From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755064AbaIPTan (ORCPT ); Tue, 16 Sep 2014 15:30:43 -0400 Received: from mx1.redhat.com ([209.132.183.28]:52398 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754840AbaIPTal (ORCPT ); Tue, 16 Sep 2014 15:30:41 -0400 From: Jeff Moyer To: Milosz Tanski Cc: linux-kernel@vger.kernel.org, Christoph Hellwig , linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, Mel Gorman , Volker Lendecke , Tejun Heo Subject: Re: [RFC PATCH 0/7] Non-blockling buffered fs read (page cache only) References: X-PGP-KeyID: 1F78E1B4 X-PGP-CertKey: F6FE 280D 8293 F72C 65FD 5A58 1FF8 A7CA 1F78 E1B4 X-PCLoadLetter: What the f**k does that mean? Date: Tue, 16 Sep 2014 15:30:04 -0400 In-Reply-To: (Milosz Tanski's message of "Mon, 15 Sep 2014 16:20:01 -0400") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Milosz Tanski writes: > This patcheset introduces an ability to perform a non-blocking read from > regular files in buffered IO mode. This works by only for those filesystems > that have data in the page cache. > > It does this by introducing new syscalls new syscalls readv2/writev2 and > preadv2/pwritev2. These new syscalls behave like the network sendmsg, recvmsg > syscalls that accept an extra flag argument (O_NONBLOCK). > > It's a very common patern today (samba, libuv, etc..) use a large threadpool to > perform buffered IO operations. They submit the work form another thread > that performs network IO and epoll or other threads that perform CPU work. This > leads to increased latency for processing, esp. in the case of data that's > already cached in the page cache. > > With the new interface the applications will now be able to fetch the data in > their network / cpu bound thread(s) and only defer to a threadpool if it's not > there. In our own application (VLDB) we've observed a decrease in latency for > "fast" request by avoiding unnecessary queuing and having to swap out current > tasks in IO bound work threads. > > I have co-developed these changes with Christoph Hellwig, a whole lot of his > fixes went into the first patch in the series (were squashed with his > approval). > > I am going to post the perf report in a reply-to to this RFC. You can send the performance data along with the patch series, no need to separate it off in a reply. One additional patch I'd like to see is a man page update. That would help clarify exactly what you're trying to accomplish. I look forward to v2! Cheers, Jeff