From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dominik Brodowski Subject: Performance impact of CONFIG_DEBUG? direct-io test case Date: Thu, 5 Aug 2010 22:47:49 +0200 Message-ID: <20100805204749.GA6318@comet.dominikbrodowski.net> References: <20100805123649.GA18672@dhcp231-156.rdu.redhat.com> <20100805113240.GA29846@think> <20100805153519.GA7242@comet.dominikbrodowski.net> <20100805163519.GA6604@comet.dominikbrodowski.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20100805163519.GA6604@comet.dominikbrodowski.net> Sender: linux-raid-owner@vger.kernel.org To: linux-kernel@vger.kernel.org, mingo@redhat.com, peterz@infradead.org Cc: Chris Mason , josef@redhat.com, Valdis.Kletnieks@vt.edu, Michael Monnerie , Christoph Hellwig , linux-raid@vger.kernel.org, xfs@oss.sgi.com, dm-devel@redhat.com List-Id: linux-raid.ids How large is the performance impact of CONFIG_DEBUG? Well, for the test workload I've been working with lately, dd if= of=/dev/zero bs=8k count=100000 iflag=direct where is a dm-crypted LVM volume consisting of several partitions on a notebook pata harddisk, I get the following results: 1) best results are ~ 28 MB/s 2) Enabling CONFIG_DEBUG_LOCK_ALLOC, which also means CONFIG_LOCKDEP being enabled, causes the transfer rate to decrease by ~ 1.2 MB/s 3) Enabling CONFIG_DEBUG_SPINLOCK && CONFIG_DEBUG_MUTEXTES or CONFIG_DEBUG_SPINLOCK_SLEEP=y costs about ~ 0.4 MB/s each 4) Enabling all of the following options: CONFIG_DEBUG_RT_MUTEXES CONFIG_DEBUG_PI_LIST CONFIG_PROVE_LOCKING CONFIG_LOCK_STAT CONFIG_DEBUG_LOCKDEP costs another ~ 5 MB/s. So, for this test case, the performance impact of (some) CONFIG_DEBUG options is highly significant, here by about 25 %. Best, Dominik