Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Song Liu <songliubraving@fb.com>
To:     Yonghong Song <yhs@fb.com>
CC:     bpf <bpf@vger.kernel.org>, Networking <netdev@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "mingo@redhat.com" <mingo@redhat.com>,
        "peterz@infradead.org" <peterz@infradead.org>,
        "ast@kernel.org" <ast@kernel.org>,
        "daniel@iogearbox.net" <daniel@iogearbox.net>,
        "andrii@kernel.org" <andrii@kernel.org>,
        "john.fastabend@gmail.com" <john.fastabend@gmail.com>,
        "kpsingh@chromium.org" <kpsingh@chromium.org>,
        Kernel Team <Kernel-team@fb.com>,
        "haoluo@google.com" <haoluo@google.com>
Subject: Re: [PATCH bpf-next 4/4] bpf: runqslower: use task local storage
Thread-Topic: [PATCH bpf-next 4/4] bpf: runqslower: use task local storage
Thread-Index: AQHW5hZGTzByk5itW0+Ehl6CErtdN6oiuAcAgABVVAA=
Date:   Mon, 11 Jan 2021 22:54:50 +0000
Message-ID: <352FED72-11B3-44F0-9B1C-92552AEB4AE8@fb.com>
References: <20210108231950.3844417-1-songliubraving@fb.com>
 <20210108231950.3844417-5-songliubraving@fb.com>
 <ad40d69d-9c0f-8205-26df-c5a755778f9e@fb.com>
In-Reply-To: <ad40d69d-9c0f-8205-26df-c5a755778f9e@fb.com>
Accept-Language: en-US
Content-Language: en-US
Content-Type: text/plain; charset="us-ascii"
Content-ID: <6E8F0EF4B8011048BAC4757AA7352B30@namprd15.prod.outlook.com>
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 8c0ff542-4795-41f4-710e-08d8b683e741
X-MS-Exchange-CrossTenant-originalarrivaltime: 11 Jan 2021 22:54:50.8322
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: WtUO086K0Egy/N1U9erZzy+khvCYHwl2oH5354G+oZ06cKL9ty/g6hzo3K7Yd8hioKBybHyJPrvHwAJbPmvTYQ==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BYAPR15MB3254
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.343,18.0.737
 definitions=2021-01-11_34:2021-01-11,2021-01-11 signatures=0
X-Proofpoint-Spam-Details: rule=fb_default_notspam policy=fb_default score=0 mlxscore=0 bulkscore=0
 phishscore=0 priorityscore=1501 impostorscore=0 adultscore=0
 malwarescore=0 clxscore=1015 suspectscore=0 mlxlogscore=999 spamscore=0
 lowpriorityscore=0 classifier=spam adjust=0 reason=mlx scancount=1
 engine=8.12.0-2009150000 definitions=main-2101110129
X-FB-Internal: deliver
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


> On Jan 11, 2021, at 9:49 AM, Yonghong Song <yhs@fb.com> wrote:
>=20
>=20
>=20
> On 1/8/21 3:19 PM, Song Liu wrote:
>> Replace hashtab with task local storage in runqslower. This improves the
>> performance of these BPF programs. The following table summarizes averag=
e
>> 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.
>> Signed-off-by: Song Liu <songliubraving@fb.com>
>> ---
>>  tools/bpf/runqslower/runqslower.bpf.c | 26 +++++++++++++++-----------
>>  1 file changed, 15 insertions(+), 11 deletions(-)
>> diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslowe=
r/runqslower.bpf.c
>> index 1f18a409f0443..c4de4179a0a17 100644
>> --- a/tools/bpf/runqslower/runqslower.bpf.c
>> +++ b/tools/bpf/runqslower/runqslower.bpf.c
>> @@ -11,9 +11,9 @@ const volatile __u64 min_us =3D 0;
>>  const volatile pid_t targ_pid =3D 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 +25,19 @@ 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 =3D t->pid;
>> +	u64 ts, *ptr;
>>    	if (!pid || (targ_pid && targ_pid !=3D pid))
>>  		return 0;
>>    	ts =3D bpf_ktime_get_ns();
>> -	bpf_map_update_elem(&start, &pid, &ts, 0);
>> +	ptr =3D bpf_task_storage_get(&start, t, 0,
>> +				   BPF_LOCAL_STORAGE_GET_F_CREATE);
>> +	if (ptr)
>> +		*ptr =3D ts;
>>  	return 0;
>>  }
>>  @@ -43,7 +47,7 @@ int handle__sched_wakeup(u64 *ctx)
>>  	/* TP_PROTO(struct task_struct *p) */
>>  	struct task_struct *p =3D (void *)ctx[0];
>>  -	return trace_enqueue(p->tgid, p->pid);
>> +	return trace_enqueue(p);
>>  }
>>    SEC("tp_btf/sched_wakeup_new")
>> @@ -52,7 +56,7 @@ int handle__sched_wakeup_new(u64 *ctx)
>>  	/* TP_PROTO(struct task_struct *p) */
>>  	struct task_struct *p =3D (void *)ctx[0];
>>  -	return trace_enqueue(p->tgid, p->pid);
>> +	return trace_enqueue(p);
>>  }
>>    SEC("tp_btf/sched_switch")
>> @@ -70,12 +74,12 @@ int handle__sched_switch(u64 *ctx)
>>    	/* ivcsw: treat like an enqueue event and store timestamp */
>>  	if (prev->state =3D=3D TASK_RUNNING)
>> -		trace_enqueue(prev->tgid, prev->pid);
>> +		trace_enqueue(prev);
>>    	pid =3D next->pid;
>>    	/* fetch timestamp and calculate delta */
>> -	tsp =3D bpf_map_lookup_elem(&start, &pid);
>> +	tsp =3D bpf_task_storage_get(&start, next, 0, 0);
>>  	if (!tsp)
>>  		return 0;   /* missed enqueue */
>=20
> Previously, hash table may overflow so we may have missed enqueue.
> Here with task local storage, is it possible to add additional pid
> filtering in the beginning of handle__sched_switch such that
> missed enqueue here can be treated as an error?

IIUC, hashtab overflow is not the only reason of missed enqueue. If the
wakeup (which calls trace_enqueue) happens before runqslower starts, we
may still get missed enqueue in sched_switch, no?

Thanks,
Song=