From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sage Weil Subject: Re: read performance not perfect Date: Fri, 5 Aug 2011 13:17:02 -0700 (PDT) Message-ID: References: <4E3B2D78.5060605@ufm.su> <4E3B8F0E.20606@ufm.su> <4E3C44DC.9090906@ufm.su> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Return-path: Received: from cobra.newdream.net ([66.33.216.30]:45180 "EHLO cobra.newdream.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756221Ab1HEUMq (ORCPT ); Fri, 5 Aug 2011 16:12:46 -0400 In-Reply-To: <4E3C44DC.9090906@ufm.su> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Fyodor Ustinov Cc: ceph-devel@vger.kernel.org On Fri, 5 Aug 2011, Fyodor Ustinov wrote: > On 08/05/2011 07:07 PM, Sage Weil wrote: > > > > This is the problem. The readahead patches in the master branch of > > git://ceph.newdream.net/git/ceph-client.git. They're not upstream yet. > > Sorry that wasn't clear! > > http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=commit;h=e9852227431a0ed6ceda064f33e4218757acab6c > - it's not this patch? Nope, it's ebd62c49c0a71a9af6b92b4f0cedfd2b1d46c16e, in ceph-client.git. Then d0a287e18a81a0314a9aa82b6f54eb7f5ecabd60 bumps up the default rasize window. FWIW I saw a big jump in read spead on my cluster (now fully saturates the client interface). sage