perf lock contention: Add BPF support (v1)
Namhyung Kim
maintainercover perf lock contention: Add BPF support (v1)
Hello,
This patchset adds -b/--use-bpf option and others to use BPF to collect kernel lock contention stats. With this option it doesn't require a separate perf lock record step. Basic filtering on cpu (with -a or -C option) and on task (with -p and --tid option) is supported as usual.
$ sudo perf lock con -a -b sleep 1
contended total wait max wait avg wait type caller 42 192.67 us 13.64 us 4.59 us spinlock queue_work_on+0x20
23 85.54 us 10.28 us 3.72 us spinlock worker_thread+0x14a
6 13.92 us 6.51 us 2.32 us mutex kernfs_iop_permission+0x30
3 11.59 us 10.04 us 3.86 us mutex kernfs_dop_revalidate+0x3c
1 7.52 us 7.52 us 7.52 us spinlock kthread+0x115
1 7.24 us 7.24 us 7.24 us rwlock:W sys_epoll_wait+0x148
2 7.08 us 3.99 us 3.54 us spinlock delayed_work_timer_fn+0x1b
1 6.41 us 6.41 us 6.41 us spinlock idle_balance+0xa06
2 2.50 us 1.83 us 1.25 us mutex kernfs_iop_lookup+0x2f
1 1.71 us 1.71 us 1.71 us mutex kernfs_iop_getattr+0x2cIt seems my system had some contentions on the workqueue spinlock and the kernfs mutex.
The code is available at perf/lock-bpf-v1 branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git
Thanks,
Namhyung
Namhyung Kim (3):
perf lock: Pass machine pointer to is_lock_function() perf lock: Use BPF for lock contention analysis perf lock: Implement cpu and task filters for BPF
tools/perf/Documentation/perf-lock.txt | 22 ++ tools/perf/Makefile.perf | 2 +- tools/perf/builtin-lock.c | 226 ++++++++---------- tools/perf/util/Build | 1 + tools/perf/util/bpf_lock_contention.c | 181 ++++++++++++++ .../perf/util/bpf_skel/lock_contention.bpf.c | 170 +++++++++++++ tools/perf/util/lock-contention.h | 140 +++++++++++ 7 files changed, 614 insertions(+), 128 deletions(-) create mode 100644 tools/perf/util/bpf_lock_contention.c create mode 100644 tools/perf/util/bpf_skel/lock_contention.bpf.c create mode 100644 tools/perf/util/lock-contention.h
Signature · 1 line
2.37.1.455.g008518b4e5-goog
Namhyung Kim
maintainerPATCH 1/3 perf lock: Pass machine pointer to is_lock_function()
This is a preparation for later change to expose the function externally so that it can be used without the implicit session data.
--- tools/perf/builtin-lock.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)
tools/perf/builtin-lock.c +7 -8
@@ -947,10 +947,9 @@ static int report_lock_release_event(struct evsel *evsel,return 0 ; } -static bool is_lock_function (u64 addr) +static bool is_lock_function (struct machine *machine,u64 addr) {if (!sched_text_start) { -struct machine *machine = &session->machines.host;struct map *kmap;struct symbol *sym;
@@ -1002,6 +1001,7 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl {struct thread *thread;struct callchain_cursor *cursor = &callchain_cursor; +struct machine *machine = &session->machines.host;struct symbol *sym;int skip =0 ;int ret;
@@ -1010,8 +1010,7 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *samplif (show_thread_stats)return -1 ; - thread =machine__findnew_thread (&session->machines.host, --1 , sample->pid); + thread =machine__findnew_thread (machine,-1 , sample->pid);if (thread ==NULL )return -1 ;
@@ -1038,7 +1037,7 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl goto next; sym = node->ms.sym; -if (sym && !is_lock_function (node->ip)) { +if (sym && !is_lock_function (machine, node->ip)) {struct map *map = node->ms.map;u64 offset;
@@ -1060,13 +1059,13 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *samplstatic u64 callchain_id (struct evsel *evsel,struct perf_sample *sample) {struct callchain_cursor *cursor = &callchain_cursor; +struct machine *machine = &session->machines.host;struct thread *thread;u64 hash =0 ;int skip =0 ;int ret; - thread =machine__findnew_thread (&session->machines.host, --1 , sample->pid); + thread =machine__findnew_thread (machine,-1 , sample->pid);if (thread ==NULL )return -1 ;
@@ -1091,7 +1090,7 @@ static u64 callchain_id(struct evsel *evsel, struct perf_sample *sample)if (++skip <=CONTENTION_STACK_SKIP ) goto next; -if (node->ms.sym &&is_lock_function (node->ip)) +if (node->ms.sym &&is_lock_function (machine, node->ip)) goto next; hash ^=hash_long ((unsigned long )node->ip,64 );
Signature · 1 line
2.37.1.455.g008518b4e5-goog
Namhyung Kim
maintainerPATCH 2/3 perf lock: Use BPF for lock contention analysis
In reply to Namhyung KimAdd -b/--use-bpf option to use BPF to collect lock contention stats. For simplicity it now runs system-wide and requires C-c to stop. Upcoming changes will add the usual filtering.
