Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752810AbZDNEP1 (ORCPT ); Tue, 14 Apr 2009 00:15:27 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751100AbZDNEPM (ORCPT ); Tue, 14 Apr 2009 00:15:12 -0400 Received: from yw-out-2324.google.com ([74.125.46.28]:50183 "EHLO yw-out-2324.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750996AbZDNEPL (ORCPT ); Tue, 14 Apr 2009 00:15:11 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer:content-transfer-encoding; b=xOzaTShkiDU8PVe3lbFtOHZm+r8ybLON4TvqdFn1eq32aiE3bODr+W12+hkV8R7rV2 84oouxWL4oTofmxvaGyYGwfcMLGjlVpA/dzQYPSCciM48+ei/9Z0HNIIuygV4DQUSqYz tOkl2PnAO5Gy2RheIlgptPnPV3C+cjKPzk7QE= Subject: Re: [PATCH] blktrace: move trace/ dir to /sys/block/sda/ From: Tom Zanussi To: Ingo Molnar Cc: Jens Axboe , Steven Rostedt , Li Zefan , "Theodore Ts'o" , Arnaldo Carvalho de Melo , LKML In-Reply-To: <20090413201155.GA17450@elte.hu> References: <49E31931.5000506@cn.fujitsu.com> <20090413180054.GZ5178@kernel.dk> <20090413201155.GA17450@elte.hu> Content-Type: text/plain Date: Mon, 13 Apr 2009 23:15:04 -0500 Message-Id: <1239682504.7011.46.camel@tropicana> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1946 Lines: 47 On Mon, 2009-04-13 at 22:11 +0200, Ingo Molnar wrote: > * Jens Axboe wrote: > > > On Mon, Apr 13 2009, Li Zefan wrote: > > > Impact: allow ftrace-plugin blktrace to trace device-mapper devices > > > > > > blktrace can't trace a single partition, so it makes no sense to > > > have one trace/ dir in each /sys/block/sda/sdaX. Move it to > > > /sys/block/sda/. > > > > > > Thus we fix an issue reported by Ted, that ftrace-plugin > > > blktrace can't be used to trace device-mapper devices. > > > > Perhaps I never committed that patch, but it would be trivial to > > do partition based blktrace tracing. It's also quite useful. So > > please don't go changing things to make that harder to support, it > > would be nicer to just add the (small) bits to support > > per-partition tracing. It's basically just a start/stop sector > > range, while some events are per-device and should just be > > included always. > > btw., per tracepoint filters could be used for that. That would > allow multiple partitions to be traced at once. > > blktrace user-space could make use of sector range filters straight > away [ hm, Tom - do we have the <= comparison operator already, or > is that still WIP? ] - but i think it's better to do this in a more The new comparison operators aren't there yet, but will be part of the new parser, which I'll be getting back to this week. Tom > integrated way: via the sysfs API, via /sys/block/sda/sda2/trace/. > > So when a partition's trace entry is activated, it would > auto-install a specific filter expression for sda, with the sector > range of that partition. Or something like that. How does this > sound? > > 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/