All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Sagi Grimberg <sagi@grimberg.me>, Ming Lei <ming.lei@redhat.com>,
	linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
	Christoph Hellwig <hch@lst.de>, Keith Busch <kbusch@kernel.org>
Cc: Hannes Reinecke <hare@suse.de>,
	Bart Van Assche <bvanassche@acm.org>,
	Johannes Thumshirn <Johannes.Thumshirn@wdc.com>,
	Chao Leng <lengchao@huawei.com>
Subject: Re: [PATCH V5 0/4] blk-mq: implement queue quiesce via percpu_ref for BLK_MQ_F_BLOCKING
Date: Fri, 11 Sep 2020 12:45:49 -0600	[thread overview]
Message-ID: <bbce9d82-2a59-7918-ec27-2b1bea4e015d@kernel.dk> (raw)
In-Reply-To: <09d5cb96-b442-6965-96b3-d884c95a3ca7@grimberg.me>

On 9/11/20 12:34 PM, Sagi Grimberg wrote:
> 
>>> Hi Jens,
>>>
>>> The 1st patch add .mq_quiesce_mutex for serializing quiesce/unquiesce,
>>> and prepares for replacing srcu with percpu_ref.
>>>
>>> The 2nd patch replaces srcu with percpu_ref.
>>>
>>> The 3rd patch adds tagset quiesce interface.
>>>
>>> The 4th patch applies tagset quiesce interface for NVMe subsystem.
>>
>> Tested some reset storms and target restarts during traffic with
>> nvme-tcp.
>>
>> Seems that no apparent breakage.
>>
>> So:
>>
>> Tested-by: Sagi Grimberg <sagi@grimberg.me>
> 
> Probably unrelated to this patches, but I do see new
> kmemleak complaints in the form of:
> --
> unreferenced object 0xffff9440dbf3c240 (size 64):
>    comm "systemd", pid 1, jiffies 4306444056 (age 25034.440s)
>    hex dump (first 32 bytes):
>      00 00 00 00 00 00 00 00 b0 fe 13 99 ff ff ff ff  ................
>      00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>    backtrace:
>      [<00000000f1d0b20e>] percpu_ref_init+0x5f/0xf0
>      [<000000009598103f>] cgroup_mkdir+0xe9/0x440
>      [<0000000001b93c19>] kernfs_iop_mkdir+0x57/0x80
>      [<000000001ed0f985>] vfs_mkdir+0x10e/0x1d0
>      [<00000000cac65f7e>] do_mkdirat+0xec/0x120
>      [<00000000956db630>] do_syscall_64+0x33/0x80
>      [<000000001c2b0e1a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Looks more related to the percpu_ref changes that allocate it
dynamically, causing issues on cases that forget to exit the ref.

-- 
Jens Axboe


WARNING: multiple messages have this Message-ID (diff)
From: Jens Axboe <axboe@kernel.dk>
To: Sagi Grimberg <sagi@grimberg.me>, Ming Lei <ming.lei@redhat.com>,
	linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
	Christoph Hellwig <hch@lst.de>, Keith Busch <kbusch@kernel.org>
Cc: Johannes Thumshirn <Johannes.Thumshirn@wdc.com>,
	Hannes Reinecke <hare@suse.de>, Chao Leng <lengchao@huawei.com>,
	Bart Van Assche <bvanassche@acm.org>
Subject: Re: [PATCH V5 0/4] blk-mq: implement queue quiesce via percpu_ref for BLK_MQ_F_BLOCKING
Date: Fri, 11 Sep 2020 12:45:49 -0600	[thread overview]
Message-ID: <bbce9d82-2a59-7918-ec27-2b1bea4e015d@kernel.dk> (raw)
In-Reply-To: <09d5cb96-b442-6965-96b3-d884c95a3ca7@grimberg.me>

