On Tue, 5 Jul 2016 10:22:37 +0200 Dan van der Ster wrote: > On Tue, Jul 5, 2016 at 10:04 AM, Dan van der Ster <dan@xxxxxxxxxxxxxx> > wrote: > > On Tue, Jul 5, 2016 at 9:53 AM, Christian Balzer <chibi@xxxxxxx> wrote: > >>> Unfamiliar: Samsung SM863 > >>> > >> You might want to read the thread here: > >> http://lists.ceph.com/pipermail/ceph-users-ceph.com/2016-February/007871.html > >> > >> And google "ceph SM863". > >> > >> However I'm still waiting for somebody to confirm that these perform > >> (as one would expect from DC level SSDs) at full speed with sync > >> writes, which is the only important factor for journals. > > > > Tell me the fio options you're interested in and I'll run it right now. > > Using the options from Sebastien's blog I get: > > 1 job: write: io=5863.3MB, bw=100065KB/s, iops=25016, runt= 60001msec > 5 jobs: write: io=11967MB, bw=204230KB/s, iops=51057, runt= 60001msec > 10 jobs: write: io=13760MB, bw=234829KB/s, iops=58707, runt= 60001msec > > Drive is model MZ7KM240 with firmware GXM1003Q. > That looks good enough, but looking at those numbers and what is reported on the page here: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/ and my experiences with DC S3700 (100/200GB), DC S3710 (200GB) and DC S3610s (800GB) I'm more than slightly inclined to distrust the results there or at least the methodology. As in, was the same HW (CPU. controller, etc) used? Doubt it. For example the 200GB DC S3700 used for Ceph journals can write close write over 300MB/s (verified with iostat/atop) sustained, out of 365MB/s per the specification. The model of the SM863 you have there should do 485MB/s according to Samsung, so I'd expect it to do around 400MB/s if on par with the Intels. You can probably guestimate that easily by looking at the machines you have them deployed in with atop/iostat by extrapolating the top speed from the MB/s and util%. Christian > -- > Dan > > > [1] fio --filename=/dev/sdc --direct=1 --sync=1 --rw=write --bs=4k > --numjobs=1 --iodepth=1 --runtime=60 --time_based --group_reporting > --name=journal-test > -- Christian Balzer Network/Systems Engineer chibi@xxxxxxx Global OnLine Japan/Rakuten Communications http://www.gol.com/ _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |