From: Yang Jihong <yangjihong1@huawei.com>
To: Ian Rogers <irogers@google.com>
Cc: Ian Rogers <irogers@google.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
Nick Terrell <terrelln@fb.com>,
Kan Liang <kan.liang@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
James Clark <james.clark@arm.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Miguel Ojeda <ojeda@kernel.org>,
Liam Howlett <liam.howlett@oracle.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
Kajol Jain <kjain@linux.ibm.com>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Sean Christopherson <seanjc@google.com>,
Yanteng Si <siyanteng@loongson.cn>,
Ravi Bangoria <ravi.bangoria@amd.com>,
German Gomez <german.gomez@arm.com>,
Changbin Du <changbin.du@huawei.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
liuwenyu <liuwenyu7@huawei.com>, <linux-kernel@vger.kernel.org>,
<linux-perf-users@vger.kernel.org>
Subject: Re: [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer
Date: Wed, 25 Oct 2023 11:44:19 +0800 [thread overview]
Message-ID: <7516348d-fe6d-9768-049e-328cfcda89ee@huawei.com> (raw)
In-Reply-To: <20231024222353.3024098-21-irogers@google.com>
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@google.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.
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
next prev parent reply other threads:[~2023-10-25 3:45 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-24 22:23 [PATCH v3 00/50] Improvements to memory use Ian Rogers
2023-10-24 22:23 ` [PATCH v3 01/50] perf rwsem: Add debug mode that uses a mutex Ian Rogers
2023-10-24 22:23 ` [PATCH v3 02/50] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-24 22:23 ` [PATCH v3 03/50] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-24 22:23 ` [PATCH v3 04/50] libperf rc_check: Add RC_CHK_EQUAL Ian Rogers
2023-10-24 22:23 ` [PATCH v3 05/50] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-24 22:23 ` [PATCH v3 06/50] perf threads: Remove unused dead thread list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 07/50] perf offcpu: Add missed btf_free Ian Rogers
2023-10-24 22:23 ` [PATCH v3 08/50] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-24 22:23 ` [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional Ian Rogers
2023-10-24 22:23 ` [PATCH v3 10/50] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 11/50] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-24 22:23 ` [PATCH v3 12/50] perf record: Lazy load kernel symbols Ian Rogers
2023-10-25 18:25 ` Namhyung Kim
2023-10-25 18:35 ` Adrian Hunter
2023-10-24 22:23 ` [PATCH v3 13/50] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-25 2:38 ` Yang Jihong
2023-10-25 3:28 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 14/50] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-10-24 22:23 ` [PATCH v3 15/50] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-24 22:23 ` [PATCH v3 16/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-10-24 22:23 ` [PATCH v3 17/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-10-24 22:23 ` [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative Ian Rogers
2023-10-25 18:43 ` Namhyung Kim
2023-10-25 22:15 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 19/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-10-25 3:44 ` Yang Jihong [this message]
2023-10-25 17:00 ` Ian Rogers
2023-10-25 19:04 ` Namhyung Kim
2023-10-25 19:00 ` Namhyung Kim
2023-10-24 22:23 ` [PATCH v3 21/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 22/50] perf bpf: Don't synthesize BPF events when disabled Ian Rogers
2023-10-24 22:23 ` [PATCH v3 23/50] perf header: Switch mem topology to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 24/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-10-24 22:23 ` [PATCH v3 25/50] perf map: Simplify map_ip/unmap_ip and make map size smaller Ian Rogers
2023-10-24 22:23 ` [PATCH v3 26/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-10-24 22:23 ` [PATCH v3 27/50] perf thread: Add missing RC_CHK_ACCESS Ian Rogers
2023-10-24 22:23 ` [PATCH v3 28/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 29/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 30/50] perf debug: Expose debug file Ian Rogers
2023-10-24 22:23 ` [PATCH v3 31/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-10-24 22:23 ` [PATCH v3 32/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 33/50] perf maps: Rename clone to copy from Ian Rogers
2023-10-24 22:23 ` [PATCH v3 34/50] perf maps: Add maps__load_first Ian Rogers
2023-10-24 22:23 ` [PATCH v3 35/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-10-24 22:23 ` [PATCH v3 36/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 37/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-10-24 22:23 ` [PATCH v3 38/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-10-24 22:23 ` [PATCH v3 39/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-10-24 22:23 ` [PATCH v3 40/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-10-24 22:23 ` [PATCH v3 41/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 42/50] perf maps: Hide maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 43/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-10-24 22:23 ` [PATCH v3 44/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-10-24 22:23 ` [PATCH v3 45/50] perf report: Sort child tasks by tid Ian Rogers
2023-10-24 22:23 ` [PATCH v3 46/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-10-24 22:23 ` [PATCH v3 47/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 48/50] perf threads: Move threads to its own files Ian Rogers
2023-10-24 22:23 ` [PATCH v3 49/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 50/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-10-26 17:11 ` (subset) [PATCH v3 00/50] Improvements to memory use Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7516348d-fe6d-9768-049e-328cfcda89ee@huawei.com \
--to=yangjihong1@huawei.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=changbin.du@huawei.com \
--cc=german.gomez@arm.com \
--cc=irogers@google.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=kjain@linux.ibm.com \
--cc=kprateek.nayak@amd.com \
--cc=leo.yan@linaro.org \
--cc=liam.howlett@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=liuwenyu7@huawei.com \
--cc=mark.rutland@arm.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=ojeda@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=sandipan.das@amd.com \
--cc=seanjc@google.com \
--cc=siyanteng@loongson.cn \
--cc=song@kernel.org \
--cc=terrelln@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox