| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAP-5=fX2Mk9uUfbnF75B=2xFjGy3HWtjPaM-B0-_KWaHjBW0qQ@mail.gmail.com>
Date: Wed, 25 Oct 2023 10:00:50 -0700
From: Ian Rogers <irogers@...gle.com>
To: Yang Jihong <yangjihong1@...wei.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Nick Terrell <terrelln@...com>,
Kan Liang <kan.liang@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>, Leo Yan <leo.yan@...aro.org>,
Song Liu <song@...nel.org>,
Sandipan Das <sandipan.das@....com>,
James Clark <james.clark@....com>,
Anshuman Khandual <anshuman.khandual@....com>,
Miguel Ojeda <ojeda@...nel.org>,
Liam Howlett <liam.howlett@...cle.com>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>,
Kajol Jain <kjain@...ux.ibm.com>,
K Prateek Nayak <kprateek.nayak@....com>,
Sean Christopherson <seanjc@...gle.com>,
Yanteng Si <siyanteng@...ngson.cn>,
Ravi Bangoria <ravi.bangoria@....com>,
German Gomez <german.gomez@....com>,
Changbin Du <changbin.du@...wei.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Masami Hiramatsu <mhiramat@...nel.org>,
liuwenyu <liuwenyu7@...wei.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org
Subject: Re: [PATCH v3 20/50] perf record: Be lazier in allocating lost
samples buffer
On Tue, Oct 24, 2023 at 8:44 PM Yang Jihong <yangjihong1@...wei.com> wrote:
>
> Hello,
>
> On 2023/10/25 6:23, Ian Rogers wrote:
> > Wait until a lost sample occurs to allocate the lost samples buffer,
> > often the buffer isn't necessary. This saves a 64kb allocation and
> > 5.3kb of peak memory consumption.
> >
> > Signed-off-by: Ian Rogers <irogers@...gle.com>
> > ---
> > tools/perf/builtin-record.c | 29 +++++++++++++++++++----------
> > 1 file changed, 19 insertions(+), 10 deletions(-)
> >
> > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > index 9b4f3805ca92..b6c8c1371b39 100644
> > --- a/tools/perf/builtin-record.c
> > +++ b/tools/perf/builtin-record.c
> > @@ -1924,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
> > static void record__read_lost_samples(struct record *rec)
> > {
> > struct perf_session *session = rec->session;
> > - struct perf_record_lost_samples *lost;
> > + struct perf_record_lost_samples *lost = NULL;
> > struct evsel *evsel;
> >
> > /* there was an error during record__open */
> > if (session->evlist == NULL)
> > return;
> >
> > - lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > - if (lost == NULL) {
> > - pr_debug("Memory allocation failed\n");
> > - return;
> > - }
> > -
> > - lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > -
> > evlist__for_each_entry(session->evlist, evsel) {
> > struct xyarray *xy = evsel->core.sample_id;
> > u64 lost_count;
> > @@ -1961,6 +1953,14 @@ static void record__read_lost_samples(struct record *rec)
> > }
> >
> > if (count.lost) {
> > + if (!lost) {
> > + lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > + if (!lost) {
> > + pr_debug("Memory allocation failed\n");
> > + return;
> > + }
> > + lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > + }
> > __record__save_lost_samples(rec, evsel, lost,
> > x, y, count.lost, 0);
> > }
> > @@ -1968,9 +1968,18 @@ static void record__read_lost_samples(struct record *rec)
> > }
> >
> > lost_count = perf_bpf_filter__lost_count(evsel);
> > - if (lost_count)
> > + if (lost_count) {
> > + if (!lost) {
> > + lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > + if (!lost) {
> > + pr_debug("Memory allocation failed\n");
> > + return;
> > + }
> > + lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > + }
> > __record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
> > PERF_RECORD_MISC_LOST_SAMPLES_BPF);
> > + }
> > }
>
> Can zalloc for `lost` be moved to __record__save_lost_samples?
> This simplifies the code.
Hmm.. seems marginal. This change makes the code not return in
record__read_lost_samples when the memory allocation fails, so I'm
50/50 on it.
Thanks,
Ian
>
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index dcf288a4fb9a..8d2eb746031a 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -1888,14 +1888,25 @@ record__switch_output(struct record *rec, bool
> at_exit)
> }
>
> static void __record__save_lost_samples(struct record *rec, struct
> evsel *evsel,
> - struct perf_record_lost_samples
> *lost,
> + struct perf_record_lost_samples
> **plost,
> int cpu_idx, int thread_idx,
> u64 lost_count,
> u16 misc_flag)
> {
> struct perf_sample_id *sid;
> struct perf_sample sample = {};
> + struct perf_record_lost_samples *lost = *plost;
> int id_hdr_size;
>
> + if (!lost) {
> + lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> + if (!lost) {
> + pr_debug("Memory allocation failed\n");
> + return;
> + }
> + lost->header.type = PERF_RECORD_LOST_SAMPLES;
> + *plost = lost;
> + }
> +
> lost->lost = lost_count;
> if (evsel->core.ids) {
> sid = xyarray__entry(evsel->core.sample_id, cpu_idx,
> thread_idx);
> @@ -1912,21 +1923,13 @@ static void __record__save_lost_samples(struct
> record *rec, struct evsel *evsel,
> static void record__read_lost_samples(struct record *rec)
> {
> struct perf_session *session = rec->session;
> - struct perf_record_lost_samples *lost;
> + struct perf_record_lost_samples *lost = NULL;
> struct evsel *evsel;
>
> /* there was an error during record__open */
> if (session->evlist == NULL)
> return;
>
> - lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> - if (lost == NULL) {
> - pr_debug("Memory allocation failed\n");
> - return;
> - }
> -
> - lost->header.type = PERF_RECORD_LOST_SAMPLES;
> -
> evlist__for_each_entry(session->evlist, evsel) {
> struct xyarray *xy = evsel->core.sample_id;
> u64 lost_count;
> @@ -1949,7 +1952,7 @@ static void record__read_lost_samples(struct
> record *rec)
> }
>
> if (count.lost) {
> - __record__save_lost_samples(rec,
> evsel, lost,
> + __record__save_lost_samples(rec,
> evsel, &lost,
> x,
> y, count.lost, 0);
> }
> }
> @@ -1957,11 +1960,12 @@ static void record__read_lost_samples(struct
> record *rec)
>
> lost_count = perf_bpf_filter__lost_count(evsel);
> if (lost_count)
> - __record__save_lost_samples(rec, evsel, lost, 0,
> 0, lost_count,
> + __record__save_lost_samples(rec, evsel, &lost,
> 0, 0, lost_count,
>
> PERF_RECORD_MISC_LOST_SAMPLES_BPF);
> }
> out:
> - free(lost);
> + if (lost)
> + free(lost);
> }
>
> static volatile sig_atomic_t workload_exec_errno;
>
>
> Thanks,
> Yang
>
Powered by blists - more mailing lists