From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 9351 invoked by alias); 31 Mar 2006 20:38:16 -0000 Received: (qmail 9344 invoked by uid 22791); 31 Mar 2006 20:38:16 -0000 X-Spam-Status: No, hits=-2.6 required=5.0 tests=BAYES_00 X-Spam-Check-By: sourceware.org Received: from mga01.intel.com (HELO fmsmga101-1.fm.intel.com) (192.55.52.88) by sourceware.org (qpsmtpd/0.31) with ESMTP; Fri, 31 Mar 2006 20:38:14 +0000 Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga101-1.fm.intel.com with ESMTP; 31 Mar 2006 12:38:13 -0800 Received: from scsmsx331.sc.intel.com (HELO scsmsx331.amr.corp.intel.com) ([10.3.90.4]) by fmsmga001.fm.intel.com with ESMTP; 31 Mar 2006 12:38:13 -0800 X-IronPort-AV: i="4.03,152,1141632000"; d="scan'208"; a="18345683:sNHT15989428" Received: from scsmsx403.amr.corp.intel.com ([10.3.90.18]) by scsmsx331.amr.corp.intel.com with Microsoft SMTPSVC(6.0.3790.211); Fri, 31 Mar 2006 12:38:12 -0800 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-MimeOLE: Produced By Microsoft Exchange V6.5 Subject: RE: SystemTap vs. FC5 Xen kernels (was: 03-23-2006 Meeting minutes) Date: Fri, 31 Mar 2006 20:38:00 -0000 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: SystemTap vs. FC5 Xen kernels (was: 03-23-2006 Meeting minutes) Thread-Index: AcZUzIP4gLmug4RFQV+fBAjYSVLYxAANIrqQ From: "Stone, Joshua I" To: "William Cohen" Cc: "Roland McGrath" , "SystemTap" X-OriginalArrivalTime: 31 Mar 2006 20:38:12.0115 (UTC) FILETIME=[073A1E30:01C65503] X-IsSubscribed: yes Mailing-List: contact systemtap-help@sourceware.org; run by ezmlm Precedence: bulk List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org X-SW-Source: 2006-q1/txt/msg00915.txt.bz2 William Cohen wrote: > On the earlier s390 kernels the regular timer interrupt was > eliminated. This was done for efficiency. The s390 has had > virtualization for years. Having the Linux kernels do the timer > interrupt was unwanted overhead. I wonder if the xen kernel is doing > the same, only have timer interrupt=20 > when something really needs to get run at a certain time. >=20 > http://lwn.net/Articles/138969/ One of the comments after this article specifically mentions that "similar patches" are in xen as well. I find it odd that the timer.ms/jiffies probes still work fine, but timer.profile gets no probes at all. It may just be that the dynamic-ticks patch changes the timer path, so the softIRQ timers still happen, but the hard IRQ timers used for timer.profile are sidestepped. It may turn out that timer.profile will have to be emulated using PMU sampling on clockticks... > Do we need variations on the timer probe, wall clock time and > virtual time?=20 Possibly - do you have a suggestion for how to accomplish this? The current timer probes are using the {add,mod,del}_timer interface, which is based purely on jiffies. Josh