* [PATCH] perf: test: Speed up running brstack test
@ 2024-12-13 23:13 Rob Herring (Arm)
2024-12-17 14:41 ` James Clark
` (3 more replies)
0 siblings, 4 replies; 6+ messages in thread
From: Rob Herring (Arm) @ 2024-12-13 23:13 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
Ian Rogers, Adrian Hunter, Liang, Kan
Cc: James Clark, Anshuman Khandual, linux-perf-users, linux-kernel
From: James Clark <james.clark@arm.com>
The brstack test runs quite slowly in software models. Part of the reason
is "xargs -n1" is quite inefficient in replacing spaces with newlines.
While that's not noticeable on normal machines, it is on software models.
Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
much faster. For comparison on an M1 Macbook Pro:
$ time seq -s ' ' 10000 | xargs -n1 > /dev/null
real 0m2.729s
user 0m2.009s
sys 0m0.914s
$ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
real 0m0.002s
user 0m0.001s
sys 0m0.001s
The "grep '.'" is also needed to remove any remaining blank lines.
Signed-off-by: James Clark <james.clark@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
[robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
Originally part of this series[1], but I've dropped any Arm specifics,
and it stands on its own. No reason this needs to wait on Arm BRBE
support (which I'm working on now). I don't expect to have other changes
to this test related to BRBE anymore.
[1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
tools/perf/tests/shell/test_brstack.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index 5f14d0cb013f..e01df7581393 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -30,7 +30,7 @@ test_user_branches() {
echo "Testing user branch stack sampling"
perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
- perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
+ perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
# example of branch entries:
# brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
@@ -59,7 +59,7 @@ test_filter() {
echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
- perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
+ perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
# fail if we find any branch type that doesn't match any of the expected ones
# also consider UNKNOWN branch types (-)
--
2.45.2
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH] perf: test: Speed up running brstack test
2024-12-13 23:13 [PATCH] perf: test: Speed up running brstack test Rob Herring (Arm)
@ 2024-12-17 14:41 ` James Clark
2024-12-18 3:32 ` Anshuman Khandual
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: James Clark @ 2024-12-17 14:41 UTC (permalink / raw)
To: Rob Herring (Arm)
Cc: Anshuman Khandual, linux-perf-users, linux-kernel, Peter Zijlstra,
Ingo Molnar, Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Jiri Olsa, Ian Rogers, Adrian Hunter,
Liang, Kan
On 13/12/2024 11:13 pm, Rob Herring (Arm) wrote:
> From: James Clark <james.clark@arm.com>
>
> The brstack test runs quite slowly in software models. Part of the reason
> is "xargs -n1" is quite inefficient in replacing spaces with newlines.
> While that's not noticeable on normal machines, it is on software models.
> Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
> much faster. For comparison on an M1 Macbook Pro:
>
> $ time seq -s ' ' 10000 | xargs -n1 > /dev/null
>
> real 0m2.729s
> user 0m2.009s
> sys 0m0.914s
> $ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
>
> real 0m0.002s
> user 0m0.001s
> sys 0m0.001s
>
> The "grep '.'" is also needed to remove any remaining blank lines.
>
> Signed-off-by: James Clark <james.clark@arm.com>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> [robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
> Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
> ---
> Originally part of this series[1], but I've dropped any Arm specifics,
> and it stands on its own. No reason this needs to wait on Arm BRBE
> support (which I'm working on now). I don't expect to have other changes
> to this test related to BRBE anymore.
>
> [1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
>
Reviewed-by: James Clark <james.clark@linaro.org>
> tools/perf/tests/shell/test_brstack.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
> index 5f14d0cb013f..e01df7581393 100755
> --- a/tools/perf/tests/shell/test_brstack.sh
> +++ b/tools/perf/tests/shell/test_brstack.sh
> @@ -30,7 +30,7 @@ test_user_branches() {
> echo "Testing user branch stack sampling"
>
> perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
>
> # example of branch entries:
> # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
> @@ -59,7 +59,7 @@ test_filter() {
> echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
>
> perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
>
> # fail if we find any branch type that doesn't match any of the expected ones
> # also consider UNKNOWN branch types (-)
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] perf: test: Speed up running brstack test
2024-12-13 23:13 [PATCH] perf: test: Speed up running brstack test Rob Herring (Arm)
2024-12-17 14:41 ` James Clark
@ 2024-12-18 3:32 ` Anshuman Khandual
2024-12-19 5:48 ` Namhyung Kim
2025-01-13 14:25 ` Rob Herring
3 siblings, 0 replies; 6+ messages in thread
From: Anshuman Khandual @ 2024-12-18 3:32 UTC (permalink / raw)
To: Rob Herring (Arm), Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Jiri Olsa, Ian Rogers, Adrian Hunter,
Liang, Kan
Cc: James Clark, linux-perf-users, linux-kernel
On 12/14/24 04:43, Rob Herring (Arm) wrote:
> From: James Clark <james.clark@arm.com>
>
> The brstack test runs quite slowly in software models. Part of the reason
> is "xargs -n1" is quite inefficient in replacing spaces with newlines.
