From owner-freebsd-bugs@FreeBSD.ORG Tue Jan 5 21:50:03 2010 Return-Path: Delivered-To: freebsd-bugs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 021881065679 for ; Tue, 5 Jan 2010 21:50:03 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id B89988FC18 for ; Tue, 5 Jan 2010 21:50:02 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.3/8.14.3) with ESMTP id o05Lo2Bt039538 for ; Tue, 5 Jan 2010 21:50:02 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.3/8.14.3/Submit) id o05Lo2mg039537; Tue, 5 Jan 2010 21:50:02 GMT (envelope-from gnats) Resent-Date: Tue, 5 Jan 2010 21:50:02 GMT Resent-Message-Id: <201001052150.o05Lo2mg039537@freefall.freebsd.org> Resent-From: FreeBSD-gnats-submit@FreeBSD.org (GNATS Filer) Resent-To: freebsd-bugs@FreeBSD.org Resent-Reply-To: FreeBSD-gnats-submit@FreeBSD.org, Marko Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id BCC6B106566B for ; Tue, 5 Jan 2010 21:45:44 +0000 (UTC) (envelope-from nobody@FreeBSD.org) Received: from www.freebsd.org (www.freebsd.org [IPv6:2001:4f8:fff6::21]) by mx1.freebsd.org (Postfix) with ESMTP id ABC7C8FC0A for ; Tue, 5 Jan 2010 21:45:44 +0000 (UTC) Received: from www.freebsd.org (localhost [127.0.0.1]) by www.freebsd.org (8.14.3/8.14.3) with ESMTP id o05Ljihq077778 for ; Tue, 5 Jan 2010 21:45:44 GMT (envelope-from nobody@www.freebsd.org) Received: (from nobody@localhost) by www.freebsd.org (8.14.3/8.14.3/Submit) id o05Lji35077777; Tue, 5 Jan 2010 21:45:44 GMT (envelope-from nobody) Message-Id: <201001052145.o05Lji35077777@www.freebsd.org> Date: Tue, 5 Jan 2010 21:45:44 GMT From: Marko To: freebsd-gnats-submit@FreeBSD.org X-Send-Pr-Version: www-3.1 Cc: Subject: misc/142365: FreeBSD RAID1 (gmirror) is much slower than Linux RAID1! X-BeenThere: freebsd-bugs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Bug reports List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 05 Jan 2010 21:50:03 -0000 >Number: 142365 >Category: misc >Synopsis: FreeBSD RAID1 (gmirror) is much slower than Linux RAID1! >Confidential: no >Severity: serious >Priority: medium >Responsible: freebsd-bugs >State: open >Quarter: >Keywords: >Date-Required: >Class: change-request >Submitter-Id: current-users >Arrival-Date: Tue Jan 05 21:50:02 UTC 2010 >Closed-Date: >Last-Modified: >Originator: Marko >Release: 7.1 >Organization: www.cursor.si >Environment: 32bit and 64 bit >Description: I run many servers with double hard-disk for lowering the risk of data loss. I normally use software RAID1 on these systems (RAID1 is giving me very simple situation if one disk fails, software RAID1 is making my hardware cheaper). After doing extensive performance testing in FreeBSD 7.1 I found out, that FreeBSD is much faster in arithmetic calculations than Linux. But when I tried to store data in the database (PostgreSQL) I was very dissapointed. The same hardware configuration is by factor 2 or 3 times slower than Linux, because of very slow gmirror. Gmirror is even slower than disk access without RAID at all... (although 2 disks are available and therefore reads should be 2x faster). I compared Scientific Linux 5.4 (based on Red Hat Enterprise 5.4) with FreeBSD 7.1. I googled much on this topic, but there is no solution. One issue-ticked on this topic got very low priority. I had to decide to use Linux instead, because it was much faster for my servers. Please make GMIRROR faster in the next releases. >How-To-Repeat: 1) Install GMIRROR on FreeBSD according to the User Manual. 2) Do performance measurements (disk access). 3) Then install CentOS 5.4 or Scientific Linux 5.4 and make software RAID1 within the installation wizard. 4) Do performance measurements (disk access). 5) Compare performance measurements. >Fix: not known (at least for software RAID1) >Release-Note: >Audit-Trail: >Unformatted: