Hi Niel, I am wondering what is the priority between RAID-5 recovery and input IO from application. I am seeing these filesystem errors when RAID-5 recovery is going on I tried to install ext3 file-system and send data to /mnt/tmpmnt(/dev/md0 mount point) using "dd" command. I noticed that when amount of data is less than RAID-5 recovery size no file system errors seen. When amount of data copied crosses RAID-5 recovery size I am seeing file-system errors. Regards, Marri -----Original Message----- From: linux-raid-owner@xxxxxxxxxxxxxxx [mailto:linux-raid-owner@xxxxxxxxxxxxxxx] On Behalf Of NeilBrown Sent: Wednesday, July 08, 2009 4:28 PM To: Guy Watkins Cc: Tirumala Reddy Marri; linux-raid@xxxxxxxxxxxxxxx; 'Dan Williams' Subject: RE: Question on RAID-5 using ADMA On Thu, July 9, 2009 9:11 am, Guy Watkins wrote: > I think you are doing --assume-clean wrong. > > Anyway, if you are bypassing the parity build with --assume-clean then how > can you expect it to work with a failed disk? That was my first thought too, but it doesn't actually follow. With only 3 devices, every write will construct new correct parity, so every block that was actually written will read back with the correct data after a device failure. There must be something going wrong in the xor calculations. NeilBrown -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