> While that's not noticeable on normal machines, it is on software models.
> Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
> much faster. For comparison on an M1 Macbook Pro:
>
> $ time seq -s ' ' 10000 | xargs -n1 > /dev/null
>
> real 0m2.729s
> user 0m2.009s
> sys 0m0.914s
> $ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
>
> real 0m0.002s
> user 0m0.001s
> sys 0m0.001s
>
> The "grep '.'" is also needed to remove any remaining blank lines.
>
> Signed-off-by: James Clark <james.clark@arm.com>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> [robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
> Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
> ---
> Originally part of this series[1], but I've dropped any Arm specifics,
> and it stands on its own. No reason this needs to wait on Arm BRBE
> support (which I'm working on now). I don't expect to have other changes
> to this test related to BRBE anymore.
>
> [1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
>
> tools/perf/tests/shell/test_brstack.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
> index 5f14d0cb013f..e01df7581393 100755
> --- a/tools/perf/tests/shell/test_brstack.sh
> +++ b/tools/perf/tests/shell/test_brstack.sh
> @@ -30,7 +30,7 @@ test_user_branches() {
> echo "Testing user branch stack sampling"
>
> perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
>
> # example of branch entries:
> # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
> @@ -59,7 +59,7 @@ test_filter() {
> echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
>
> perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
>
> # fail if we find any branch type that doesn't match any of the expected ones
> # also consider UNKNOWN branch types (-)
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] perf: test: Speed up running brstack test
2024-12-13 23:13 [PATCH] perf: test: Speed up running brstack test Rob Herring (Arm)
2024-12-17 14:41 ` James Clark
2024-12-18 3:32 ` Anshuman Khandual
@ 2024-12-19 5:48 ` Namhyung Kim
2025-01-13 14:25 ` Rob Herring
3 siblings, 0 replies; 6+ messages in thread
From: Namhyung Kim @ 2024-12-19 5:48 UTC (permalink / raw)
To: Rob Herring (Arm)
Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Mark Rutland, Alexander Shishkin, Jiri Olsa, Ian Rogers,
Adrian Hunter, Liang, Kan, James Clark, Anshuman Khandual,
linux-perf-users, linux-kernel
On Fri, Dec 13, 2024 at 05:13:12PM -0600, Rob Herring (Arm) wrote:
> From: James Clark <james.clark@arm.com>
>
> The brstack test runs quite slowly in software models. Part of the reason
> is "xargs -n1" is quite inefficient in replacing spaces with newlines.
> While that's not noticeable on normal machines, it is on software models.
> Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
> much faster. For comparison on an M1 Macbook Pro:
>
> $ time seq -s ' ' 10000 | xargs -n1 > /dev/null
>
> real 0m2.729s
> user 0m2.009s
> sys 0m0.914s
> $ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
>
> real 0m0.002s
> user 0m0.001s
> sys 0m0.001s
>
> The "grep '.'" is also needed to remove any remaining blank lines.
>
> Signed-off-by: James Clark <james.clark@arm.com>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> [robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
> Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Thanks,
Namhyung
> ---
> Originally part of this series[1], but I've dropped any Arm specifics,
> and it stands on its own. No reason this needs to wait on Arm BRBE
> support (which I'm working on now). I don't expect to have other changes
> to this test related to BRBE anymore.
>
> [1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
>
> tools/perf/tests/shell/test_brstack.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
> index 5f14d0cb013f..e01df7581393 100755
> --- a/tools/perf/tests/shell/test_brstack.sh
> +++ b/tools/perf/tests/shell/test_brstack.sh
> @@ -30,7 +30,7 @@ test_user_branches() {
> echo "Testing user branch stack sampling"
>
> perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
>
> # example of branch entries:
> # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
> @@ -59,7 +59,7 @@ test_filter() {
> echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
>
> perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
>
> # fail if we find any branch type that doesn't match any of the expected ones
> # also consider UNKNOWN branch types (-)
> --
> 2.45.2
>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] perf: test: Speed up running brstack test
2024-12-13 23:13 [PATCH] perf: test: Speed up running brstack test Rob Herring (Arm)
` (2 preceding siblings ...)
