. Also,
all users I know are setting it to 1 on rtla... so I think it is safe to
move the value to 1.
Acked-by: Daniel Bristot de Oliveira
> Suggested-by: Daniel Bristot de Oliveira
> Reviewed-by: Clark Williams
> Signed-off-by: Luis Claudio R. Goncalves
> ---
> Document
trace_set_buffer_size() appears on libtracefs v1.6,
so increase the minimum required version on Makefile.config.
Signed-off-by: Daniel Bristot de Oliveira
---
Changes from V1:
Increase minimum libtracefs version (jkacur).
Link:
https://lkml.kernel.org/r/0281bfbd3b3fed11a0150a8645a1f9941a423c7a
On 4/24/24 16:36, Daniel Bristot de Oliveira wrote:
> + retval = trace_set_buffer_size(&record->trace,
> params->buffer_size);
This function appears on libtracefs from 1.6 up, so I need to update
the minimum required lib version to 1.6. I will send a v2 of
: Daniel Bristot de Oliveira
---
Documentation/tools/rtla/common_options.rst | 3 +++
tools/tracing/rtla/src/osnoise_hist.c | 13 -
tools/tracing/rtla/src/osnoise_top.c| 14 +-
tools/tracing/rtla/src/timerlat_hist.c | 14 +-
tools/tracing/rtla
option to allow the user to request kernel-threads.
Signed-off-by: Daniel Bristot de Oliveira
---
.../tools/rtla/common_timerlat_options.rst| 6 +++-
tools/tracing/rtla/src/timerlat_hist.c| 31 +--
tools/tracing/rtla/src/timerlat_top.c | 31 +--
3
workload is set, but the results are discarded.
Signed-off-by: Daniel Bristot de Oliveira
---
Documentation/tools/rtla/common_options.rst | 4 ++
tools/tracing/rtla/src/osnoise_hist.c | 30 +++--
tools/tracing/rtla/src/osnoise_top.c| 29 +++-
tools/tracing/rtla/src
: Juri Lelli
Signed-off-by: Daniel Bristot de Oliveira
---
tools/tracing/rtla/src/timerlat_hist.c | 130 -
1 file changed, 129 insertions(+), 1 deletion(-)
diff --git a/tools/tracing/rtla/src/timerlat_hist.c
b/tools/tracing/rtla/src/timerlat_hist.c
index 8bd51aab6513
---||---
ALL #40011 e0 | 2 137 462 | 8
156 481
Suggested-by: Juri Lelli
Signed-off-by: Daniel Bristot de Oliveira
---
tools/tracing/rtla/src/timerlat_top.c | 108
0 154 |5 2
457
1 #1013 |3 0 110 |6 2
415
To avoid this problem, do the formatting only if running on a tty,
and in !quiet mode.
Signed-off-by: Daniel Bristot de Oliveira
r:2364.93 us
Thread latency: 1235.47 us (100%)
Replace \t with spaces to avoid this problem.
Cc: sta...@vger.kernel.org
Fixes: 27e348b221f6 ("rtla/timerlat: Add auto-analysis core")
Signed-off-by: Daniel Bristot de Oliveir
th kernel threads.
Cc: sta...@vger.kernel.org
Fixes: cdca4f4e5e8e ("rtla/timerlat_top: Add timerlat user-space support")
Signed-off-by: Daniel Bristot de Oliveira
---
tools/tracing/rtla/src/timerlat_top.c | 17 +
1 file changed, 5 insertions(+), 12 deletions(-)
diff --git
ce, also adding the
a -k option, allowing the user to switch to kerne-threads.
Daniel Bristot de Oliveira (8):
rtla/timerlat: Simplify "no value" printing on top
rtla/auto-analysis: Replace \t with spaces
rtla/timerlat: Use pretty formatting only on interactive tty
rtla/timerla
options on rtla timerlat works in this setup
as well, including auto analysis.
Signed-off-by: Daniel Bristot de Oliveira
---
.../tools/rtla/common_timerlat_options.rst| 6 ++
tools/tracing/rtla/sample/timerlat_load.py| 74 +++
tools/tracing/rtla/src/timerlat_hist.c|
On 9/19/23 15:30, Xie XiuQi wrote:
> From: Xie XiuQi
>
> The following error message is reported when running the example in document.
>
> # timerlat hist -d 10m -c 0-4 -P d:100us:1ms -p 1ms --no-aa
> Failed to set timerlat period
> Could not apply config
>
> The unit of the period is mic
The documentation was mentioning the "future SCHED EDF" as the
solution for fine-grained control of deadline/period. This patch
updates this citing the (now) existing SCHED_DEADLINE.
Signed-off-by: Daniel Bristot de Oliveira
Cc: Jonathan Corbet
Cc: Juri Lelli
Cc: Luca Abeni
C
15 matches
Mail list logo
