From: Hongchen Zhang <zhanghongchen@loongson.cn>
To: Andrew Morton <akpm@linux-foundation.org>,
Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>,
maobibo <maobibo@loongson.cn>,
David Howells <dhowells@redhat.com>,
Sedat Dilek <sedat.dilek@gmail.com>,
"Christian Brauner (Microsoft)" <brauner@kernel.org>,
Luis Chamberlain <mcgrof@kernel.org>,
Mauro Carvalho Chehab <mchehab@kernel.org>,
Eric Dumazet <edumazet@google.com>,
"Fabio M. De Francesco" <fmdefrancesco@gmail.com>,
Christophe JAILLET <christophe.jaillet@wanadoo.fr>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3] pipe: use __pipe_{lock,unlock} instead of spinlock
Date: Sun, 29 Jan 2023 10:29:17 +0800 [thread overview]
Message-ID: <90dd93c0-d0ed-50c1-9a86-dad5bb3754af@loongson.cn> (raw)
In-Reply-To: <20230116141608.a72015bdd8bbbedd5c50cc3e@linux-foundation.org>
Hi Andrew,
Sorry to reply to you so late, because I took a long holiday.
On 2023/1/17 am 6:16, Andrew Morton wrote:
> On Mon, 16 Jan 2023 21:10:37 +0000 Al Viro <viro@zeniv.linux.org.uk> wrote:
>
>> On Mon, Jan 16, 2023 at 04:38:01AM +0000, Matthew Wilcox wrote:
>>> On Mon, Jan 16, 2023 at 11:16:13AM +0800, maobibo wrote:
>>>> Hongchen,
>>>>
>>>> I have a glance with this patch, it simply replaces with
>>>> spinlock_irqsave with mutex lock. There may be performance
>>>> improvement with two processes competing with pipe, however
>>>> for N processes, there will be complex context switches
>>>> and ipi interruptts.
>>>>
>>>> Can you find some cases with more than 2 processes competing
>>>> pipe, rather than only unixbench?
>>>
>>> What real applications have pipes with more than 1 writer & 1 reader?
>>> I'm OK with slowing down the weird cases if the common cases go faster.
>>
>> >From commit 0ddad21d3e99c743a3aa473121dc5561679e26bb:
>> While this isn't a common occurrence in the traditional "use a pipe as a
>> data transport" case, where you typically only have a single reader and
>> a single writer process, there is one common special case: using a pipe
>> as a source of "locking tokens" rather than for data communication.
>>
>> In particular, the GNU make jobserver code ends up using a pipe as a way
>> to limit parallelism, where each job consumes a token by reading a byte
>> from the jobserver pipe, and releases the token by writing a byte back
>> to the pipe.
>
> The author has tested this patch with Linus's test code from 0ddad21d3e
> and the results were OK
> (https://lkml.kernel.org/r/c3cbede6-f19e-3333-ba0f-d3f005e5d599@loongson.cn).
>
> I've been stalling on this patch until Linus gets back to his desk,
> which now appears to have happened.
>
> Hongchen, when convenient, please capture this discussion (as well as
> the testing results with Linus's sample code) in the changelog and send
> us a v4, with Linus on cc?
>
I will send you a v4 and cc to Linus.
Thanks.
Hongchen Zhang
next prev parent reply other threads:[~2023-01-29 2:29 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-07 1:23 [PATCH v3] pipe: use __pipe_{lock,unlock} instead of spinlock Hongchen Zhang
2023-01-13 3:19 ` Hongchen Zhang
2023-01-13 9:32 ` Sedat Dilek
2023-01-16 1:52 ` Sedat Dilek
2023-01-16 2:16 ` Hongchen Zhang
2023-01-16 2:42 ` Sedat Dilek
2023-01-16 3:16 ` maobibo
2023-01-16 4:38 ` Matthew Wilcox
2023-01-16 21:10 ` Al Viro
2023-01-16 22:16 ` Andrew Morton
2023-01-17 6:54 ` Sedat Dilek
2023-01-29 2:29 ` Hongchen Zhang [this message]
-- strict thread matches above, loose matches on Subject: below --
2023-01-06 9:48 Hongchen Zhang
2023-01-06 19:13 ` Luis Chamberlain
2023-01-06 20:33 ` Sedat Dilek
2023-01-07 3:31 ` Hongchen Zhang
2023-01-07 0:58 ` Hongchen Zhang
2023-01-06 9:28 Hongchen Zhang
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=90dd93c0-d0ed-50c1-9a86-dad5bb3754af@loongson.cn \
--to=zhanghongchen@loongson.cn \
--cc=akpm@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=christophe.jaillet@wanadoo.fr \
--cc=dhowells@redhat.com \
--cc=edumazet@google.com \
--cc=fmdefrancesco@gmail.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maobibo@loongson.cn \
--cc=mcgrof@kernel.org \
--cc=mchehab@kernel.org \
--cc=sedat.dilek@gmail.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@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
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).