From: Ian Rogers <irogers@google.com>
To: 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@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Masahiro Yamada <yamada.masahiro@socionext.com>,
Kees Cook <keescook@chromium.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Petr Mladek <pmladek@suse.com>,
Mauro Carvalho Chehab <mchehab+samsung@kernel.org>,
Qian Cai <cai@lca.pw>, Joe Lawrence <joe.lawrence@redhat.com>,
Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>,
"Uladzislau Rezki (Sony)" <urezki@gmail.com>,
Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
Ard Biesheuvel <ardb@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Kent Overstreet <kent.overstreet@gmail.com>,
Gary Hook <Gary.Hook@amd.com>, Arnd Bergmann <arnd@arndb.de>,
Kan Liang <kan.liang@linux.intel.com>,
linux-kernel@vger.kernel.org
Cc: Stephane Eranian <eranian@google.com>,
Andi Kleen <ak@linux.intel.com>, Ian Rogers <irogers@google.com>
Subject: [PATCH v5 08/10] perf: cache perf_event_groups_first for cgroups
Date: Fri, 6 Dec 2019 15:15:37 -0800 [thread overview]
Message-ID: <20191206231539.227585-9-irogers@google.com> (raw)
In-Reply-To: <20191206231539.227585-1-irogers@google.com>
Add a per-CPU cache of the pinned and flexible perf_event_groups_first
value for a cgroup avoiding an O(log(#perf events)) searches during
sched_in.
Based-on-work-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
include/linux/perf_event.h | 7 ++++
kernel/events/core.c | 84 ++++++++++++++++++++++++++++++++++----
2 files changed, 82 insertions(+), 9 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index cd7d3b624655..a29a38df909e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -892,6 +892,13 @@ struct perf_cgroup_info {
struct perf_cgroup {
struct cgroup_subsys_state css;
struct perf_cgroup_info __percpu *info;
+ /*
+ * A cache of the first event with the perf_cpu_context's
+ * perf_event_context for the first event in pinned_groups or
+ * flexible_groups. Avoids an rbtree search during sched_in.
+ */
+ struct perf_event * __percpu *pinned_event;
+ struct perf_event * __percpu *flexible_event;
};
/*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3da9cc1ebc2d..5935d2474050 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1638,6 +1638,27 @@ perf_event_groups_insert(struct perf_event_groups *groups,
rb_link_node(&event->group_node, parent, node);
rb_insert_color(&event->group_node, &groups->tree);
+#ifdef CONFIG_CGROUP_PERF
+ if (is_cgroup_event(event)) {
+ struct perf_event **cgrp_event;
+
+ if (event->attr.pinned) {
+ cgrp_event = per_cpu_ptr(event->cgrp->pinned_event,
+ event->cpu);
+ } else {
+ cgrp_event = per_cpu_ptr(event->cgrp->flexible_event,
+ event->cpu);
+ }
+ /*
+ * Remember smallest, left-most, group index event. The
+ * less-than condition is only possible if the group_index
+ * overflows.
+ */
+ if (!*cgrp_event ||
+ event->group_index < (*cgrp_event)->group_index)
+ *cgrp_event = event;
+ }
+#endif
}
/*
@@ -1652,6 +1673,9 @@ add_event_to_groups(struct perf_event *event, struct perf_event_context *ctx)
perf_event_groups_insert(groups, event);
}
+static struct perf_event *
+perf_event_groups_next(struct perf_event *event);
+
/*
* Delete a group from a tree.