$ sudo perf lock con -b ^C contended total wait max wait avg wait type caller
42 192.67 us 13.64 us 4.59 us spinlock queue_work_on+0x20
23 85.54 us 10.28 us 3.72 us spinlock worker_thread+0x14a
6 13.92 us 6.51 us 2.32 us mutex kernfs_iop_permission+0x30
3 11.59 us 10.04 us 3.86 us mutex kernfs_dop_revalidate+0x3c
1 7.52 us 7.52 us 7.52 us spinlock kthread+0x115
1 7.24 us 7.24 us 7.24 us rwlock:W sys_epoll_wait+0x148
2 7.08 us 3.99 us 3.54 us spinlock delayed_work_timer_fn+0x1b
1 6.41 us 6.41 us 6.41 us spinlock idle_balance+0xa06
2 2.50 us 1.83 us 1.25 us mutex kernfs_iop_lookup+0x2f
1 1.71 us 1.71 us 1.71 us mutex kernfs_iop_getattr+0x2c--- tools/perf/Documentation/perf-lock.txt | 5 + tools/perf/Makefile.perf | 2 +- tools/perf/builtin-lock.c | 164 ++++++------------ tools/perf/util/Build | 1 + tools/perf/util/bpf_lock_contention.c | 132 ++++++++++++++ .../perf/util/bpf_skel/lock_contention.bpf.c | 131 ++++++++++++++ tools/perf/util/lock-contention.h | 133 ++++++++++++++ 7 files changed, 453 insertions(+), 115 deletions(-) create mode 100644 tools/perf/util/bpf_lock_contention.c create mode 100644 tools/perf/util/bpf_skel/lock_contention.bpf.c create mode 100644 tools/perf/util/lock-contention.h
tools/perf/Documentation/perf-lock.txt +5 -0
@@ -123,6 +123,11 @@ CONTENTION OPTIONS --threads:: Show per-thread lock contention stat +-b:: +--use-bpf:: + Use BPF program to collect lock contention stats instead of + using the input data. + SEE ALSO --------
tools/perf/Makefile.perf +1 -1
@@ -1028,7 +1028,7 @@ SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h -SKELETONS += $(SKEL_OUT)/off_cpu.skel.h +SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_TMP_OUT) $(LIBBPF_OUTPUT):
tools/perf/builtin-lock.c +50 -114
242 lines not on this page · raw message
tools/perf/util/Build +1 -0
@@ -149,6 +149,7 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o
tools/perf/util/bpf_lock_contention.c new file +132 -0
132 lines not on this page · raw message
tools/perf/util/bpf_skel/lock_contention.bpf.c new file +131 -0
131 lines not on this page · raw message
tools/perf/util/lock-contention.h new file +133 -0
133 lines not on this page · raw message
Signature · 1 line
2.37.1.455.g008518b4e5-goog
Namhyung Kim
maintainerPATCH 3/3 perf lock: Implement cpu and task filters for BPF
In reply to Namhyung KimAdd -a/--all-cpus and -C/--cpu options for cpu filtering. Also -p/--pid and --tid options are added for task filtering. The short -t option is taken for --threads already. Tracking the command line workload is possible as well.
