BPF Archive on lore.kernel.org
 help / color / Atom feed
From: Song Liu <songliubraving@fb.com>
To: <bpf@vger.kernel.org>, <netdev@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Cc: <ast@kernel.org>, <daniel@iogearbox.net>, <kernel-team@fb.com>,
	<peterz@infradead.org>, Song Liu <songliubraving@fb.com>,
	Andrii Nakryiko <andrii@kernel.org>
Subject: [PATCH v4 bpf-next 6/6] bpf: runqslower: use task local storage
Date: Mon, 22 Feb 2021 17:20:14 -0800
Message-ID: <20210223012014.2087583-7-songliubraving@fb.com> (raw)
In-Reply-To: <20210223012014.2087583-1-songliubraving@fb.com>

Replace hashtab with task local storage in runqslower. This improves the
performance of these BPF programs. The following table summarizes average
runtime of these programs, in nanoseconds:

                          task-local   hash-prealloc   hash-no-prealloc
handle__sched_wakeup             125             340               3124
handle__sched_wakeup_new        2812            1510               2998
handle__sched_switch             151             208                991

Note that, task local storage gives better performance than hashtab for
handle__sched_wakeup and handle__sched_switch. On the other hand, for
handle__sched_wakeup_new, task local storage is slower than hashtab with
prealloc. This is because handle__sched_wakeup_new accesses the data for
the first time, so it has to allocate the data for task local storage.
Once the initial allocation is done, subsequent accesses, as those in
handle__sched_wakeup, are much faster with task local storage. If we
disable hashtab prealloc, task local storage is much faster for all 3
functions.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 tools/bpf/runqslower/runqslower.bpf.c | 33 +++++++++++++++++----------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
index 1f18a409f0443..645530ca7e985 100644
--- a/tools/bpf/runqslower/runqslower.bpf.c
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -11,9 +11,9 @@ const volatile __u64 min_us = 0;
 const volatile pid_t targ_pid = 0;
 
 struct {
-	__uint(type, BPF_MAP_TYPE_HASH);
-	__uint(max_entries, 10240);
-	__type(key, u32);
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
 	__type(value, u64);
 } start SEC(".maps");
 
@@ -25,15 +25,20 @@ struct {
 
 /* record enqueue timestamp */
 __always_inline
-static int trace_enqueue(u32 tgid, u32 pid)
+static int trace_enqueue(struct task_struct *t)
 {
-	u64 ts;
+	u32 pid = t->pid;
+	u64 *ptr;
 
 	if (!pid || (targ_pid && targ_pid != pid))
 		return 0;
 
-	ts = bpf_ktime_get_ns();
-	bpf_map_update_elem(&start, &pid, &ts, 0);
+	ptr = bpf_task_storage_get(&start, t, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!ptr)
+		return 0;
+
+	*ptr = bpf_ktime_get_ns();
 	return 0;
 }
 
@@ -43,7 +48,7 @@ int handle__sched_wakeup(u64 *ctx)
 	/* TP_PROTO(struct task_struct *p) */
 	struct task_struct *p = (void *)ctx[0];
 
-	return trace_enqueue(p->tgid, p->pid);
+	return trace_enqueue(p);
 }
 
 SEC("tp_btf/sched_wakeup_new")
@@ -52,7 +57,7 @@ int handle__sched_wakeup_new(u64 *ctx)
 	/* TP_PROTO(struct task_struct *p) */
 	struct task_struct *p = (void *)ctx[0];
 
-	return trace_enqueue(p->tgid, p->pid);
+	return trace_enqueue(p);
 }
 
 SEC("tp_btf/sched_switch")
@@ -70,12 +75,16 @@ int handle__sched_switch(u64 *ctx)
 
 	/* ivcsw: treat like an enqueue event and store timestamp */
 	if (prev->state == TASK_RUNNING)
-		trace_enqueue(prev->tgid, prev->pid);
+		trace_enqueue(prev);
 
 	pid = next->pid;
 
+	/* For pid mismatch, save a bpf_task_storage_get */
+	if (!pid || (targ_pid && targ_pid != pid))
+		return 0;
+
 	/* fetch timestamp and calculate delta */
-	tsp = bpf_map_lookup_elem(&start, &pid);
+	tsp = bpf_task_storage_get(&start, next, 0, 0);
 	if (!tsp)
 		return 0;   /* missed enqueue */
 
@@ -91,7 +100,7 @@ int handle__sched_switch(u64 *ctx)
 	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
 			      &event, sizeof(event));
 
-	bpf_map_delete_elem(&start, &pid);
+	bpf_task_storage_delete(&start, next);
 	return 0;
 }
 
-- 
2.24.1


  parent reply index

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-23  1:20 [PATCH v4 bpf-next 0/6] bpf: enable task local storage for tracing programs Song Liu
2021-02-23  1:20 ` [PATCH v4 bpf-next 1/6] " Song Liu
2021-02-23  3:08   ` kernel test robot
2021-02-23  4:04   ` kernel test robot
2021-02-23 19:23   ` Martin KaFai Lau
2021-02-23 20:51     ` Song Liu
2021-02-23  1:20 ` [PATCH v4 bpf-next 2/6] bpf: prevent deadlock from recursive bpf_task_storage_[get|delete] Song Liu
2021-02-23  6:21   ` Andrii Nakryiko
2021-02-23  7:16     ` Song Liu
2021-02-23  7:19       ` Andrii Nakryiko
2021-02-23 16:44         ` Alexei Starovoitov
2021-02-23 11:06   ` Peter Zijlstra
2021-02-23 20:49     ` Song Liu
2021-02-23  1:20 ` [PATCH v4 bpf-next 3/6] selftests/bpf: add non-BPF_LSM test for task local storage Song Liu
2021-02-23  1:20 ` [PATCH v4 bpf-next 4/6] selftests/bpf: test deadlock from recursive bpf_task_storage_[get|delete] Song Liu
2021-02-23  1:20 ` [PATCH v4 bpf-next 5/6] bpf: runqslower: prefer using local vmlimux to generate vmlinux.h Song Liu
2021-02-23  6:26   ` Andrii Nakryiko
2021-02-23 21:24   ` Martin KaFai Lau
2021-02-23  1:20 ` Song Liu [this message]
2021-02-23 21:33   ` [PATCH v4 bpf-next 6/6] bpf: runqslower: use task local storage Martin KaFai Lau

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=20210223012014.2087583-7-songliubraving@fb.com \
    --to=songliubraving@fb.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    /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

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git