Re: [ceph-users] Bluestore cluster, bad IO perf on blocksize<64k... could it be throttling ?

On 2018-03-21 19:50, Frederic BRET wrote: > Hi all, > > The context : > - Test cluster aside production one > - Fresh install on Luminous > - choice of Bluestore (coming from Filestore) > - Default config (including wpq queuing) > - 6 nodes SAS12, 14 OSD, 2 SSD, 2 x 10Gb nodes, far more Gb at

Re: [ceph-users] Bluestore cluster, bad IO perf on blocksize<64k... could it be throttling ?

On Wed, Mar 21, 2018 at 6:50 PM, Frederic BRET wrote: > Hi all, > > The context : > - Test cluster aside production one > - Fresh install on Luminous > - choice of Bluestore (coming from Filestore) > - Default config (including wpq queuing) > - 6 nodes SAS12, 14 OSD, 2

[ceph-users] Bluestore cluster, bad IO perf on blocksize<64k... could it be throttling ?

Hi all, We encounter bad IO perfs on blocksize<64k on our new Bluestore test cluster The context : - Test cluster aside production one - Fresh install on Luminous - choice of Bluestore (coming from Filestore) - Default config (including wpq queuing) - 6 nodes SAS12, 14 OSD, 2 SSD, 2 x 10Gb

[ceph-users] Bluestore cluster, bad IO perf on blocksize<64k... could it be throttling ?

Hi all, The context : - Test cluster aside production one - Fresh install on Luminous - choice of Bluestore (coming from Filestore) - Default config (including wpq queuing) - 6 nodes SAS12, 14 OSD, 2 SSD, 2 x 10Gb nodes, far more Gb at each switch uplink... - R3 pool, 2 nodes per site -