From: Eric Wong Subject: Re: [RFC] eventpoll: Move a kmem_cache_alloc and kmem_cache_free Date: Sun, 22 Sep 2013 20:41:37 +0000 Message-ID: <20130922204137.GA1612@dcvr.yhbt.net> References: <1379087642-131349-1-git-send-email-nzimmer@sgi.com> <5239FA69.8030202@akamai.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Nathan Zimmer , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, Al Viro To: Jason Baron Return-path: Content-Disposition: inline In-Reply-To: <5239FA69.8030202@akamai.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Jason Baron wrote: > epoll: reduce usage of global 'epmutex' lock > > Epoll file descriptors that are 1 link from a wakeup source and > are not nested within other epoll descriptors, or pointing to > other epoll descriptors, don't need to check for loop creation or > the creation of wakeup storms. Because of this we can avoid taking > the global 'epmutex' in these cases. This state for the epoll file > descriptor is marked as 'EVENTPOLL_BASIC'. Once the epoll file > descriptor is attached to another epoll file descriptor it is > labeled as 'EVENTPOLL_COMPLEX', and full loop checking and wakeup > storm creation are checked using the the global 'epmutex'. It does > not transition back. Hopefully, this is a common usecase... Cool. I was thinking about doing the same thing down the line (for EPOLL_CTL_ADD, too) > @@ -166,6 +167,14 @@ struct epitem { > > /* The structure that describe the interested events and the source fd */ > struct epoll_event event; > + > + /* TODO: really necessary? */ > + int on_list; There's some things we can overload to avoid increasing epitem size (.ep, .ffd.fd, ...), so on_list should be unnecessary.