From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 2714 invoked by alias); 18 Apr 2006 19:32:50 -0000 Received: (qmail 2697 invoked by uid 22791); 18 Apr 2006 19:32:49 -0000 X-Spam-Status: No, hits=-4.3 required=5.0 tests=AWL,BAYES_00,DK_SIGNED,DK_VERIFIED,SPF_PASS X-Spam-Check-By: sourceware.org Received: from xproxy.gmail.com (HELO xproxy.gmail.com) (66.249.82.202) by sourceware.org (qpsmtpd/0.31) with ESMTP; Tue, 18 Apr 2006 19:32:43 +0000 Received: by xproxy.gmail.com with SMTP id h29so558666wxd for ; Tue, 18 Apr 2006 12:32:41 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=fbtea/91vhm8NWM9LyOm53+m2+c5D4fa3pWY5JEyCZJQpD+GiK2dPgswTIXuLl/84qFKQUktH+wsbqdgco7Uv/22WgwI56Uzcxlc4ro9D0mqDVFqHK0rkhG6T7dPky3LUhAarAo43ZbOiRyvO3NpTO+QMtsEMir8WU2Va3RJ6Ro= Received: by 10.70.133.2 with SMTP id g2mr995420wxd; Tue, 18 Apr 2006 12:32:41 -0700 (PDT) Received: by 10.70.33.7 with HTTP; Tue, 18 Apr 2006 12:32:41 -0700 (PDT) Message-ID: Date: Tue, 18 Apr 2006 19:32:00 -0000 From: "James Dickens" To: sourceware-bugzilla@sourceware.org Subject: Re: [Bug kprobes/2062] Return probes does not scale well on SMP box Cc: systemtap@sources.redhat.com In-Reply-To: <20060418180940.2285.qmail@sourceware.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <20051216010933.2062.anil.s.keshavamurthy@intel.com> <20060418180940.2285.qmail@sourceware.org> 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-q2/txt/msg00178.txt.bz2 On 18 Apr 2006 18:09:40 -0000, jkenisto at us dot ibm dot com wrote: > > ------- Additional Comments From jkenisto at us dot ibm dot com 2006-04-= 18 18:09 ------- > Created an attachment (id=3D974) > --> (http://sourceware.org/bugzilla/attachment.cgi?id=3D974&action=3Dvie= w) > Thoughts on finer-grained locking for return probes > > I don't see how we can avoid significant lock overhead, because kretprobe= data > structures are much more dynamic that kprobe data structures: we're const= antly > moving kretprobe_instances back and forth between the kretprobe's free li= st and > kretprobe_inst_table[]. > > I've been thinking about this issue, though. Attached are my current tho= ughts > on finer-grained locking. > why not just store data per cpu/core, there is no way that two exit probes can fire at the same time on the same cpu/core if you are in the kernel and inturupts are disabled. Then you just need one lock for when you report the data from that cpus data structure. If a return probe fires while someone else is accessing are data in the cpu's structure we should give up and note the missed the probe fire and return but this would be a very rare occurance in a properly written script. James Dickens uadmin.blogspot.com > -- > > > http://sourceware.org/bugzilla/show_bug.cgi?id=3D2062 > > ------- You are receiving this mail because: ------- > You are the assignee for the bug, or are watching the assignee. >