On Mon, 2013-08-26 at 22:14 -0600, Scott Hallowell wrote: > Nicholas, > > > > > To confirm, when you enable buffered FILEIO, your able to reach > > comparable results with Samba, right..? > > > > I got much closer to my Samba results, yes. > > > If your able to switch backends and reach 1 Gb/sec performance, that > > would tend to indicate that it's something specific to the backend, and > > not an iscsi fabric specific issue. > > > >> The NAS I am comparing against, which is performing surprisingly well, > >> is also set up to use iblock. > > > > Please share what NAS and the version of LIO that it's using for > > comparison. (eg: cat /sys/kernel/config/target/version) > > > > The Commerical NAS I have to compare against is a Synology DS1511+. > It has a hardware configuration that is quite close the the system I > am working on. The version string: > > Target Engine Core ConfigFS Infrastructure v3.4.0 on Linux/x86_64 on 3.2.30 > It's my understanding that Synology is caching all of their writes to the backend, which explains the difference between different MD raid backends. > The version I am running: > > Target Engine Core ConfigFS Infrastructure v4.1.0-rc-m1 on > Linux/x86_64 on 3.2.0-4-amd64 > > > It depends on a number of things. One is the physical queue depth for > > each of the drives in the software raid. Typical low end HBAs only > > support queue_depth=1, which certainly has an effect on performance. > > This value is located at /sys/class/scsi_device/$HCTL/device_queue_depth > > > > Another factor can be if the individual drives in the raid have the > > underlying WriteCacheEnable bit set. This can be checked with 'sdparm > > --get=WCE /dev/SDX', and set with 'sdparm --set=WCE /dev/sdX'. > > > > Also, you'll want to understand the implications of using this, which is > > that in case of a power failure there is no assurance the data in the > > individual drive's cache has been written out to disk. > > > > I confirmed WCE is set on all disks in the raid array. I also turned > on NCQ, setting queue_depth to 31. It made a small improvement (about > 5%). > > > Since you've already eliminated a different default_cmdsn_depth value, > > it's likely not going to be a iscsi-target issue. It's most likely an > > issue of one of the software RAID configurations being faster for non > > buffered IO. > > > > The best test I have to look at this would be to do a dd direct to the > volume, to the raid array, and directly to the disks and compare those > values to the copy from the windows system. I'll give that a shot > tomorrow. > dd is a pretty crummy test. I'd recommend using fio instead. --nab -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
