Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id ; Mon, 24 Feb 2003 07:35:48 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id ; Mon, 24 Feb 2003 07:35:47 -0500 Received: from mx2.elte.hu ([157.181.151.9]:49336 "HELO mx2.elte.hu") by vger.kernel.org with SMTP id ; Mon, 24 Feb 2003 07:35:47 -0500 Date: Mon, 24 Feb 2003 13:45:48 +0100 (CET) From: Ingo Molnar Reply-To: Ingo Molnar To: "Albert D. Cahalan" Cc: procps-list@redhat.com, Linus Torvalds , , , Subject: Re: [patch] procfs/procps threading performance speedup, 2.5.62 In-Reply-To: <200302241229.h1OCTRF331287@saturn.cs.uml.edu> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 910 Lines: 23 On Mon, 24 Feb 2003, Albert D. Cahalan wrote: > Sorting is not default because of the memory requirements and because > there have been many kernel bugs that cause ps to hang when it hits a > particular process. Sorting may mean that ps hangs or is killed before > producing anything. in fact there was an unconditional qsort() done after scanning all tasks, until i pointed it out to Alex. It never caused any problems, and sorting never showed up as a source of overhead in the profiler, so i'm not sure why you insist on sorting so much. if procps hangs then that's a bug in procps. I'm not quite sure what you mean by 'it hits a particular process'. Ingo - 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/