From: Jason Baron <jbaron@akamai.com>
To: Andy Lutomirski <luto@amacapital.net>,
peterz@infradead.org, mingo@redhat.com, viro@zeniv.linux.org.uk
Cc: akpm@linux-foundation.org, normalperson@yhbt.net,
davidel@xmailserver.org, mtk.manpages@gmail.com,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 2/2] epoll: introduce EPOLLEXCLUSIVE and EPOLLROUNDROBIN
Date: Mon, 09 Feb 2015 16:32:48 -0500 [thread overview]
Message-ID: <54D92780.4000303@akamai.com> (raw)
In-Reply-To: <54D915FC.7010003@amacapital.net>
On 02/09/2015 03:18 PM, Andy Lutomirski wrote:
> On 02/09/2015 12:06 PM, Jason Baron wrote:
>> Epoll file descriptors that are added to a shared wakeup source are always
>> added in a non-exclusive manner. That means that when we have multiple epoll
>> fds attached to a shared wakeup source they are all woken up. This can
>> lead to excessive cpu usage and uneven load distribution.
>>
>> This patch introduces two new 'events' flags that are intended to be used
>> with EPOLL_CTL_ADD operations. EPOLLEXCLUSIVE, adds the epoll fd to the event
>> source in an exclusive manner such that the minimum number of threads are
>> woken. EPOLLROUNDROBIN, which depends on EPOLLEXCLUSIVE also being set, can
>> also be added to the 'events' flag, such that we round robin around the set
>> of waiting threads.
>>
>> An implementation note is that in the epoll wakeup routine,
>> 'ep_poll_callback()', if EPOLLROUNDROBIN is set, we return 1, for a successful
>> wakeup, only when there are current waiters. The idea is to use this additional
>> heuristic in order minimize wakeup latencies.
>
> I don't understand what this is intended to do.
>
> If an event has EPOLLONESHOT, then this only one thread should be woken regardless, right? If not, isn't that just a bug that should be fixed?
>
hmm...so with EPOLLONESHOT you basically get notified once about an event. If i have multiple epoll fds (say 1 per-thread) attached to a single source in EPOLLONESHOT, then all threads will potentially get woken up once per event. Then, I would have to re-arm all of them. So I don't think this addresses this particular usecase...what I am trying to avoid is this mass wakeup or thundering herd for a shared event source.
> If an event has EPOLLET, then the considerations are similar to EPOLLONESHOT, right?
>
EPOLLET is still going to cause this thundering herd.
> If an event is a normal level-triggered non-one-shot event, then I don't understand how a round-robin wakeup makes any sense. It's level-triggered, after all.
Yeah, so the current behavior is to wake up all of the threads. I'm trying to add a new mode where it load balances among the threads interested in the event. Perhaps, the test program I attached to 0/2 will show the issue better?
Also, this originally came up in the context of a single listening socket which was attached to multiple epoll fds each in a separate thread. With the attached patch, I can measure a large decrease in cpu usage and better balancing behavior among the accepting threads.
Thanks,
-Jason
next prev parent reply other threads:[~2015-02-09 21:32 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-09 20:05 [PATCH 0/2] Add epoll round robin wakeup mode Jason Baron
2015-02-09 20:05 ` [PATCH 1/2] sched/wait: add " Jason Baron
2015-02-09 20:26 ` Michael Kerrisk
2015-02-09 21:50 ` Peter Zijlstra
2015-02-10 4:06 ` Jason Baron
2015-02-10 9:03 ` Peter Zijlstra
2015-02-10 15:59 ` Jason Baron
2015-02-10 16:11 ` Peter Zijlstra
2015-02-09 20:06 ` [PATCH 2/2] epoll: introduce EPOLLEXCLUSIVE and EPOLLROUNDROBIN Jason Baron
2015-02-09 20:18 ` Andy Lutomirski
2015-02-09 21:32 ` Jason Baron [this message]
2015-02-09 22:45 ` Andy Lutomirski
2015-02-10 3:59 ` Jason Baron
2015-02-10 4:49 ` Eric Wong
2015-02-10 19:16 ` Jason Baron
2015-02-10 19:32 ` Eric Wong
2015-02-09 20:27 ` Michael Kerrisk
2015-02-09 20:25 ` [PATCH 0/2] Add epoll round robin wakeup mode Michael Kerrisk
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=54D92780.4000303@akamai.com \
--to=jbaron@akamai.com \
--cc=akpm@linux-foundation.org \
--cc=davidel@xmailserver.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@redhat.com \
--cc=mtk.manpages@gmail.com \
--cc=normalperson@yhbt.net \
--cc=peterz@infradead.org \
--cc=viro@zeniv.linux.org.uk \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).