2024-12-19 5:48 ` Namhyung Kim
@ 2025-01-13 14:25 ` Rob Herring
2025-01-13 14:59 ` Arnaldo Carvalho de Melo
3 siblings, 1 reply; 6+ messages in thread
From: Rob Herring @ 2025-01-13 14:25 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
Ian Rogers, Adrian Hunter, Liang, Kan
Cc: James Clark, Anshuman Khandual, linux-perf-users, linux-kernel
On Fri, Dec 13, 2024 at 5:19 PM Rob Herring (Arm) <robh@kernel.org> wrote:
>
> From: James Clark <james.clark@arm.com>
>
> The brstack test runs quite slowly in software models. Part of the reason
> is "xargs -n1" is quite inefficient in replacing spaces with newlines.
> While that's not noticeable on normal machines, it is on software models.
> Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
> much faster. For comparison on an M1 Macbook Pro:
>
> $ time seq -s ' ' 10000 | xargs -n1 > /dev/null
>
> real 0m2.729s
> user 0m2.009s
> sys 0m0.914s
> $ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
>
> real 0m0.002s
> user 0m0.001s
> sys 0m0.001s
>
> The "grep '.'" is also needed to remove any remaining blank lines.
>
> Signed-off-by: James Clark <james.clark@arm.com>
> Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> [robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
> Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
> ---
> Originally part of this series[1], but I've dropped any Arm specifics,
> and it stands on its own. No reason this needs to wait on Arm BRBE
> support (which I'm working on now). I don't expect to have other changes
> to this test related to BRBE anymore.
>
> [1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
>
> tools/perf/tests/shell/test_brstack.sh | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
Ping!
>
> diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
> index 5f14d0cb013f..e01df7581393 100755
> --- a/tools/perf/tests/shell/test_brstack.sh
> +++ b/tools/perf/tests/shell/test_brstack.sh
> @@ -30,7 +30,7 @@ test_user_branches() {
> echo "Testing user branch stack sampling"
>
> perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
>
> # example of branch entries:
> # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
> @@ -59,7 +59,7 @@ test_filter() {
> echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
>
> perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
> - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script
> + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
>
> # fail if we find any branch type that doesn't match any of the expected ones
> # also consider UNKNOWN branch types (-)
> --
> 2.45.2
>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] perf: test: Speed up running brstack test
2025-01-13 14:25 ` Rob Herring
@ 2025-01-13 14:59 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 6+ messages in thread
From: Arnaldo Carvalho de Melo @ 2025-01-13 14:59 UTC (permalink / raw)
To: Rob Herring
Cc: Peter Zijlstra, Ingo Molnar, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Jiri Olsa, Ian Rogers, Adrian Hunter,
Liang, Kan, James Clark, Anshuman Khandual, linux-perf-users,
linux-kernel
On Mon, Jan 13, 2025 at 08:25:45AM -0600, Rob Herring wrote:
> On Fri, Dec 13, 2024 at 5:19 PM Rob Herring (Arm) <robh@kernel.org> wrote:
> >
> > From: James Clark <james.clark@arm.com>
> >
> > The brstack test runs quite slowly in software models. Part of the reason
> > is "xargs -n1" is quite inefficient in replacing spaces with newlines.
> > While that's not noticeable on normal machines, it is on software models.
> > Use "tr -s ' ' '\n'" instead which can do the same transformation, but is
> > much faster. For comparison on an M1 Macbook Pro:
> >
> > $ time seq -s ' ' 10000 | xargs -n1 > /dev/null
> >
> > real 0m2.729s
> > user 0m2.009s
> > sys 0m0.914s
> > $ time seq -s ' ' 10000 | tr -s ' ' '\n' | grep '.' > /dev/null
> >
> > real 0m0.002s
> > user 0m0.001s
> > sys 0m0.001s
> >
> > The "grep '.'" is also needed to remove any remaining blank lines.
> >
> > Signed-off-by: James Clark <james.clark@arm.com>
> > Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
> > [robh: Drop changing loop iterations on arm64. Squash blank line fix and redo commit msg]
> > Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
> > ---
> > Originally part of this series[1], but I've dropped any Arm specifics,
> > and it stands on its own. No reason this needs to wait on Arm BRBE
> > support (which I'm working on now). I don't expect to have other changes
> > to this test related to BRBE anymore.
> >
> > [1] https://lore.kernel.org/all/20240613061731.3109448-8-anshuman.khandual@arm.com/
> >
> > tools/perf/tests/shell/test_brstack.sh | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
>
> Ping!
Thanks, applied.
- Arnaldo
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2025-01-13 14:59 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-12-13 23:13 [PATCH] perf: test: Speed up running brstack test Rob Herring (Arm)
2024-12-17 14:41 ` James Clark
2024-12-18 3:32 ` Anshuman Khandual
2024-12-19 5:48 ` Namhyung Kim
2025-01-13 14:25 ` Rob Herring
2025-01-13 14:59 ` Arnaldo Carvalho de Melo
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.