* [PATCH] perf test: Fix basic bpf filtering test
@ 2020-08-17 7:27 Sumanth Korikkar
2020-08-25 8:32 ` Sumanth Korikkar
0 siblings, 1 reply; 3+ messages in thread
From: Sumanth Korikkar @ 2020-08-17 7:27 UTC (permalink / raw)
To: acme; +Cc: tmricht, hca, svens, jolsa, linux-perf-users, bpf, Sumanth Korikkar
BPF basic filtering test fails on s390x (when vmlinux debuginfo is
utilized instead of /proc/kallsyms)
Info:
- bpf_probe_load installs the bpf code at do_epoll_wait.
- For s390x, do_epoll_wait resolves to 3 functions including inlines.
found inline addr: 0x43769e
Probe point found: __s390_sys_epoll_wait+6
found inline addr: 0x437290
Probe point found: do_epoll_wait+0
found inline addr: 0x4375d6
Probe point found: __se_sys_epoll_wait+6
- add_bpf_event creates evsel for every probe in a BPF object. This
results in 3 evsels.
Solution:
- Expected result = 50% of the samples to be collected from epoll_wait *
number of entries present in the evlist.
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
---
tools/perf/tests/bpf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 5d20bf8397f0..cd77e334e577 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
perf_mmap__read_done(&md->core);
}
- if (count != expect) {
+ if (count != expect * evlist->core.nr_entries) {
pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
goto out_delete_evlist;
}
--
2.17.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] perf test: Fix basic bpf filtering test
2020-08-17 7:27 [PATCH] perf test: Fix basic bpf filtering test Sumanth Korikkar
@ 2020-08-25 8:32 ` Sumanth Korikkar
2020-09-01 15:17 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 3+ messages in thread
From: Sumanth Korikkar @ 2020-08-25 8:32 UTC (permalink / raw)
To: acme; +Cc: tmricht, hca, svens, jolsa, linux-perf-users, bpf
Kind Ping. Thank you.
On 8/17/20 9:27 AM, Sumanth Korikkar wrote:
> BPF basic filtering test fails on s390x (when vmlinux debuginfo is
> utilized instead of /proc/kallsyms)
>
> Info:
> - bpf_probe_load installs the bpf code at do_epoll_wait.
> - For s390x, do_epoll_wait resolves to 3 functions including inlines.
> found inline addr: 0x43769e
> Probe point found: __s390_sys_epoll_wait+6
> found inline addr: 0x437290
> Probe point found: do_epoll_wait+0
> found inline addr: 0x4375d6
> Probe point found: __se_sys_epoll_wait+6
> - add_bpf_event creates evsel for every probe in a BPF object. This
> results in 3 evsels.
>
> Solution:
> - Expected result = 50% of the samples to be collected from epoll_wait *
> number of entries present in the evlist.
>
> Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
> Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
> ---
> tools/perf/tests/bpf.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
> index 5d20bf8397f0..cd77e334e577 100644
> --- a/tools/perf/tests/bpf.c
> +++ b/tools/perf/tests/bpf.c
> @@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
> perf_mmap__read_done(&md->core);
> }
>
> - if (count != expect) {
> + if (count != expect * evlist->core.nr_entries) {
> pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
> goto out_delete_evlist;
> }
--
Sumanth Korikkar
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] perf test: Fix basic bpf filtering test
2020-08-25 8:32 ` Sumanth Korikkar
@ 2020-09-01 15:17 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 3+ messages in thread
From: Arnaldo Carvalho de Melo @ 2020-09-01 15:17 UTC (permalink / raw)
To: Sumanth Korikkar; +Cc: tmricht, hca, svens, jolsa, linux-perf-users, bpf
Em Tue, Aug 25, 2020 at 10:32:45AM +0200, Sumanth Korikkar escreveu:
> Kind Ping. Thank you.
I've applied it already, will go to Linus today.
- Arnaldo
> On 8/17/20 9:27 AM, Sumanth Korikkar wrote:
> > BPF basic filtering test fails on s390x (when vmlinux debuginfo is
> > utilized instead of /proc/kallsyms)
> >
> > Info:
> > - bpf_probe_load installs the bpf code at do_epoll_wait.
> > - For s390x, do_epoll_wait resolves to 3 functions including inlines.
> > found inline addr: 0x43769e
> > Probe point found: __s390_sys_epoll_wait+6
> > found inline addr: 0x437290
> > Probe point found: do_epoll_wait+0
> > found inline addr: 0x4375d6
> > Probe point found: __se_sys_epoll_wait+6
> > - add_bpf_event creates evsel for every probe in a BPF object. This
> > results in 3 evsels.
> >
> > Solution:
> > - Expected result = 50% of the samples to be collected from epoll_wait *
> > number of entries present in the evlist.
> >
> > Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
> > Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
> > ---
> > tools/perf/tests/bpf.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
> > index 5d20bf8397f0..cd77e334e577 100644
> > --- a/tools/perf/tests/bpf.c
> > +++ b/tools/perf/tests/bpf.c
> > @@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
> > perf_mmap__read_done(&md->core);
> > }
> > - if (count != expect) {
> > + if (count != expect * evlist->core.nr_entries) {
> > pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
> > goto out_delete_evlist;
> > }
>
> --
> Sumanth Korikkar
>
--
- Arnaldo
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-09-01 15:17 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-08-17 7:27 [PATCH] perf test: Fix basic bpf filtering test Sumanth Korikkar
2020-08-25 8:32 ` Sumanth Korikkar
2020-09-01 15:17 ` Arnaldo Carvalho de Melo
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).