From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andre Tomt Subject: Re: mdadm creating raid5 with all spare disks Date: Fri, 11 Dec 2009 10:08:44 +0100 Message-ID: <4B220C1C.1040902@tomt.net> References: <1D0665FE-138F-480F-9872-48C94CEBC5C2@mac.com> <20091211071006.56270ebf@notabene.brown> <91296851101702456968380052308470713510-Webmail@me.com> <4B2196B0.2090604@sauce.co.nz> <6E2CD5BC-5F08-44A0-869C-1875DF5CCA9F@mac.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <6E2CD5BC-5F08-44A0-869C-1875DF5CCA9F@mac.com> Sender: linux-raid-owner@vger.kernel.org To: Matt Tehonica Cc: Richard Scobie , "linux-raid@vger.kernel.org" List-Id: linux-raid.ids On 11.12.2009 02:01, Matt Tehonica wrote: > On Dec 10, 2009, at 7:47 PM, Richard Scobie wro= te: >> Looks like the drives are being dropped by the controller. >> >> I believe there was some recent discussion here about mv_sas, md and >> failures under heavy I/O load. > > Thanks Richard! After some more review I found many people with this > problem and appears the linux-scsi devs submitted patches mid last > month. Building the latest kernel as we speak! =46YI; The fixes has not made it to mainline yet so 2.6.32 and 2.6.33-g= it=20 is still broken with this driver. Not sure if they've landed in some=20 scsi tree yet but manually applying patches 1-6 from the linux-scsi=20 mailing list worked for me, at least to the point that it is now usable= =20 (patch 7 is for some libsas change not in 2.6.32). On a related note, mptsas driver also seems to have issues with newer=20 HBA's. Non-RAID SAS HBA's doesn't seem to be in a very good shape in=20 Linux nowadays. Might give a mpt2sas driven controller a spin soon,=20 curious on how that pans out.. --=20 Andr=E9 -- To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html