Hi, I've configured a dm logical volume with thin provisioning using a single md device which is configured as a 3-drive RAID-10 (aka RAID1e, I think) array in the default "near" configuration. My chunk size is the default 64k. And the fs is to use the default 4k blocks. There are 3 devices + 1 spare. I've used this command to format it as ext4: mkfs.ext4 -E stride=16 -E stripe-width=48 /dev/VolumeGroup/VolumeName I'm seeing poor performance on writes. Only about 43MB/sec in bonnie++. By comparison, formatting XFS without specifying a stride or stripe-width gets me 83MB/s. (My understanding is that XFS autoconfigures the values when running on md/lvm2. It that correct?) Am I doing something wrong when I format the ext4 fs? Thanks for any guidance. -Steve Bergman -- 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
