From: Andy Lutomirski <luto@amacapital.net>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Fam Zheng <famz@redhat.com>,
"Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
X86 ML <x86@kernel.org>, Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
David Herrmann <dh.herrmann@gmail.com>,
Alexei Starovoitov <ast@plumgrid.com>,
Miklos Szeredi <mszeredi@suse.cz>,
David Drysdale <drysdale@google.com>,
Oleg Nesterov <oleg@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Vivek Goyal <vgoyal@redhat.com>,
Mike Frysinger <vapier@gentoo.org>,
"Theodore Ts'o" <tytso@mit.edu>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Rasmus Villemoes <linux@rasmusvillemoes.dk>,
Rashika Kheria <rashika.kheria@gmail.com>,
Hugh Dickins <hughd@google.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Peter Zijlstra <peterz@infradead.org>,
Linux FS Devel <linux-fsdevel@vger.kernel.org>,
Linux API <linux-api@vger.kernel.org>,
Josh Triplett <josh@joshtriplett.org>
Subject: Re: [PATCH RFC 5/6] epoll: Add implementation for epoll_mod_wait
Date: Thu, 22 Jan 2015 13:12:59 -0800 [thread overview]
Message-ID: <CALCETrWwuJpFK+38mBxxTQCu7Oig22Nr+mAuO++Y+0CdAhfzkw@mail.gmail.com> (raw)
In-Reply-To: <54BF9294.3070902@redhat.com>
On Wed, Jan 21, 2015 at 3:50 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
>
> On 21/01/2015 12:14, Fam Zheng wrote:
>> > My take for simplicity will be leaving epoll_ctl as-is, and my take for
>> > performance will be epoll_pwait1. And I don't really like putting my time on
>> > epoll_ctl_batch, thinking it as a ambivalent compromise in between.
>>
>> > I agree with Michael actually. The big change is going from O(n)
>> > epoll_ctl calls to O(1), and epoll_ctl_batch achieves that just fine.
>> > Changing 2 syscalls to 1 is the icing on the cake, but we're talking of
>> > a fraction of a microsecond.
>>
>> Maybe I'm missing something, but in common cases, the set of fds for epoll_wait
>> doesn't change that radically from one iteration to another, does it?
>
> That depends on the application.
In my application, the set of fds almost never changes, but the set of
events I want changes all the time. The main thing that changes is
whether I care about EPOLLOUT. If I'm ready to send something, then I
want EPOLLOUT. If I'm not ready, then I don't want EPOLLOUT.
--Andy
WARNING: multiple messages have this Message-ID (diff)
From: Andy Lutomirski <luto@amacapital.net>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Fam Zheng <famz@redhat.com>,
"Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
X86 ML <x86@kernel.org>, Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
David Herrmann <dh.herrmann@gmail.com>,
Alexei Starovoitov <ast@plumgrid.com>,
Miklos Szeredi <mszeredi@suse.cz>,
David Drysdale <drysdale@google.com>,
Oleg Nesterov <oleg@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Vivek Goyal <vgoyal@redhat.com>,
Mike Frysinger <vapier@gentoo.org>,
"Theodore Ts'o" <tytso@mit.edu>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Rasmus Villemoes <linux@rasmusvillemoes.dk>,
Rashika Kheria <rashika.kheria@gmail.com>,
Hugh Dickins <hugh
Subject: Re: [PATCH RFC 5/6] epoll: Add implementation for epoll_mod_wait
Date: Thu, 22 Jan 2015 13:12:59 -0800 [thread overview]
Message-ID: <CALCETrWwuJpFK+38mBxxTQCu7Oig22Nr+mAuO++Y+0CdAhfzkw@mail.gmail.com> (raw)
In-Reply-To: <54BF9294.3070902@redhat.com>
On Wed, Jan 21, 2015 at 3:50 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
>
> On 21/01/2015 12:14, Fam Zheng wrote:
>> > My take for simplicity will be leaving epoll_ctl as-is, and my take for
>> > performance will be epoll_pwait1. And I don't really like putting my time on
>> > epoll_ctl_batch, thinking it as a ambivalent compromise in between.
