Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S967369AbYCTA3U (ORCPT ); Wed, 19 Mar 2008 20:29:20 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S941506AbYCSXv6 (ORCPT ); Wed, 19 Mar 2008 19:51:58 -0400 Received: from mga02.intel.com ([134.134.136.20]:64411 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S942344AbYCSXv4 convert rfc822-to-8bit (ORCPT ); Wed, 19 Mar 2008 19:51:56 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.25,527,1199692800"; d="scan'208";a="263695626" X-MIMEOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 8BIT Subject: RE: [2.6.25-rc5-mm1][regression] ia64: hackbench doesn't finish>12 hour Date: Wed, 19 Mar 2008 16:50:28 -0700 Message-ID: In-reply-to: <1205969039.6437.44.camel@lappy> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [2.6.25-rc5-mm1][regression] ia64: hackbench doesn't finish>12 hour Thread-Index: AciKGMkrDvVxYApER1CMLGbJBqwfDwAAQ6Dw References: <20080318084314.FF0F.KOSAKI.MOTOHIRO@jp.fujitsu.com> <20080318094527.FF12.KOSAKI.MOTOHIRO@jp.fujitsu.com> <1205969039.6437.44.camel@lappy> From: "Yu, Fenghua" To: "Peter Zijlstra" Cc: "KOSAKI Motohiro" , "Luck, Tony" , "LKML" , , "Hidetoshi Seto" , "Andrew Morton" X-OriginalArrivalTime: 19 Mar 2008 23:50:27.0247 (UTC) FILETIME=[01B5D3F0:01C88A1C] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1030 Lines: 32 >Which makes me wonder, why did you ever use a semaphore here? Looking at >the code its a straight forward mutex. And when you would have used a >mutex lockdep would have warned about this. >There is hardly ever a good reason to use semaphores in new code, we're >trying very hard to get rid of them. The real issue here is the code path can not go to sleep. If simply replacing semaphore with mutex, the issue still happens. First of all we need to have a lock system which doesn't allow the code go to sleep. We are working on a new patch now. But one step back, if without considering this sleeping issue, I agree with you that mutex would be a better approach than semaphore. >Hmm, then again, does ia64 have lockdep? IA64 doesn't support lockdep yet. Thanks. -Fenghua -- 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/