From mboxrd@z Thu Jan 1 00:00:00 1970 From: William Lee Irwin III Subject: Re: simultaneous creates in a directory Date: Fri, 27 Sep 2002 13:44:25 -0700 Sender: linux-fsdevel-owner@vger.kernel.org Message-ID: <20020927204425.GT22942@holomorphy.com> References: <20020927150249.B27592@parcelfarce.linux.theplanet.co.uk> <3D94B512.2BDF1840@digeo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Matthew Wilcox , linux-fsdevel@vger.kernel.org, dwmw2@infradead.org Return-path: To: Andrew Morton Content-Description: brief message Content-Disposition: inline In-Reply-To: <3D94B512.2BDF1840@digeo.com> List-Id: linux-fsdevel.vger.kernel.org Matthew Wilcox wrote: >> At startup, tiobench does a large number of open(O_CREAT) calls, all >> in the same directory. This leads to a large number of processes all >> trying to do down() on the parent directory's i_sem. That wouldn't be >> so bad, but each one is sleeping with an entire page (of ZONE_NORMAL) >> allocated. 800MB of ZONE_NORMAL / 4k pages.. ok, it'd take 200,000 >> tasks to completely OOM your box, but a user can certainly make life >> difficult for us with fewer tasks. >> The most important question is: Do we care? tiobench is only a benchmark. On Fri, Sep 27, 2002 at 12:44:18PM -0700, Andrew Morton wrote: > If the fs was mounted -o sync or -o dirsync, those creates would involve > synchronous I/O inside i_sem. So the problem is potentially more serious > in such a setup. > Even then, do we care? Well hrm. One page of ZONE_NORMAL per process > doesn't sound like the end of the world... Well, it's one of the larger contributors to one of my OOM scenarios, which is why I asked willy to do it. Also consider /tmp/ ... Cheers, Bill