From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Moyer Subject: Re: aio: bump i_count instead of using igrab Date: Mon, 23 Aug 2010 17:18:41 -0400 Message-ID: References: <20100823144755.GP21975@think> <20100823145031.GA1279@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Chris Mason , linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org To: Christoph Hellwig Return-path: In-Reply-To: <20100823145031.GA1279@infradead.org> (Christoph Hellwig's message of "Mon, 23 Aug 2010 10:50:31 -0400") Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Christoph Hellwig writes: > On Mon, Aug 23, 2010 at 10:47:55AM -0400, Chris Mason wrote: >> The aio batching code is using igrab to get an extra reference on the >> inode so it can safely batch. igrab will go ahead and take the global >> inode spinlock, which can be a bottleneck on large machines doing lots >> of AIO. >> >> In this case, igrab isn't required because we already have a reference >> on the file handle. It is safe to just bump the i_count directly >> on the inode. >> >> Benchmarking shows this patch brings IOP/s on tons of flash up by about >> 2.5X. > > There's some places in XFS where we do the same, and it showed up as a > bottle neck before. Instead of open coding the increment we have > a wrapper that includes and assert that the numbers is always positive. > > I think we really want a proper helper for general use instead of > completly opencoding it. Well, it would make detecting races or invalid assumptions a little easier. If Chris wants to code that up, that's fine with me. Honestly, though, I don't think it's necessary. I've gone through the alloc/free paths for the inode and I'm convinced this is safe. I'm happy with this version of the patch. Reviewed-by: Jeff Moyer