From owner-cvs-src@FreeBSD.ORG Fri Jun 8 14:54:41 2007 Return-Path: X-Original-To: cvs-src@FreeBSD.org Delivered-To: cvs-src@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 2496316A46C; Fri, 8 Jun 2007 14:54:41 +0000 (UTC) (envelope-from gallatin@cs.duke.edu) Received: from duke.cs.duke.edu (duke.cs.duke.edu [152.3.140.1]) by mx1.freebsd.org (Postfix) with ESMTP id DE50F13C4B9; Fri, 8 Jun 2007 14:54:40 +0000 (UTC) (envelope-from gallatin@cs.duke.edu) Received: from grasshopper.cs.duke.edu (grasshopper.cs.duke.edu [152.3.145.30]) by duke.cs.duke.edu (8.14.0/8.14.0) with ESMTP id l58EsenW023768 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 8 Jun 2007 10:54:40 -0400 (EDT) Received: (from gallatin@localhost) by grasshopper.cs.duke.edu (8.12.9p2/8.12.9/Submit) id l58EsCMA072218; Fri, 8 Jun 2007 10:54:12 -0400 (EDT) (envelope-from gallatin) From: Andrew Gallatin MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <18025.28075.163371.116715@grasshopper.cs.duke.edu> Date: Fri, 8 Jun 2007 10:54:12 -0400 (EDT) To: Gleb Smirnoff In-Reply-To: <20070608135015.GP89017@FreeBSD.org> References: <200706081243.l58ChQnr045086@repoman.freebsd.org> <20070608135015.GP89017@FreeBSD.org> X-Mailer: VM 6.75 under 21.1 (patch 12) "Channel Islands" XEmacs Lucid Cc: cvs-src@FreeBSD.org, src-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/net pfil.h X-BeenThere: cvs-src@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: CVS commit messages for the src tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 08 Jun 2007 14:54:41 -0000 Gleb Smirnoff writes: > Nice! I guess you can tell how much performance did we lose before? Thanks. I was running packet blasting tests to mxge(4). At ~1.3Mpps, where my old, slow machine was cpu bound, hwpmc showed an rw lock (presumably from pfil_run_hooks), and pfil_run_hooks() as the top cpu users behind my driver's rx handler, ip_input, and udp_input. I got very busy, and never had a chance to re-run the tests with the fix in place. > Do you plan to MFC this? I honestly hadn't checked to see if the bug was in -stable. If it is, then I'll MFC it next week (if nobody beats me to it). Drew