*/
@@ -1662,6 +1686,22 @@ perf_event_groups_delete(struct perf_event_groups *groups,
WARN_ON_ONCE(RB_EMPTY_NODE(&event->group_node) ||
RB_EMPTY_ROOT(&groups->tree));
+#ifdef CONFIG_CGROUP_PERF
+ if (is_cgroup_event(event)) {
+ struct perf_event **cgrp_event;
+
+ if (event->attr.pinned) {
+ cgrp_event = per_cpu_ptr(event->cgrp->pinned_event,
+ event->cpu);
+ } else {
+ cgrp_event = per_cpu_ptr(event->cgrp->flexible_event,
+ event->cpu);
+ }
+ if (*cgrp_event == event)
+ *cgrp_event = perf_event_groups_next(event);
+ }
+#endif
+
rb_erase(&event->group_node, &groups->tree);
init_event_group(event);
}
@@ -1679,7 +1719,8 @@ del_event_from_groups(struct perf_event *event, struct perf_event_context *ctx)
}
/*
- * Get the leftmost event in the cpu/cgroup subtree.
+ * Get the leftmost event in the cpu subtree without a cgroup (ie task or
+ * system-wide).
*/
static struct perf_event *
perf_event_groups_first(struct perf_event_groups *groups, int cpu,
@@ -3596,8 +3637,8 @@ static int ctx_groups_sched_in(struct perf_event_context *ctx,
.cap = ARRAY_SIZE(itrs),
};
/* Events not within a CPU context may be on any CPU. */
- __heap_add(&event_heap, perf_event_groups_first(groups, -1,
- NULL));
+ __heap_add(&event_heap,
+ perf_event_groups_first(groups, -1, NULL));
}
evt = event_heap.data;
@@ -3605,8 +3646,16 @@ static int ctx_groups_sched_in(struct perf_event_context *ctx,
#ifdef CONFIG_CGROUP_PERF
for (; css; css = css->parent) {
- __heap_add(&event_heap, perf_event_groups_first(groups, cpu,
- css->cgroup));
+ struct perf_cgroup *cgrp;
+
+ /* root cgroup doesn't have events */
+ if (css->id == 1)
+ break;
+
+ cgrp = container_of(css, struct perf_cgroup, css);
+ __heap_add(&event_heap, is_pinned
+ ? *per_cpu_ptr(cgrp->pinned_event, cpu)
+ : *per_cpu_ptr(cgrp->flexible_event, cpu));
}
#endif
@@ -12672,18 +12721,35 @@ perf_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
return ERR_PTR(-ENOMEM);
jc->info = alloc_percpu(struct perf_cgroup_info);
- if (!jc->info) {
- kfree(jc);
- return ERR_PTR(-ENOMEM);
- }
+ if (!jc->info)
+ goto free_jc;
+
+ jc->pinned_event = alloc_percpu(struct perf_event *);
+ if (!jc->pinned_event)
+ goto free_jc_info;
+
+ jc->flexible_event = alloc_percpu(struct perf_event *);
+ if (!jc->flexible_event)
+ goto free_jc_pinned;
return &jc->css;
+
+free_jc_pinned:
+ free_percpu(jc->pinned_event);
+free_jc_info:
+ free_percpu(jc->info);
+free_jc:
+ kfree(jc);
+
+ return ERR_PTR(-ENOMEM);
}
static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct perf_cgroup *jc = container_of(css, struct perf_cgroup, css);
+ free_percpu(jc->pinned_event);
+ free_percpu(jc->flexible_event);
free_percpu(jc->info);
kfree(jc);
}
--
2.24.0.393.g34dc348eaf-goog
next prev parent reply other threads:[~2019-12-06 23:16 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-14 0:30 [PATCH v3 00/10] Optimize cgroup context switch Ian Rogers
2019-11-14 0:30 ` [PATCH v3 01/10] perf/cgroup: Reorder perf_cgroup_connect() Ian Rogers
