Message-ID: <1420708372.18399.15.camel@suse.cz>
Date:	Thu, 08 Jan 2015 10:12:52 +0100
From:	Miklos Szeredi <mszeredi@...e.cz>
To:	Fam Zheng <famz@...hat.com>
Cc:	linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	"H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
	Alexander Viro <viro@...iv.linux.org.uk>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Juri Lelli <juri.lelli@...il.com>, Zach Brown <zab@...bo.net>,
	David Drysdale <drysdale@...gle.com>,
	Kees Cook <keescook@...omium.org>,
	Alexei Starovoitov <ast@...mgrid.com>,
	David Herrmann <dh.herrmann@...il.com>,
	Dario Faggioli <raistlin@...ux.it>,
	Theodore Ts'o <tytso@....edu>,
	Peter Zijlstra <peterz@...radead.org>,
	Vivek Goyal <vgoyal@...hat.com>,
	Mike Frysinger <vapier@...too.org>,
	Heiko Carstens <heiko.carstens@...ibm.com>,
	Rasmus Villemoes <linux@...musvillemoes.dk>,
	Oleg Nesterov <oleg@...hat.com>,
	Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
	Fabian Frederick <fabf@...net.be>,
	Josh Triplett <josh@...htriplett.org>,
	"David S. Miller" <davem@...emloft.net>,
	linux-fsdevel@...r.kernel.org, linux-api@...r.kernel.org,
	Paolo Bonzini <pbonzini@...hat.com>,
	Stefan Hajnoczi <stefanha@...hat.com>,
	"Michael Kerrisk (man-pages)" <mtk.manpages@...il.com>
Subject: Re: [PATCH 0/3] epoll: Add epoll_pwait1 syscall

On Thu, 2015-01-08 at 16:25 +0800, Fam Zheng wrote:
> Applications could use epoll interface when then need to poll a big number of
> files in their main loops, to achieve better performance than ppoll(2). Except
> for one concern: epoll only takes timeout parameters in microseconds, rather
> than nanoseconds.
> 
> That is a drawback we should address. For a real case in QEMU, we run into a
> scalability issue with ppoll(2) when many devices are attached to guest, in
> which case many host fds, such as virtual disk images and sockets, need to be
> polled by the main loop. As a result we are looking at switching to epoll, but
> the coarse timeout precision is a trouble, as explained below. 
> 
> We're already using prctl(PR_SET_TIMERSLACK, 1) which is necessary to implement
> timers in the main loop; and we call ppoll(2) with the next firing timer as
> timeout, so when ppoll(2) returns, we know that we have more work to do (either
> handling IO events, or fire a timer callback). This is natual and efficient,
> except that ppoll(2) itself is slow.
> 
> Now that we want to switch to epoll, to speed up the polling. However the timer
> slack setting will be effectively undone, because that way we will have to
> round up the timeout to microseconds honoring timer contract. But consequently,
> this hurts the general responsiveness.
> 
> Note: there are two alternatives, without changing kernel:
> 
> 1) Leading ppoll(2), with the epollfd only and a nanosecond timeout. It won't
> be slow as one fd is polled. No more scalability issue. And if there are
> events, we know from ppoll(2)'s return, then we do the epoll_wait(2) with
> timeout=0; otherwise, there can't be events for the epoll, skip the following
> epoll_wait and just continue with other work.
> 
> 2) Setup and add a timerfd to epoll, then we do epoll_wait(..., timeout=-1).
> The timerfd will hopefully force epoll_wait to return when it timeouts, even if
> no other events have arrived. This will inheritly give us timerfd's precision.
> Note that for each poll, the desired timeout is different because the next
> timer is different, so that, before each epoll_wait(2), there will be a
> timerfd_settime syscall to set it to a proper value.
> 
> Unfortunately, both approaches require one more syscall per iteration, compared
> to the original single ppoll(2), cost of which is unneglectable when we talk
> about nanosecond granularity.

Please consider adding a "flags" argument to the new syscall (and
returning EINVAL if non-zero).  See this article, which shows that
extended syscalls almost always want flags, and they often get it only
on the second try:

http://lwn.net/Articles/585415/

Thanks,
Miklos

P.S. stray apostrophes in To: and Cc: lines seems to be causing trouble.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists