From mboxrd@z Thu Jan 1 00:00:00 1970 From: Benjamin LaHaise Subject: Re: [RFC] Add support for semaphore-like structure with support for asynchronous I/O Date: Mon, 4 Apr 2005 12:22:16 -0400 Message-ID: <20050404162216.GA18469@kvack.org> References: <1112219491.10771.18.camel@lade.trondhjem.org> <20050330143409.04f48431.akpm@osdl.org> <1112224663.18019.39.camel@lade.trondhjem.org> <1112309586.27458.19.camel@lade.trondhjem.org> <20050331161350.0dc7d376.akpm@osdl.org> <1112318537.11284.10.camel@lade.trondhjem.org> <20050401141225.GA3707@in.ibm.com> <20050404155245.GA4659@in.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Trond Myklebust , Andrew Morton , linux-kernel@vger.kernel.org, Linux Filesystem Development , linux-aio@kvack.org Return-path: To: Suparna Bhattacharya Content-Disposition: inline In-Reply-To: <20050404155245.GA4659@in.ibm.com> Sender: owner-linux-aio@kvack.org List-Id: linux-fsdevel.vger.kernel.org On Mon, Apr 04, 2005 at 09:22:45PM +0530, Suparna Bhattacharya wrote: > And oh yes, even though this was a really small change, having to > update and verify those umpteen different arch specific pieces was not > entirely an exciting prospect - I got as far as x86, x86_64 and ppc64 > ... but stopped after that. It so happened that i_sem contention > didn't show up as a major latency issue even without async semaphores > in the kinds of workloads we were working with then. There are workloads where it does make a difference, like in audio processing. > Your approach looks reasonable and simple enough. It'd be useful if I > could visualize the caller side of things as in the NFS client stream > as you mention - do you plan to post that soon ? > I'm tempted to think about the possibility of using your iosems > with retry-based AIO. I'm not sure I see the point in adding yet another type of lock to the kernel that has different infrastructure. This will end up with much more code changing to adapt to the new iosems, rather than just using a new primative on the existing semaphores. -ben -- To unsubscribe, send a message with 'unsubscribe linux-aio' in the body to majordomo@kvack.org. For more info on Linux AIO, see: http://www.kvack.org/aio/ Don't email: aart@kvack.org