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:   ebiederm@xmission.com (Eric W. Biederman)
To:     Masahiro Yamada <masahiroy@kernel.org>
Cc:     Junxiao Bi <junxiao.bi@oracle.com>,
        Matthew Wilcox <willy@infradead.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Linux FS-devel Mailing List <linux-fsdevel@vger.kernel.org>,
        Matthew Wilcox <matthew.wilcox@oracle.com>,
        Srinivas Eeda <SRINIVAS.EEDA@oracle.com>,
        "joe.jin\@oracle.com" <joe.jin@oracle.com>
References: <54091fc0-ca46-2186-97a8-d1f3c4f3877b@oracle.com>
        <20200618233958.GV8681@bombadil.infradead.org>
        <877dw3apn8.fsf@x220.int.ebiederm.org>
        <2cf6af59-e86b-f6cc-06d3-84309425bd1d@oracle.com>
        <87bllf87ve.fsf_-_@x220.int.ebiederm.org>
        <CAK7LNARr4aWTUqcS5TGdQ-7C_u=PFQVMMuakQ2Oro3-43fYu9w@mail.gmail.com>
Date:   Mon, 22 Jun 2020 10:13:09 -0500
In-Reply-To: <CAK7LNARr4aWTUqcS5TGdQ-7C_u=PFQVMMuakQ2Oro3-43fYu9w@mail.gmail.com>
        (Masahiro Yamada's message of "Mon, 22 Jun 2020 14:33:39 +0900")
Message-ID: <87366n3zi2.fsf@x220.int.ebiederm.org>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/26.1 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Subject: Re: [PATCH] proc: Avoid a thundering herd of threads freeing proc dentries
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Masahiro Yamada <masahiroy@kernel.org> writes:

> On Fri, Jun 19, 2020 at 11:14 PM Eric W. Biederman
> <ebiederm@xmission.com> wrote:
>>
>>
>> Junxiao Bi <junxiao.bi@oracle.com> reported:
>> > When debugging some performance issue, i found that thousands of threads exit
>> > around same time could cause a severe spin lock contention on proc dentry
>> > "/proc/$parent_process_pid/task/", that's because threads needs to clean up
>> > their pid file from that dir when exit.
>>
>> Matthew Wilcox <willy@infradead.org> reported:
>> > We've looked at a few different ways of fixing this problem.
>>
>> The flushing of the proc dentries from the dcache is an optmization,
>> and is not necessary for correctness.  Eventually cache pressure will
>> cause the dentries to be freed even if no flushing happens.  Some
>> light testing when I refactored the proc flushg[1] indicated that at
>> least the memory footprint is easily measurable.
>>
>> An optimization that causes a performance problem due to a thundering
>> herd of threads is no real optimization.
>>
>> Modify the code to only flush the /proc/<tgid>/ directory when all
>> threads in a process are killed at once.  This continues to flush
>> practically everything when the process is reaped as the threads live
>> under /proc/<tgid>/task/<tid>.
>>
>> There is a rare possibility that a debugger will access /proc/<tid>/,
>> which this change will no longer flush, but I believe such accesses
>> are sufficiently rare to not be observed in practice.
>>
>> [1] 7bc3e6e55acf ("proc: Use a list of inodes to flush from proc")
>> Link: https://lkml.kernel.org/r/54091fc0-ca46-2186-97a8-d1f3c4f3877b@oracle.com
>
>
>> Reported-by: Masahiro Yamada <masahiroy@kernel.org>
>
> I did not report this.

Thank you for catching this.

I must have cut&pasted the wrong email address by mistake.

My apologies.

Eric