2019-11-14 8:50 ` Peter Zijlstra
2019-11-14 0:30 ` [PATCH v3 02/10] lib: introduce generic min max heap Ian Rogers
2019-11-14 9:32 ` Peter Zijlstra
2019-11-14 9:35 ` Peter Zijlstra
2019-11-17 18:28 ` Joe Perches
2019-11-18 8:40 ` Peter Zijlstra
2019-11-18 11:50 ` Joe Perches
2019-11-18 12:21 ` Peter Zijlstra
2019-11-14 0:30 ` [PATCH v3 03/10] perf: Use min_max_heap in visit_groups_merge Ian Rogers
2019-11-14 9:39 ` Peter Zijlstra
2019-11-14 0:30 ` [PATCH v3 04/10] perf: Add per perf_cpu_context min_heap storage Ian Rogers
2019-11-14 9:51 ` Peter Zijlstra
2019-11-16 1:19 ` Ian Rogers
2019-11-14 0:30 ` [PATCH v3 05/10] perf/cgroup: Grow per perf_cpu_context heap storage Ian Rogers
2019-11-14 9:54 ` Peter Zijlstra
2019-11-14 0:30 ` [PATCH v3 06/10] perf/cgroup: Order events in RB tree by cgroup id Ian Rogers
2019-11-14 0:30 ` [PATCH v3 07/10] perf: simplify and rename visit_groups_merge Ian Rogers
2019-11-14 10:03 ` Peter Zijlstra
2019-11-16 1:20 ` Ian Rogers
2019-11-14 0:30 ` [PATCH v3 08/10] perf: cache perf_event_groups_first for cgroups Ian Rogers
2019-11-14 10:25 ` Peter Zijlstra
2019-11-16 1:20 ` Ian Rogers
2019-11-18 8:37 ` Peter Zijlstra
2019-11-14 0:30 ` [PATCH v3 09/10] perf: optimize event_filter_match during sched_in Ian Rogers
2019-11-14 0:30 ` [PATCH v3 10/10] perf/cgroup: Do not switch system-wide events in cgroup switch Ian Rogers
2019-11-14 10:43 ` Peter Zijlstra
2019-11-14 13:46 ` Liang, Kan
2019-11-14 13:57 ` Peter Zijlstra
2019-11-14 15:16 ` Liang, Kan
2019-11-14 15:24 ` Liang, Kan
2019-11-14 20:49 ` Liang, Kan
2019-11-14 0:42 ` [PATCH v3 00/10] Optimize cgroup context switch Ian Rogers
2019-11-14 10:45 ` Peter Zijlstra
2019-11-14 18:17 ` Ian Rogers
2019-12-06 23:16 ` Ian Rogers
2019-11-16 1:18 ` [PATCH v4 " Ian Rogers
2019-11-16 1:18 ` [PATCH v4 01/10] perf/cgroup: Reorder perf_cgroup_connect() Ian Rogers
2019-11-16 1:18 ` [PATCH v4 02/10] lib: introduce generic min max heap Ian Rogers
2019-11-21 11:11 ` Joe Perches
2019-11-16 1:18 ` [PATCH v4 03/10] perf: Use min_max_heap in visit_groups_merge Ian Rogers
2019-11-16 1:18 ` [PATCH v4 04/10] perf: Add per perf_cpu_context min_heap storage Ian Rogers
2019-11-16 1:18 ` [PATCH v4 05/10] perf/cgroup: Grow per perf_cpu_context heap storage Ian Rogers
2019-11-16 1:18 ` [PATCH v4 06/10] perf/cgroup: Order events in RB tree by cgroup id Ian Rogers
2019-11-16 1:18 ` [PATCH v4 07/10] perf: simplify and rename visit_groups_merge Ian Rogers
2019-11-16 1:18 ` [PATCH v4 08/10] perf: cache perf_event_groups_first for cgroups Ian Rogers
2019-11-16 1:18 ` [PATCH v4 09/10] perf: optimize event_filter_match during sched_in Ian Rogers
2019-11-16 1:18 ` [PATCH v4 10/10] perf/cgroup: Do not switch system-wide events in cgroup switch Ian Rogers
2019-12-06 23:15 ` [PATCH v5 00/10] Optimize cgroup context switch Ian Rogers
2019-12-06 23:15 ` [PATCH v5 01/10] perf/cgroup: Reorder perf_cgroup_connect() Ian Rogers
