| 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
| ||
|
Date: Thu, 13 Sep 2018 14:54:49 +0200
From: Jiri Olsa <jolsa@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: lkml <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Andi Kleen <andi@...stfloor.org>,
Alexey Budankov <alexey.budankov@...ux.intel.com>
Subject: [PATCH 47/48] perf record: Spread maps for --threads option
Currently we assign all maps to main thread. Adding
code that spreads maps for --threads option.
For --thread option we create as many threads as there
are memory maps in evlist, which is the number of CPUs
in the system or CPUs we monitor. Each thread gets a
single data mmap to read.
In addition we have also same amount of tracking mmaps
for auxiliary events which we don't create special thread
for. Instead we assign the to the main thread, because
there's not much traffic expected there.
The assignment is visible from --thread-stats output:
pid write poll skip maps (size 20K)
1s 9770 144B 1 0 19K 19K 19K 18K 19K
9772 0B 1 0 18K
9773 0B 1 0 19K
9774 0B 1 0 19K
There are 5 maps for thread 9770 (1 data map and 4 auxiliary)
and one data map for every other thread. Each thread writes
data to the separate data file.
In addition we also pin every thread to the cpu that
the data map belongs to in order to keep both writer
(kernel) and reader (perf tool thread) on the same CPU.
Link: http://lkml.kernel.org/n/tip-ghcsnp3b73innq2gkl1lkfbz@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@...nel.org>
---
tools/perf/builtin-record.c | 133 +++++++++++++++++++++++++++++++++---
1 file changed, 125 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 92ba4d83b18c..4cc728174c79 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -109,6 +109,8 @@ struct record {
struct switch_output switch_output;
unsigned long long samples;
struct record_thread *threads;
+ bool threads_all;
+ bool threads_one;
int threads_cnt;
bool threads_set;
int threads_signal_cnt;
@@ -393,15 +395,11 @@ static int record__mmap_evlist(struct record *rec,
return 0;
}
-static int record__mmap_index(struct record *rec)
+static void record__mmap_index_single(struct record *rec)
{
struct perf_evlist *evlist = rec->evlist;
struct perf_data *data = &rec->data;
- int i, ret, nr = evlist->nr_mmaps;
-
- ret = perf_data__create_index(data, nr);
- if (ret)
- return ret;
+ int i, nr = evlist->nr_mmaps;
for (i = 0; i < nr; i++) {
struct perf_mmap *map = &evlist->mmap[i];
@@ -414,6 +412,50 @@ static int record__mmap_index(struct record *rec)
map->file = &data->file;
}
+}
+
+static void record__mmap_index_all(struct record *rec)
+{
+ struct perf_evlist *evlist = rec->evlist;
+ struct perf_data *data = &rec->data;
+ struct record_thread *threads = rec->threads;
+ struct record_thread *thread0 = threads;
+ int i, t;
+
+ BUG_ON(data->index_nr != rec->threads_cnt);
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ struct perf_mmap *map = &evlist->track_mmap[i];
+
+ map->file = &data->file;
+ }
+
+ thread0->mmap[0]->file = &data->index[0];
+
+ for (t = 1; t < rec->threads_cnt; t++) {
+ struct record_thread *th = threads + t;
+
+ for (i = 0; i < th->mmap_nr; i++) {
+ struct perf_mmap *map = th->mmap[i];
+
+ map->file = &data->index[t];
+ }
+ }
+}
+
+static int record__mmap_index(struct record *rec)
