From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paul Jackson Subject: Re: Task watchers v2 Date: Tue, 19 Dec 2006 04:26:07 -0800 Message-ID: <20061219042607.dcd865a3.pj@sgi.com> References: <20061215000754.764718000@us.ibm.com> <20061215000817.771088000@us.ibm.com> <1166420641.15989.117.camel@ymzhang> <1166447901.995.110.camel@localhost.localdomain> <20061218214159.2d571bf5.pj@sgi.com> <1166529955.995.177.camel@localhost.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1166529955.995.177.camel@localhost.localdomain> List-Unsubscribe: List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org To: Matt Helsley Cc: yanmin_zhang@linux.intel.com, akpm@osdl.org, linux-kernel@vger.kernel.org, jes@sgi.com, hch@lst.de, viro@zeniv.linux.org.uk, sgrubb@redhat.com, linux-audit@redhat.com, systemtap@sources.redhat.com List-Id: linux-audit@redhat.com Matt wrote: > Previous iterations of task watchers would prevent the code in these > paths from being inlined. Furthermore, the code certainly wouldn't be > placed near the table of function pointers (which was in an entirely > different ELF section). By placing them adjacent to each other in the > same ELF section we can improve the likelihood of cache hits in > fork-heavy workloads (which were the ones that showed a performance > decrease in the previous iteration of these patches). Ah so - by marking some of the fork (and exit, exec, ...) routines with the WATCH_TASK_* mechanism, you can compact them together in the kernel's text pages, instead of having them scattered about based on whatever source files they are in. Nice. -- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson 1.925.600.0401