2019-12-06 23:15 ` [PATCH v5 02/10] lib: introduce generic min-heap Ian Rogers
2019-12-06 23:15 ` [PATCH v5 03/10] perf: Use min_max_heap in visit_groups_merge Ian Rogers
2019-12-08 7:10 ` kbuild test robot
2019-12-06 23:15 ` [PATCH v5 04/10] perf: Add per perf_cpu_context min_heap storage Ian Rogers
2019-12-06 23:15 ` [PATCH v5 05/10] perf/cgroup: Grow per perf_cpu_context heap storage Ian Rogers
2019-12-06 23:15 ` [PATCH v5 06/10] perf/cgroup: Order events in RB tree by cgroup id Ian Rogers
2019-12-06 23:15 ` [PATCH v5 07/10] perf: simplify and rename visit_groups_merge Ian Rogers
2019-12-06 23:15 ` Ian Rogers [this message]
2019-12-06 23:15 ` [PATCH v5 09/10] perf: optimize event_filter_match during sched_in Ian Rogers
2019-12-06 23:15 ` [PATCH v5 10/10] perf/cgroup: Do not switch system-wide events in cgroup switch Ian Rogers
2020-02-14 7:51 ` [PATCH v6 0/6] Optimize cgroup context switch Ian Rogers
2020-02-14 7:51 ` [PATCH v6 1/6] perf/cgroup: Reorder perf_cgroup_connect() Ian Rogers
2020-02-14 16:11 ` Shuah Khan
2020-02-14 17:37 ` Peter Zijlstra
2020-03-06 14:42 ` [tip: perf/core] " tip-bot2 for Peter Zijlstra
2020-02-14 7:51 ` [PATCH v6 2/6] lib: introduce generic min-heap Ian Rogers
2020-02-14 22:06 ` Randy Dunlap
2020-02-17 16:29 ` Peter Zijlstra
2020-03-06 14:42 ` [tip: perf/core] lib: Introduce " tip-bot2 for Ian Rogers
2020-02-14 7:51 ` [PATCH v6 3/6] perf: Use min_heap in visit_groups_merge Ian Rogers
2020-02-17 17:23 ` Peter Zijlstra
2020-03-06 14:42 ` [tip: perf/core] perf/core: Use min_heap in visit_groups_merge() tip-bot2 for Ian Rogers
2020-02-14 7:51 ` [PATCH v6 4/6] perf: Add per perf_cpu_context min_heap storage Ian Rogers
2020-03-06 14:42 ` [tip: perf/core] perf/core: " tip-bot2 for Ian Rogers
2020-02-14 7:51 ` [PATCH v6 5/6] perf/cgroup: Grow per perf_cpu_context heap storage Ian Rogers
2020-03-06 14:42 ` [tip: perf/core] " tip-bot2 for Ian Rogers
2020-02-14 7:51 ` [PATCH v6 6/6] perf/cgroup: Order events in RB tree by cgroup id Ian Rogers
2020-02-14 19:32 ` [PATCH v6 0/6] Optimize cgroup context switch Ian Rogers
2020-02-17 16:18 ` Peter Zijlstra
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=20191206231539.227585-9-irogers@google.com \
--to=irogers@google.com \
--cc=Gary.Hook@amd.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=andriy.shevchenko@linux.intel.com \
--cc=ardb@kernel.org \
--cc=arnd@arndb.de \
--cc=cai@lca.pw \
--cc=catalin.marinas@arm.com \
--cc=davem@davemloft.net \
--cc=eranian@google.com \
--cc=joe.lawrence@redhat.com \
--cc=jolsa@redhat.com \
--cc=kan.liang@linux.intel.com \
--cc=keescook@chromium.org \
--cc=kent.overstreet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mchehab+samsung@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=penguin-kernel@i-love.sakura.ne.jp \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
--cc=urezki@gmail.com \
--cc=yamada.masahiro@socionext.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;
as well as URLs for NNTP newsgroup(s).