+{
+ struct perf_data *data = &rec->data;
+ int ret;
+
+ ret = perf_data__create_index(data, rec->threads_cnt);
+ if (ret)
+ return ret;
+
+ if (rec->threads_all)
+ record__mmap_index_all(rec);
+ else if (rec->threads_one)
+ record__mmap_index_single(rec);
return 0;
}
@@ -1056,7 +1098,7 @@ record_thread__mmap(struct record_thread *th, int nr, int nr_ovw)
}
static int
-record__threads_assign(struct record *rec)
+record__threads_assign_single(struct record *rec)
{
struct record_thread *threads = rec->threads;
struct record_thread *thread0 = threads;
@@ -1089,6 +1131,55 @@ record__threads_assign(struct record *rec)
return ret;
}
+static int
+record__threads_assign_all(struct record *rec)
+{
+ struct perf_evlist *evlist = rec->evlist;
+ struct record_thread *threads = rec->threads;
+ struct record_thread *thread0 = threads;
+ int cnt = rec->threads_cnt;
+ int i, t, nr, nr0, nr_trk;
+ int nr_cpus = cpu__max_present_cpu();
+
+ nr = evlist->mmap ? evlist->nr_mmaps : 0;
+ nr_trk = evlist->track_mmap ? evlist->nr_mmaps : 0;
+
+ BUG_ON(evlist->overwrite_mmap);
+ BUG_ON(nr_cpus != nr);
+
+ nr0 = 1 + nr_trk;
+
+ if (record_thread__mmap(thread0, nr0, 0))
+ return -ENOMEM;
+
+ thread0->mmap[0] = &evlist->mmap[0];
+
+ for (i = 0; i < nr_trk; i++)
+ thread0->mmap[i + 1] = &evlist->track_mmap[i];
+
+ for (t = 1; t < cnt; t++) {
+ struct record_thread *th = threads + t;
+
+ if (record_thread__mmap(th, 1, 0))
+ return -ENOMEM;
+
+ th->mmap[0] = &evlist->mmap[t];
+ }
+
+ return 0;
+}
+
+static int
+record__threads_assign(struct record *rec)
+{
+ if (rec->threads_all)
+ return record__threads_assign_all(rec);
+ else if (rec->threads_one)
+ return record__threads_assign_single(rec);
+ else
+ return -EINVAL;
+}
+
static int
record_thread__create_poll(struct record_thread *th,
struct perf_evlist *evlist)
@@ -1146,7 +1237,8 @@ record__threads_create(struct record *rec)
static int record__threads_cnt(struct record *rec)
{
struct perf_evlist *evlist = rec->evlist;
- int cnt;
+ bool all = false, one = false;
+ int cnt = 0;
if (rec->threads_set) {
if (rec->threads_cnt) {
@@ -1158,11 +1250,15 @@ static int record__threads_cnt(struct record *rec)
return -EINVAL;
}
cnt = evlist->nr_mmaps;
+ all = true;
} else {
+ one = true;
cnt = 1;
}
rec->threads_cnt = cnt;
+ rec->threads_all = all;
+ rec->threads_one = one;
return 0;
}
@@ -1200,6 +1296,25 @@ static inline pid_t gettid(void)
return (pid_t) syscall(__NR_gettid);
}
+static int set_affinity(int cpu)
+{
+ cpu_set_t mask;
+
+ CPU_ZERO(&mask);
+ CPU_SET(cpu, &mask);
+ return sched_setaffinity(0, sizeof(mask), &mask);
+}
+
+static void set_thread_affinity(struct record *rec)
+{
+ if (rec->threads_all) {
+ struct perf_mmap *m0 = thread->mmap[0];
+
+ if (set_affinity(m0->cpu))
+ pr_err("failed to set affinity for cpu %d\n", m0->cpu);
+ }
+}
+
static void*
record_thread__process(struct record *rec)
{
@@ -1263,6 +1378,7 @@ static void *worker(void *arg)
thread->state = RECORD_THREAD__RUNNING;
signal_main(rec);
+ set_thread_affinity(rec);
return record_thread__process(rec);
}
@@ -1283,6 +1399,7 @@ static int record__threads_start(struct record *rec)
if (rec->threads_cnt > 1)
wait_for_signal(rec);
+ set_thread_affinity(rec);
return err;
}
--
2.17.1
Powered by blists - more mailing lists