From: Chris Mason <clm@fb.com>
To: Josef Bacik <josef@toxicpanda.com>
Cc: Nikolay Borisov <nborisov@suse.com>,
"linux-btrfs@vger.kernel.org" <linux-btrfs@vger.kernel.org>,
Kernel Team <Kernel-team@fb.com>
Subject: Re: [PATCH 2/3] btrfs: wakeup cleaner thread when adding delayed iput
Date: Tue, 27 Nov 2018 19:59:42 +0000 [thread overview]
Message-ID: <13D3592A-3719-4F9E-8E8A-944FE88F30D4@fb.com> (raw)
In-Reply-To: <20181127195450.fjor2gewhp3hri56@macbook-pro-91.dhcp.thefacebook.com>
On 27 Nov 2018, at 14:54, Josef Bacik wrote:
> On Tue, Nov 27, 2018 at 10:26:15AM +0200, Nikolay Borisov wrote:
>>
>>
>> On 21.11.18 г. 21:09 ч., Josef Bacik wrote:
>>> The cleaner thread usually takes care of delayed iputs, with the
>>> exception of the btrfs_end_transaction_throttle path. The cleaner
>>> thread only gets woken up every 30 seconds, so instead wake it up to
>>> do
>>> it's work so that we can free up that space as quickly as possible.
>>
>> Have you done any measurements how this affects the overall system. I
>> suspect this introduces a lot of noise since now we are going to be
>> doing a thread wakeup on every iput, does this give a chance to have
>> nice, large batches of iputs that the cost of wake up can be
>> amortized
>> across?
>
> I ran the whole patchset with our A/B testing stuff and the patchset
> was a 5%
> win overall, so I'm inclined to think it's fine. Thanks,
It's a good point though, a delayed wakeup may be less overhead.
-chris
next prev parent reply other threads:[~2018-11-27 20:00 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-21 19:09 [PATCH 0/3] Delayed iput fixes Josef Bacik
2018-11-21 19:09 ` [PATCH 1/3] btrfs: run delayed iputs before committing Josef Bacik
2018-11-26 14:44 ` Nikolay Borisov
2018-11-21 19:09 ` [PATCH 2/3] btrfs: wakeup cleaner thread when adding delayed iput Josef Bacik
2018-11-27 8:26 ` Nikolay Borisov
2018-11-27 19:54 ` Josef Bacik
2018-11-27 19:59 ` Chris Mason [this message]
2018-11-27 20:08 ` Josef Bacik
2018-11-28 19:06 ` David Sterba
2018-11-28 19:32 ` Chris Mason
2018-11-28 20:08 ` Filipe Manana
2018-11-29 0:30 ` Qu Wenruo
2018-11-21 19:09 ` [PATCH 3/3] btrfs: replace cleaner_delayed_iput_mutex with a waitqueue Josef Bacik
2018-11-27 8:29 ` Nikolay Borisov
2018-11-27 20:01 ` Josef Bacik
2018-12-03 16:06 [PATCH 0/3][V2] Delayed iput fixes Josef Bacik
2018-12-03 16:06 ` [PATCH 2/3] btrfs: wakeup cleaner thread when adding delayed iput Josef Bacik
2018-12-04 9:21 ` Nikolay Borisov
2018-12-04 18:18 ` Josef Bacik
2019-01-11 15:21 [PATCH 0/3][V3] Delayed iput fixes Josef Bacik
2019-01-11 15:21 ` [PATCH 2/3] btrfs: wakeup cleaner thread when adding delayed iput Josef Bacik
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=13D3592A-3719-4F9E-8E8A-944FE88F30D4@fb.com \
--to=clm@fb.com \
--cc=Kernel-team@fb.com \
--cc=josef@toxicpanda.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=nborisov@suse.com \
/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).