$ sudo perf lock contention -a -b sleep 1
--- tools/perf/Documentation/perf-lock.txt | 17 ++++++ tools/perf/builtin-lock.c | 55 ++++++++++++++++--- tools/perf/util/bpf_lock_contention.c | 51 ++++++++++++++++- .../perf/util/bpf_skel/lock_contention.bpf.c | 41 +++++++++++++- tools/perf/util/lock-contention.h | 11 +++- 5 files changed, 162 insertions(+), 13 deletions(-)
tools/perf/Documentation/perf-lock.txt +17 -0
@@ -128,6 +128,23 @@ CONTENTION OPTIONS Use BPF program to collect lock contention stats instead of using the input data. +-a:: +--all-cpus:: + System-wide collection from all CPUs. + +-C:: +--cpu:: + Collect samples only on the list of CPUs provided. Multiple CPUs can be + provided as a comma-separated list with no space: 0,1. Ranges of CPUs + are specified with -: 0-2. Default is to monitor all CPUs. + +-p:: +--pid=:: + Record events on existing process ID (comma separated list). + +--tid=:: + Record events on existing thread ID (comma separated list). + SEE ALSO --------
tools/perf/builtin-lock.c +46 -9
115 lines not on this page · raw message
tools/perf/util/bpf_lock_contention.c +50 -1
77 lines not on this page · raw message
tools/perf/util/bpf_skel/lock_contention.bpf.c +40 -1
55 lines not on this page · raw message
tools/perf/util/lock-contention.h +9 -2
@@ -103,11 +103,13 @@ struct thread_stat {#define LCB_F_PERCPU (1U << 4)#define LCB_F_MUTEX (1U << 5) +struct evlist ;struct machine ; +struct target ;#ifdef HAVE_BPF_SKEL -int lock_contention_prepare (void ); +int lock_contention_prepare (struct evlist *evlist,struct target *target);int lock_contention_start (void );int lock_contention_stop (void );int lock_contention_read (struct machine *machine,struct hlist_head *head);
@@ -115,7 +117,12 @@ int lock_contention_finish(void);#else /* !HAVE_BPF_SKEL */ -static inline int lock_contention_prepare (void ) {return 0 ; } +static inline int lock_contention_prepare (struct evlist *evlist__maybe_unused , +struct target *target__maybe_unused ) +{ +return 0 ; +} +static inline int lock_contention_start (void ) {return 0 ; }static inline int lock_contention_stop (void ) {return 0 ; }static inline int lock_contention_finish (void ) {return 0 ; }
Signature · 1 line
2.37.1.455.g008518b4e5-goog
Em Fri, Jul 29, 2022 at 01:07:53PM -0700, Namhyung Kim escreveu:
Quoted 22 lines
Hello,
This patchset adds -b/--use-bpf option and others to use BPF to collect kernel lock contention stats. With this option it doesn't require a separate
perf lock recordstep. Basic filtering on cpu (with -a or -C option) and on task (with -p and --tid option) is supported as usual.$ sudo perf lock con -a -b sleep 1 contended total wait max wait avg wait type caller42 192.67 us 13.64 us 4.59 us spinlock queue_work_on+0x20 23 85.54 us 10.28 us 3.72 us spinlock worker_thread+0x14a 6 13.92 us 6.51 us 2.32 us mutex kernfs_iop_permission+0x30 3 11.59 us 10.04 us 3.86 us mutex kernfs_dop_revalidate+0x3c 1 7.52 us 7.52 us 7.52 us spinlock kthread+0x115 1 7.24 us 7.24 us 7.24 us rwlock:W sys_epoll_wait+0x148 2 7.08 us 3.99 us 3.54 us spinlock delayed_work_timer_fn+0x1b 1 6.41 us 6.41 us 6.41 us spinlock idle_balance+0xa06 2 2.50 us 1.83 us 1.25 us mutex kernfs_iop_lookup+0x2f 1 1.71 us 1.71 us 1.71 us mutex kernfs_iop_getattr+0x2c
Quoted 6 lines
It seems my system had some contentions on the workqueue spinlock and the kernfs mutex.
The code is available at perf/lock-bpf-v1 branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git
Thanks, applied.
- Arnaldo
Quoted 23 lines
Thanks,
NamhyungNamhyung Kim (3):
perf lock: Pass machine pointer tois_lock_function()perf lock: Use BPF for lock contention analysis perf lock: Implement cpu and task filters for BPFtools/perf/Documentation/perf-lock.txt | 22 ++ tools/perf/Makefile.perf | 2 +- tools/perf/builtin-lock.c | 226 ++++++++---------- tools/perf/util/Build | 1 + tools/perf/util/bpf_lock_contention.c | 181 ++++++++++++++ .../perf/util/bpf_skel/lock_contention.bpf.c | 170 +++++++++++++ tools/perf/util/lock-contention.h | 140 +++++++++++ 7 files changed, 614 insertions(+), 128 deletions(-) create mode 100644 tools/perf/util/bpf_lock_contention.c create mode 100644 tools/perf/util/bpf_skel/lock_contention.bpf.c create mode 100644 tools/perf/util/lock-contention.hSignature · 1 line
2.37.1.455.g008518b4e5-goog
Signature · 1 line
- Arnaldo