>>
>> > I agree with Michael actually. The big change is going from O(n)
>> > epoll_ctl calls to O(1), and epoll_ctl_batch achieves that just fine.
>> > Changing 2 syscalls to 1 is the icing on the cake, but we're talking of
>> > a fraction of a microsecond.
>>
>> Maybe I'm missing something, but in common cases, the set of fds for epoll_wait
>> doesn't change that radically from one iteration to another, does it?
>
> That depends on the application.
In my application, the set of fds almost never changes, but the set of
events I want changes all the time. The main thing that changes is
whether I care about EPOLLOUT. If I'm ready to send something, then I
want EPOLLOUT. If I'm not ready, then I don't want EPOLLOUT.
--Andy
WARNING: multiple messages have this Message-ID (diff)
From: Andy Lutomirski <luto@amacapital.net>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Fam Zheng <famz@redhat.com>,
"Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
X86 ML <x86@kernel.org>, Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
David Herrmann <dh.herrmann@gmail.com>,
Alexei Starovoitov <ast@plumgrid.com>,
Miklos Szeredi <mszeredi@suse.cz>,
David Drysdale <drysdale@google.com>,
Oleg Nesterov <oleg@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Vivek Goyal <vgoyal@redhat.com>,
Mike Frysinger <vapier@gentoo.org>, Theodore Ts'o <tytso@mit.edu>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Rasmus Villemoes <linux@rasmusvillemoes.dk>,
Rashika Kheria <rashika.kheria@gmail.com>, Hugh Dickins <hugh>
Subject: Re: [PATCH RFC 5/6] epoll: Add implementation for epoll_mod_wait
Date: Thu, 22 Jan 2015 13:12:59 -0800 [thread overview]
Message-ID: <CALCETrWwuJpFK+38mBxxTQCu7Oig22Nr+mAuO++Y+0CdAhfzkw@mail.gmail.com> (raw)
In-Reply-To: <54BF9294.3070902@redhat.com>
On Wed, Jan 21, 2015 at 3:50 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
>
> On 21/01/2015 12:14, Fam Zheng wrote:
>> > My take for simplicity will be leaving epoll_ctl as-is, and my take for
>> > performance will be epoll_pwait1. And I don't really like putting my time on
>> > epoll_ctl_batch, thinking it as a ambivalent compromise in between.
>>
>> > I agree with Michael actually. The big change is going from O(n)
>> > epoll_ctl calls to O(1), and epoll_ctl_batch achieves that just fine.
>> > Changing 2 syscalls to 1 is the icing on the cake, but we're talking of
>> > a fraction of a microsecond.
>>
>> Maybe I'm missing something, but in common cases, the set of fds for epoll_wait
>> doesn't change that radically from one iteration to another, does it?
>
> That depends on the application.
In my application, the set of fds almost never changes, but the set of
events I want changes all the time. The main thing that changes is
whether I care about EPOLLOUT. If I'm ready to send something, then I
want EPOLLOUT. If I'm not ready, then I don't want EPOLLOUT.
