Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965066AbWHOSle (ORCPT ); Tue, 15 Aug 2006 14:41:34 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S965095AbWHOSle (ORCPT ); Tue, 15 Aug 2006 14:41:34 -0400 Received: from main.gmane.org ([80.91.229.2]:43742 "EHLO ciao.gmane.org") by vger.kernel.org with ESMTP id S965066AbWHOSld (ORCPT ); Tue, 15 Aug 2006 14:41:33 -0400 X-Injected-Via-Gmane: http://gmane.org/ To: linux-kernel@vger.kernel.org From: Jason Lunz Subject: Re: Strange write starvation on 2.6.17 (and other) kernels Date: Tue, 15 Aug 2006 18:40:41 +0000 (UTC) Organization: PBR Streetgang Message-ID: References: <44E0A69C.5030103@agh.edu.pl> X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: jameson.reflexsecurity.com User-Agent: slrn/0.9.8.1pl1 (Debian) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 636 Lines: 9 szymans@agh.edu.pl said: > I've encountered a strange problem - if an application is sequentially > writing a large file on a busy machine, a single write() of 64KB may > take even 30 seconds. But if I do fsync() after each write() the maximum If the sleeps are that long, and reproducible, then maybe you can find the offending wait by using sysrq-t while the writer is blocked. Jason - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/