From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755898AbYG2IZl (ORCPT ); Tue, 29 Jul 2008 04:25:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753170AbYG2IZ3 (ORCPT ); Tue, 29 Jul 2008 04:25:29 -0400 Received: from courier.cs.helsinki.fi ([128.214.9.1]:34816 "EHLO mail.cs.helsinki.fi" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753118AbYG2IZ1 (ORCPT ); Tue, 29 Jul 2008 04:25:27 -0400 Subject: Re: [RFC PATCH 1/4] kmemtrace: Core implementation. From: Pekka Enberg To: Eduard - Gabriel Munteanu Cc: Mathieu Desnoyers , cl@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, rdunlap@xenotime.net, mpm@selenic.com, Steven Rostedt , Thomas Gleixner In-Reply-To: <20080728173549.GA5185@localhost> References: <1216751808-14428-1-git-send-email-eduard.munteanu@linux360.ro> <1216751808-14428-2-git-send-email-eduard.munteanu@linux360.ro> <1217237084.5998.5.camel@penberg-laptop> <20080728162916.GD17823@Krystal> <20080728173549.GA5185@localhost> Content-Type: text/plain; charset=UTF-8 Date: Tue, 29 Jul 2008 11:25:27 +0300 Message-Id: <1217319927.7813.113.camel@penberg-laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.22.3.1 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Eduard-Gabriel, On Mon, 2008-07-28 at 20:35 +0300, Eduard - Gabriel Munteanu wrote: > > > > +struct kmemtrace_event { > > > > + u8 event_id; /* Allocate or free? */ > > > > + u8 type_id; /* Kind of allocation/free. */ > > > > + u16 event_size; /* Size of event */ > > > > + s32 node; /* Target CPU. */ > > > > + u64 call_site; /* Caller address. */ > > > > + u64 ptr; /* Pointer to allocation. */ > > > > + u64 bytes_req; /* Number of bytes requested. */ > > > > + u64 bytes_alloc; /* Number of bytes allocated. */ > > > > + u64 gfp_flags; /* Requested flags. */ > > > > + s64 timestamp; /* When the operation occured in ns. */ > > > > +} __attribute__ ((__packed__)); > > > > See below for detail, but this event record is way too big and not > > adapted to 32 bits architectures. > > Pekka, what do you think? Mathieu does have a good point of optimizing the memory use of an individual event so I'm okay with that. But we really don't want to force people the analyze the dump on same architecture where we captured it. So as long as that is taken care of, I'm happy. Pekka