From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay3.corp.sgi.com [198.149.34.15]) by oss.sgi.com (Postfix) with ESMTP id D6B8B7CA1 for ; Thu, 7 Apr 2016 15:21:57 -0500 (CDT) Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by relay3.corp.sgi.com (Postfix) with ESMTP id 4D07BAC002 for ; Thu, 7 Apr 2016 13:21:54 -0700 (PDT) Received: from sandeen.net (sandeen.net [63.231.237.45]) by cuda.sgi.com with ESMTP id cvBRD9GhTTB5hmZC for ; Thu, 07 Apr 2016 13:21:48 -0700 (PDT) Received: from [10.0.0.4] (liberator [10.0.0.4]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by sandeen.net (Postfix) with ESMTPSA id 1A705142D for ; Thu, 7 Apr 2016 15:21:43 -0500 (CDT) Subject: Re: Determining whether stripe unit and stripe size were detected correctly References: <5BDD118B6525E24D82051EDA520EB5FC0105339D@IS-EXMB07-RP.ad.reyrey.com> From: Eric Sandeen Message-ID: <5706C157.5070400@sandeen.net> Date: Thu, 7 Apr 2016 15:21:43 -0500 MIME-Version: 1.0 In-Reply-To: <5BDD118B6525E24D82051EDA520EB5FC0105339D@IS-EXMB07-RP.ad.reyrey.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: quoted-printable Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com On 4/7/16 3:16 PM, Simpson, John R wrote: > Greetings, > = > = > = > I=92m in the process of tracking down lower than expected= performance and occasional blocked tasks on some internal file servers wit= h XFS datastores. Several sources have pointed out the importance of using= the correct stripe unit and stripe size when formatting and mounting XFS f= ilesystems, and that XFS can detect these values for some, but not all, har= dware RAID controllers. The servers in question are PowerEdge R510b server= s with PERC H700 controllers. Datastores are RAID5 with a 128K stripe. > Is there any way to determine if the stripe unit and stri= pe size were detected correctly? These values were not specified when the = filesystems were formatted or mounted. If they were not detected, is there= any way to determine them programmatically? > If this is not the correct forum for this question please= point me in the right direction. > = > = > = > Best regards, > # xfs_info /DS01 > = > meta-data=3D/dev/sdb1 isize=3D256 agcount=3D5, agsize=3D2= 68435455 blks > =3D sectsz=3D512 attr=3D2, projid32bit= =3D0 > data =3D bsize=3D4096 blocks=3D1212415488, im= axpct=3D5 > =3D sunit=3D0 swidth=3D0 blks sunit =3D=3D swidth =3D=3D 0, so no geometry is present on this filesystem. > naming =3Dversion 2 bsize=3D4096 ascii-ci=3D0 > log =3Dinternal bsize=3D4096 blocks=3D521728, versio= n=3D2 > =3D sectsz=3D512 sunit=3D0 blks, lazy-co= unt=3D1 > realtime =3Dnone extsz=3D4096 blocks=3D0, rtextents= =3D0 mkfs.xfs uses values exported by the block device, and can be seen by using blockdev to query them, i.e. blockdev --getiomin --getioopt /dev/sdb1 If it returns 0, no geometry is exported by the device, and you'd need to u= se your own knowledge of the device to set appropriate values (and to properly partition on aligned boundaries as well) -Eric _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs