public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: Hao Xu <[email protected]>, [email protected]
Cc: Jens Axboe <[email protected]>
Subject: Re: [PATCH v2 0/3] cancel_hash per entry lock
Date: Mon, 6 Jun 2022 13:09:22 +0100	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On 6/6/22 13:02, Pavel Begunkov wrote:
> On 6/6/22 08:06, Hao Xu wrote:
>> On 6/6/22 14:57, Hao Xu wrote:
>>> From: Hao Xu <[email protected]>
>>>
>>> Make per entry lock for cancel_hash array, this reduces usage of
>>> completion_lock and contension between cancel_hash entries.
>>>
>>> v1->v2:
>>>   - Add per entry lock for poll/apoll task work code which was missed
>>>     in v1
>>>   - add an member in io_kiocb to track req's indice in cancel_hash
>>
>> Tried to test it with many poll_add IOSQQE_ASYNC requests but turned out
>> that there is little conpletion_lock contention, so no visible change in
>> data. But I still think this may be good for cancel_hash access in some
>> real cases where completion lock matters.
> 
> Conceptually I don't mind it, but let me ask in what
> circumstances you expect it to make a difference? And
> what can we do to get favourable numbers? For instance,
> how many CPUs io-wq was using?

Btw, I couldn't find ____cacheline_aligned_in_smp anywhere,
which I expect around those new spinlocks to avoid them sharing
cache lines
  
-- 
Pavel Begunkov

  reply	other threads:[~2022-06-06 12:09 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-06  6:57 [PATCH v2 0/3] cancel_hash per entry lock Hao Xu
2022-06-06  6:57 ` [PATCH 1/3] io_uring: add hash_index and its logic to track req in cancel_hash Hao Xu
2022-06-06 11:59   ` Pavel Begunkov
2022-06-06 13:47     ` Hao Xu
2022-06-06  6:57 ` [PATCH 2/3] io_uring: add an io_hash_bucket structure for smaller granularity lock Hao Xu
2022-06-06 11:55   ` Pavel Begunkov
2022-06-06  6:57 ` [PATCH 3/3] io_uring: switch cancel_hash to use per list spinlock Hao Xu
2022-06-06  7:06 ` [PATCH v2 0/3] cancel_hash per entry lock Hao Xu
2022-06-06 12:02   ` Pavel Begunkov
2022-06-06 12:09     ` Pavel Begunkov [this message]
2022-06-06 13:39     ` Hao Xu

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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