From mboxrd@z Thu Jan 1 00:00:00 1970 From: Changli Gao Subject: Re: [RFC] sched: implement the exclusive wait queue as a LIFO queue Date: Wed, 28 Apr 2010 23:49:19 +0800 Message-ID: References: <1272430986-20436-1-git-send-email-xiaosuo@gmail.com> <20100428081545.GA19027@windriver.com> <8482.1272446987@redhat.com> <20100428132135.GA22268@shareable.org> <20100428152502.GA25569@shareable.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Howells , Yong Zhang , Xiaotian Feng , Ingo Molnar , Alexander Viro , Andrew Morton , "Eric W. Biederman" , Davide Libenzi , Roland Dreier , Stefan Richter , Peter Zijlstra , "David S. Miller" , Eric Dumazet , Christoph Lameter , Andreas Herrmann , Thomas Gleixner , Takashi Iwai , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org To: Jamie Lokier Return-path: In-Reply-To: <20100428152502.GA25569@shareable.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On Wed, Apr 28, 2010 at 11:25 PM, Jamie Lokier wr= ote: > Changli Gao wrote: >> On Wed, Apr 28, 2010 at 9:21 PM, Jamie Lokier = wrote: >> > Changli Gao wrote: >> >> >> >> fs/eventpoll.c: 1443. >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 wait.flag= s |=3D WQ_FLAG_EXCLUSIVE; >> >> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 __add_wai= t_queue(&ep->wq, &wait); >> > >> > The same thing about assumptions applies here. =C2=A0The userspace= process >> > may be waiting for an epoll condition to get access to a resource, >> > rather than being a worker thread interchangeable with others. >> >> Oh, the lines above are the current ones. So the assumptions applies >> and works here. > > No, because WQ_FLAG_EXCLUSIVE doesn't have your LIFO semantic at the = moment. > > Your patch changes the behaviour of epoll, though I don't know if it > matters. =C2=A0Perhaps all programs which have multiple tasks waiting= on > the same epoll fd are "interchangeable worker thread" types anyway :-= ) > No. You are wrong. I meant epoll implemented LIFO on its own. You should check the code. :) >> > For example, userspace might be using a pipe as a signal-safe lock= , or >> > signal-safe multi-token semaphore, and epoll to wait for that pipe= =2E >> > >> > WQ_FLAG_EXCLUSIVE means there is no point waking all tasks, to avo= id a >> > pointless thundering herd. =C2=A0It doesn't mean unfairness is ok. >> >> The users should not make any assumption about the waking up sequenc= e, >> neither LIFO nor FIFO. > > Correct, but they should be able to assume non-starvation (eventual > progress) for all waiters. > > It's one of those subtle things, possibly a unixy thing: Non-RT tasks > should always make progress when the competition is just other non-RT > tasks, even if the progress is slow. > > Starvation can spread out beyond the starved process, to cause > priority inversions in other tasks that are waiting on a resource > locked by the starved process. =C2=A0Among other things, that can cau= se > higher priority tasks, and RT priority tasks, to block permanently. > Very unpleasant. > >> > The LIFO idea _might_ make sense for interchangeable worker-thread >> > situations - including userspace. =C2=A0It would make sense for pi= pe >> > waiters, socket waiters (especially accept), etc. >> >> Yea, and my following patches are for socket waiters. > > Occasionally unix socketpairs are occasionally used in the above ways= too. > > I'm not against your patch, but I worry that starvation is a new > semantic, and it may have a significant effect on something - either > in the kernel, or in userspace which is harder to check. Thanks for your reminding. > > I suspect it's possible to combine LIFO-ish and FIFO-ish queuing to > prevent starvation while getting some of the locality benefit. > Something like add-LIFO and increment a small counter in the next wai= t > entry, but never add in front of an entry whose counter has reached > MAX_LIFO_WAITERS? :-) > It is a little complex, and I'll keep it simple and improve it when nec= essary. --=20 Regards=EF=BC=8C Changli Gao(xiaosuo@gmail.com)