Return-Path: linux-nfs-owner@vger.kernel.org Received: from mail-ie0-f177.google.com ([209.85.223.177]:64012 "EHLO mail-ie0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753483AbaDXRWK (ORCPT ); Thu, 24 Apr 2014 13:22:10 -0400 Received: by mail-ie0-f177.google.com with SMTP id rl12so2693683iec.36 for ; Thu, 24 Apr 2014 10:22:10 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <20140424031216.GA18817@umich.edu> References: <20140424031216.GA18817@umich.edu> Date: Thu, 24 Apr 2014 19:22:10 +0200 Message-ID: Subject: Re: Tuning Linux NFSv4 for high latency connections? From: Cedric Blancher To: Jim Rees , Trond Myklebust Cc: Linux NFS Mailing List Content-Type: text/plain; charset=UTF-8 Sender: linux-nfs-owner@vger.kernel.org List-ID: On 24 April 2014 05:12, Jim Rees wrote: > Cedric Blancher wrote: > > Are there any options to improve the Linux NFSv4 performance over a > high latency connection? > > We did some work along these lines at CITI years ago. As I remember, the > main thing was to increase net.ipv4.tcp_[rw]mem on the server side, because > tcp auto-tuning was being defeated. This may be less of an issue with your > work load, which sounds like many small files rather than one big one. In > theory, NFSv4 delegations should help, but I don't know how well that works. Trond, can you help? Ced -- Cedric Blancher Institute Pasteur