Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754833AbYCMPVy (ORCPT ); Thu, 13 Mar 2008 11:21:54 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752842AbYCMPVr (ORCPT ); Thu, 13 Mar 2008 11:21:47 -0400 Received: from mailhub.sw.ru ([195.214.232.25]:5311 "EHLO relay.sw.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752690AbYCMPVq (ORCPT ); Thu, 13 Mar 2008 11:21:46 -0400 Date: Thu, 13 Mar 2008 18:21:42 +0300 From: Alexey Dobriyan To: linux-kernel@vger.kernel.org Subject: Not so fair group scheduling Message-ID: <20080313152142.GB3148@localhost.sw.ru> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.11 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 637 Lines: 17 Simple testcase: a) 2 physical CPUs, not HT or something b) root gets 1024 cpu_share according to /sys/kernel/uids/0/cpu-chare c) user gets 1024 cpu_chare --//-- root runs 1 busy loop, user runs 2 busy loops According to top they got 57% for root, and 66+77% for user. But they should have 100%/50+50% division. Am I right? If yes are there any patches to fix this available for testing? -- 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/