> Am 11.03.2015 um 11:17 schrieb Nick Fisk: > > > > > >> Hi Nick, > >> > >> Am 11.03.2015 um 10:52 schrieb Nick Fisk: > >>> Hi Stefan, > >>> > >>> If the majority of your hot data fits on the cache tier you will see > >>> quite a marked improvement in read performance > >> I don't have writes ;-) just around 5%. 95% are writes. > >> > >>> and similar write performance > >>> (assuming you would have had your hdds backed by SSD journals). > >> > >> similar write performance of SSD cache tier or HDD "backend" tier? > >> > >> I'm mainly interested in a writeback mode. > > > > Writes on Cache tiering are the same speed as a non cache tiering > > solution (with SSD journals), if the blocks are in the cache. > > > > > >> > >>> However for data that is not in the cache tier you will get 10-20% > >>> less read performance and anything up to 10x less write performance. > >>> This is because a cache write miss has to read the entire object > >>> from the backing store into the cache and then modify it. > >>> > >>> The read performance degradation will probably be fixed in Hammer > >>> with proxy reads, but writes will most likely still be an issue. > >> > >> Why is writing to the HOT part so slow? > >> > > > > If the object is in the cache tier or currently doesn't exist, then > > writes are fast as it just has to write directly to the cache tier > > SSD's. However if the object is in the slow tier and you write to it, then its > very slow. > > This is because it has to read it off the slow tier (~12ms), write it > > on to the cache tier(~.5ms) and then update it (~.5ms). > > Mhm sounds correct. So it's better to stuck with journals instead of using a > cache tier. That's purely down to your workload, but in general if you are doing lots of writes, a cache tier will probably slow you down at the moment. > > Stefan > > > > > With a non caching solution, you would have just written straight to > > the journal (~.5ms) > > > >> Stefan > >> > >>> Nick > >>> > >>> > >>>> -----Original Message----- > >>>> From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx] On > >>>> Behalf Of Stefan Priebe - Profihost AG > >>>> Sent: 11 March 2015 07:27 > >>>> To: ceph-users@xxxxxxxxxxxxxx > >>>> Subject: Firefly Tiering > >>>> > >>>> Hi, > >>>> > >>>> has anybody successfully tested tiering while using firefly? How > >>>> much does > >>> it > >>>> impact performance vs. a normal pool? I mean is there any > >>>> difference between a full SSD pool und a tiering SSD pool with SATA > Backend? > >>>> > >>>> Greets, > >>>> Stefan > >>>> _______________________________________________ > >>>> ceph-users mailing list > >>>> ceph-users@xxxxxxxxxxxxxx > >>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > >>> > >>> > >>> > >>> > >> _______________________________________________ > >> ceph-users mailing list > >> ceph-users@xxxxxxxxxxxxxx > >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > > > > > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |