Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751845AbaFEOAR (ORCPT ); Thu, 5 Jun 2014 10:00:17 -0400 Received: from mx1.redhat.com ([209.132.183.28]:5769 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751321AbaFEOAP (ORCPT ); Thu, 5 Jun 2014 10:00:15 -0400 Date: Thu, 5 Jun 2014 16:01:27 +0200 From: Alexander Gordeev To: Jens Axboe Cc: linux-kernel@vger.kernel.org, Ming Lei Subject: Re: blk-mq: bitmap tag: performance degradation? Message-ID: <20140605140127.GA22198@dhcp-26-207.brq.redhat.com> References: <20140604103544.GA11350@dhcp-26-207.brq.redhat.com> <538F2AC2.1060904@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <538F2AC2.1060904@kernel.dk> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Jun 04, 2014 at 08:18:42AM -0600, Jens Axboe wrote: > A null_blk test is the absolute best case for percpu_ida, since > there are enough tags and everything is localized. The above test is > more useful for testing blk-mq than any real world application of > the tagging. > > I've done considerable testing on both 2 and 4 socket (32 and 64 > CPUs) and bitmap tagging is better in a much wider range of > applications. This includes even high tag depth devices like nvme, > and more normal ranges like mtip32xx and scsi-mq setups. Just for the record: bitmap tags on a 48 CPU box with NVMe device indeed shows almost the same performance/cache rate as the stock kernel. -- Regards, Alexander Gordeev agordeev@redhat.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/