools/rtla/rtla-timerlat-top.rst | 14 + > tools/tracing/rtla/src/osnoise.c | 65 ++++ > tools/tracing/rtla/src/osnoise.h | 5 + > tools/tracing/rtla/src/osnoise_hist.c | 90 ++++- > tools/tracing/rtla/src/osnoise_top.c | 83 ++++- > tools/tracing/rtla/src/timerlat_aa.c | 35 +- > tools/tracing/rtla/src/timerlat_aa.h | 5 +- > tools/tracing/rtla/src/timerlat_hist.c | 139 +++++++- > tools/tracing/rtla/src/timerlat_top.c | 229 +++++++++++-- > tools/tracing/rtla/src/timerlat_u.c | 224 ++++++++++++ > tools/tracing/rtla/src/timerlat_u.h | 18 + > tools/tracing/rtla/src/utils.c | 324 +++++++++++++++++- > tools/tracing/rtla/src/utils.h | 7 + > 16 files changed, 1162 insertions(+), 98 deletions(-) > create mode 100644 tools/tracing/rtla/src/timerlat_u.c > create mode 100644 tools/tracing/rtla/src/timerlat_u.h >
On 5/29/23 10:28, Steven Rostedt wrote: > Hi Daniel, > > Could you make sure to Cc linux-trace-kernel@vger.kernel.org and not > linux-trace-devel. The former is for any patch that goes into the > kernel repo, the later is for the tracing libraries (like libtracefs). > The reason why this matters is that the patchwork that is associated to > the Linux kernel tree will not get these (and I will not work on them > when I'm working on kernel patches). But it will go into the > patchwork for the libraries (and never be processed by the patchwork > infrastructure), and I will likely not work on them, because when I > look at the library patchwork, I ignore anything that goes into the > kernel. Sure, I will do that. IIRC, we agreed that we would use linux-trace-devel for rtla because it is a user-space tool. But I agree with you, as they are patches going to the kernel repo, linux-trace-kernel is a better place. It is easier to myself too... :-). > > Perhaps resend with the proper Cc and it will then be processed. I > allowed this to happen before, but that's because I did everything > manually and not with my scripts. And I'm tired of doing that. I will do that in the v3. I will also update the maintainers entry for RTLA and RV, as both are pointing to linux-trace-devel. Thanks! -- Daniel > > Thanks, > > -- Steve
On Mon, 29 May 2023 10:38:16 +0200 Daniel Bristot de Oliveira <bristot@kernel.org> wrote: > On 5/29/23 10:28, Steven Rostedt wrote: > > Hi Daniel, > > > > Could you make sure to Cc linux-trace-kernel@vger.kernel.org and not > > linux-trace-devel. The former is for any patch that goes into the > > kernel repo, the later is for the tracing libraries (like libtracefs). > > The reason why this matters is that the patchwork that is associated to > > the Linux kernel tree will not get these (and I will not work on them > > when I'm working on kernel patches). But it will go into the > > patchwork for the libraries (and never be processed by the patchwork > > infrastructure), and I will likely not work on them, because when I > > look at the library patchwork, I ignore anything that goes into the > > kernel. > > Sure, I will do that. IIRC, we agreed that we would use linux-trace-devel for > rtla because it is a user-space tool. But I agree with you, as they are patches > going to the kernel repo, linux-trace-kernel is a better place. It is easier to > myself too... :-). I think we agreed on that because linux-trace-kernel didn't exist yet ;-) > > > > > Perhaps resend with the proper Cc and it will then be processed. I > > allowed this to happen before, but that's because I did everything > > manually and not with my scripts. And I'm tired of doing that. > > I will do that in the v3. > > I will also update the maintainers entry for RTLA and RV, as both are pointing to > linux-trace-devel. I already sent the patch! -- Steve
This is a series of improvements for rtla, mainly as a result of our daily usage of the tool debugging problems at red hat. The cgroup support and house keeping options are from our usage of the tool debugging containers. The auto-analysis overhead reduction is needed when we go to large boxes - but it is really hand in practice, as it gives an idea of the problem without having to look at the trace. Running hwnoise 100 % of CPU time might cause some systems to slow down too much. Reduce its utilization to 75% by default to avoid problems for people using it for the first time. Finally, it adds support for running timerlat user-space threads, and to collect the additional field via rtla timerlat top. Changes from V1: - Add the user-space thread support to rtla timerlat top Link: https://lore.kernel.org/lkml/cover.1683827510.git.bristot@kernel.org/ Daniel Bristot de Oliveira (9): rtla: Add -C cgroup support rtla: Add --house-keeping option rtla: Change monitored_cpus from char * to cpu_set_t rtla: Automatically move rtla to a house-keeping cpu rtla/timerlat: Give timerlat auto analysis its own instance rtla/timerlat_hist: Add auto-analysis support rtla: Start the tracers after creating all instances rtla/hwnoise: Reduce runtime to 75% rtla: Add timerlat user-space support for timerlat top Documentation/tools/rtla/common_options.rst | 8 + .../tools/rtla/common_timerlat_aa.rst | 7 - .../tools/rtla/rtla-timerlat-hist.rst | 7 +- .../tools/rtla/rtla-timerlat-top.rst | 14 + tools/tracing/rtla/src/osnoise.c | 65 ++++ tools/tracing/rtla/src/osnoise.h | 5 + tools/tracing/rtla/src/osnoise_hist.c | 90 ++++- tools/tracing/rtla/src/osnoise_top.c | 83 ++++- tools/tracing/rtla/src/timerlat_aa.c | 35 +- tools/tracing/rtla/src/timerlat_aa.h | 5 +- tools/tracing/rtla/src/timerlat_hist.c | 139 +++++++- tools/tracing/rtla/src/timerlat_top.c | 229 +++++++++++-- tools/tracing/rtla/src/timerlat_u.c | 224 ++++++++++++ tools/tracing/rtla/src/timerlat_u.h | 18 + tools/tracing/rtla/src/utils.c | 324 +++++++++++++++++- tools/tracing/rtla/src/utils.h | 7 + 16 files changed, 1162 insertions(+), 98 deletions(-) create mode 100644 tools/tracing/rtla/src/timerlat_u.c create mode 100644 tools/tracing/rtla/src/timerlat_u.h