On 9/11/20 12:34 PM, Sagi Grimberg wrote:
> 
>>> Hi Jens,
>>>
>>> The 1st patch add .mq_quiesce_mutex for serializing quiesce/unquiesce,
>>> and prepares for replacing srcu with percpu_ref.
>>>
>>> The 2nd patch replaces srcu with percpu_ref.
>>>
>>> The 3rd patch adds tagset quiesce interface.
>>>
>>> The 4th patch applies tagset quiesce interface for NVMe subsystem.
>>
>> Tested some reset storms and target restarts during traffic with
>> nvme-tcp.
>>
>> Seems that no apparent breakage.
>>
>> So:
>>
>> Tested-by: Sagi Grimberg <sagi@grimberg.me>
> 
> Probably unrelated to this patches, but I do see new
> kmemleak complaints in the form of:
> --
> unreferenced object 0xffff9440dbf3c240 (size 64):
>    comm "systemd", pid 1, jiffies 4306444056 (age 25034.440s)
>    hex dump (first 32 bytes):
>      00 00 00 00 00 00 00 00 b0 fe 13 99 ff ff ff ff  ................
>      00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>    backtrace:
>      [<00000000f1d0b20e>] percpu_ref_init+0x5f/0xf0
>      [<000000009598103f>] cgroup_mkdir+0xe9/0x440
>      [<0000000001b93c19>] kernfs_iop_mkdir+0x57/0x80
>      [<000000001ed0f985>] vfs_mkdir+0x10e/0x1d0
>      [<00000000cac65f7e>] do_mkdirat+0xec/0x120
>      [<00000000956db630>] do_syscall_64+0x33/0x80
>      [<000000001c2b0e1a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Looks more related to the percpu_ref changes that allocate it
dynamically, causing issues on cases that forget to exit the ref.

-- 
Jens Axboe


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  reply	other threads:[~2020-09-11 18:45 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-11  2:41 [PATCH V5 0/4] blk-mq: implement queue quiesce via percpu_ref for BLK_MQ_F_BLOCKING Ming Lei
2020-09-11  2:41 ` Ming Lei
2020-09-11  2:41 ` [PATCH V5 1/4] block: use test_and_{clear|test}_bit to set/clear QUEUE_FLAG_QUIESCED Ming Lei
2020-09-11  2:41   ` Ming Lei
2020-09-11  6:03   ` Hannes Reinecke
2020-09-11  6:03     ` Hannes Reinecke
2020-09-11  2:41 ` [PATCH V5 2/4] blk-mq: implement queue quiesce via percpu_ref for BLK_MQ_F_BLOCKING Ming Lei
2020-09-11  2:41   ` Ming Lei
2020-09-11  2:41 ` [PATCH V5 3/4] blk-mq: add tagset quiesce interface Ming Lei
2020-09-11  2:41   ` Ming Lei
2020-09-11  2:41 ` [PATCH V5 4/4] nvme: use blk_mq_[un]quiesce_tagset Ming Lei
2020-09-11  2:41   ` Ming Lei
2020-09-11 17:29 ` [PATCH V5 0/4] blk-mq: implement queue quiesce via percpu_ref for BLK_MQ_F_BLOCKING Sagi Grimberg
2020-09-11 17:29   ` Sagi Grimberg
2020-09-11 18:34   ` Sagi Grimberg
2020-09-11 18:34     ` Sagi Grimberg
2020-09-11 18:45     ` Jens Axboe [this message]
2020-09-11 18:45       ` Jens Axboe
2020-09-11 23:28     ` Ming Lei
2020-09-11 23:28       ` Ming Lei
2020-09-11 17:33 ` Keith Busch
2020-09-11 17:33   ` Keith Busch
2020-09-11 18:05 ` Jens Axboe
2020-09-11 18:05   ` Jens Axboe
2020-09-11 19:12   ` Sagi Grimberg
2020-09-11 19:12     ` Sagi Grimberg
2020-09-11 19:14     ` Jens Axboe
2020-09-11 19:14       ` Jens Axboe
2020-09-14  3:05       ` Ming Lei
2020-09-14  3:05         ` Ming Lei

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=bbce9d82-2a59-7918-ec27-2b1bea4e015d@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=Johannes.Thumshirn@wdc.com \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=lengchao@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=ming.lei@redhat.com \
    --cc=sagi@grimberg.me \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.