From: "Aaron Wiebe" Subject: Re: Client performance questions Date: Tue, 11 Dec 2007 12:11:54 -0500 Message-ID: References: <0a15723c4b267d4eb8b5ad05800315c0@swip.net> <20732321-A9D9-4A20-8337-C8CBEC988A57@oracle.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: "Fredrik Lindgren" , "linux-nfs@vger.kernel.org" To: "Chuck Lever" Return-path: Received: from nz-out-0506.google.com ([64.233.162.237]:3105 "EHLO nz-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751291AbXLKRL4 (ORCPT ); Tue, 11 Dec 2007 12:11:56 -0500 Received: by nz-out-0506.google.com with SMTP id s18so1231022nze for ; Tue, 11 Dec 2007 09:11:55 -0800 (PST) In-Reply-To: <20732321-A9D9-4A20-8337-C8CBEC988A57@oracle.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: Afternoon.. On Dec 11, 2007 12:03 PM, Chuck Lever wrote: > > If windowing is a problem, have you tried boosting the default size > of the socket send and receive buffers on both ends? I believe we tweaked that on the client side at one point, but our issues with the current settings puts most of the problems on the storage side at present. We've shifted our concentration mostly towards getting our storage itself performing better, rather than getting client throughput higher so we can crush our storage even more. But since these things tend to be cyclical, I'll keep it in mind for when our bottleneck shifts back again. :) -Aaron