--Andy
next prev parent reply other threads:[~2015-01-22 21:13 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-01-20 9:57 [PATCH RFC 0/6] epoll: Introduce new syscall "epoll_mod_wait" Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 1/6] epoll: Extract epoll_wait_do and epoll_pwait_do Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 2/6] epoll: Specify clockid explicitly Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 3/6] epoll: Add definition for epoll_mod_wait structures Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 4/6] epoll: Extract ep_ctl_do Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 5/6] epoll: Add implementation for epoll_mod_wait Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 12:50 ` Michael Kerrisk (man-pages)
2015-01-20 12:50 ` Michael Kerrisk (man-pages)
2015-01-20 12:50 ` Michael Kerrisk (man-pages)
2015-01-21 4:59 ` Fam Zheng
2015-01-21 4:59 ` Fam Zheng
2015-01-21 4:59 ` Fam Zheng
2015-01-21 7:52 ` Michael Kerrisk (man-pages)
2015-01-21 7:52 ` Michael Kerrisk (man-pages)
2015-01-21 7:52 ` Michael Kerrisk (man-pages)
2015-01-21 8:58 ` Fam Zheng
2015-01-21 8:58 ` Fam Zheng
2015-01-21 10:37 ` Paolo Bonzini
2015-01-21 10:37 ` Paolo Bonzini
2015-01-21 11:14 ` Fam Zheng
2015-01-21 11:14 ` Fam Zheng
2015-01-21 11:14 ` Fam Zheng
2015-01-21 11:50 ` Paolo Bonzini
2015-01-21 11:50 ` Paolo Bonzini
2015-01-21 11:50 ` Paolo Bonzini
2015-01-22 21:12 ` Andy Lutomirski [this message]
2015-01-22 21:12 ` Andy Lutomirski
2015-01-22 21:12 ` Andy Lutomirski
2015-01-23 6:20 ` Fam Zheng
2015-01-23 6:20 ` Fam Zheng
2015-01-23 6:20 ` Fam Zheng
2015-01-23 9:56 ` Paolo Bonzini
2015-01-23 9:56 ` Paolo Bonzini
2015-01-23 9:56 ` Paolo Bonzini
2015-01-21 10:34 ` Paolo Bonzini
2015-01-21 10:34 ` Paolo Bonzini
2015-01-21 10:34 ` Paolo Bonzini
2015-01-21 7:56 ` Omar Sandoval
2015-01-21 7:56 ` Omar Sandoval
2015-01-21 7:56 ` Omar Sandoval
2015-01-21 8:59 ` Fam Zheng
2015-01-21 8:59 ` Fam Zheng
2015-01-21 8:59 ` Fam Zheng
2015-01-20 9:57 ` [PATCH RFC 6/6] x86: Hook up epoll_mod_wait syscall Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 9:57 ` Fam Zheng
2015-01-20 10:37 ` [PATCH RFC 0/6] epoll: Introduce new syscall "epoll_mod_wait" Rasmus Villemoes
2015-01-20 10:37 ` Rasmus Villemoes
2015-01-20 10:53 ` Fam Zheng
2015-01-20 10:53 ` Fam Zheng
2015-01-20 12:48 ` Michael Kerrisk (man-pages)
2015-01-20 12:48 ` Michael Kerrisk (man-pages)
2015-01-20 12:48 ` Michael Kerrisk (man-pages)
2015-01-21 9:05 ` Fam Zheng
2015-01-21 9:05 ` Fam Zheng
2015-01-21 9:05 ` Fam Zheng
2015-01-20 22:40 ` Andy Lutomirski
2015-01-20 22:40 ` Andy Lutomirski
2015-01-20 22:40 ` Andy Lutomirski
2015-01-20 23:03 ` josh
2015-01-20 23:03 ` josh-iaAMLnmF4UmaiuxdJuQwMA
2015-01-20 23:03 ` josh-iaAMLnmF4UmaiuxdJuQwMA
2015-01-21 5:55 ` Michael Kerrisk (man-pages)
2015-01-21 5:55 ` Michael Kerrisk (man-pages)
2015-01-21 5:55 ` Michael Kerrisk (man-pages)
2015-01-21 9:07 ` Fam Zheng
2015-01-21 9:07 ` Fam Zheng
2015-01-21 9:07 ` Fam Zheng
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=CALCETrWwuJpFK+38mBxxTQCu7Oig22Nr+mAuO++Y+0CdAhfzkw@mail.gmail.com \
--to=luto@amacapital.net \
--cc=akpm@linux-foundation.org \
--cc=ast@plumgrid.com \
--cc=davem@davemloft.net \
--cc=dh.herrmann@gmail.com \
--cc=drysdale@google.com \
--cc=famz@redhat.com \
--cc=heiko.carstens@de.ibm.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=josh@joshtriplett.org \
--cc=keescook@chromium.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@rasmusvillemoes.dk \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@redhat.com \
--cc=mszeredi@suse.cz \
--cc=mtk.manpages@gmail.com \
--cc=oleg@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rashika.kheria@gmail.com \
--cc=tglx@linutronix.de \
--cc=tytso@mit.edu \
--cc=vapier@gentoo.org \
--cc=vgoyal@redhat.com \
--cc=viro@zeniv.linux.org.uk \
--cc=x86@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.