Apologies for the top post, I can't seem to break indents on my phone. Anyway the point of that test was as maged suggests to show the effect of serial CPU speed on latency. IO is effectively serialised by the pg lock, and so trying to reduce the time spent in this area is key. Fast cpu, fast network and fast journals are the key here.
This is particularly important on either databases where the small log area which may only occupy a small number of pgs can cause contention. Similar to xfs journal as well. Higher queue depths will start to show similar behaviour if you go high enough and start waiting for pgs to unlock. Further tests on proper hardware and 3x replication over network have shown average latency figures of around 600us for qd1. ________________________________ From: Maged Mokhtar <[email protected]> Sent: 24 Jun 2017 1:17 p.m. To: Willem Jan Withagen Cc: Ceph Users Subject: Re: [ceph-users] Ceph random read IOPS > My understanding was this test is targeting latency more than IOPS. This is > probably why its was run using QD=1. It also makes sense that cpu freq will > be more important than cores. > > > > > On 2017-06-24 12:52, Willem Jan Withagen wrote: >> >> On 24-6-2017 05:30, Christian Wuerdig wrote: >>> >>> The general advice floating around is that your want CPUs with high >>> clock speeds rather than more cores to reduce latency and increase IOPS >>> for SSD setups (see also >>> http://www.sys-pro.co.uk/ceph-storage-fast-cpus-ssd-performance/) So >>> something like a E5-2667V4 might bring better results in that situation. >>> Also there was some talk about disabling the processor C states in order >>> to bring latency down (something like this should be easy to test: >>> https://stackoverflow.com/a/22482722/220986) >> >> >> I would be very careful to call this a general advice... >> >> Although the article is interesting, it is rather single sided. >> >> The only thing is shows that there is a lineair relation between >> clockspeed and write or read speeds??? >> The article is rather vague on how and what is actually tested. >> >> By just running a single OSD with no replication a lot of the >> functionality is left out of the equation. >> Nobody is running just 1 osD on a box in a normal cluster host. >> >> Not using a serious SSD is another source of noise on the conclusion. >> More Queue depth can/will certainly have impact on concurrency. >> >> I would call this an observation, and nothing more. >> >> --WjW >>> >>> >>> On Sat, Jun 24, 2017 at 1:28 AM, Kostas Paraskevopoulos >>> <[email protected] <mailto:[email protected]>> wrote: >>> >>> Hello, >>> >>> We are in the process of evaluating the performance of a testing >>> cluster (3 nodes) with ceph jewel. Our setup consists of: >>> 3 monitors (VMs) >>> 2 physical servers each connected with 1 JBOD running Ubuntu Server >>> 16.04 >>> >>> Each server has 32 threads @2.1GHz and 128GB RAM. >>> The disk distribution per server is: >>> 38 * HUS726020ALS210 (SAS rotational) >>> 2 * HUSMH8010BSS200 (SAS SSD for journals) >>> 2 * ST1920FM0043 (SAS SSD for data) >>> 1 * INTEL SSDPEDME012T4 (NVME measured with fio ~300K iops) >>> >>> Since we don't currently have a 10Gbit switch, we test the performance >>> with the cluster in a degraded state, the noout flag set and we mount >>> rbd images on the powered on osd node. We confirmed that the network >>> is not saturated during the tests. >>> >>> We ran tests on the NVME disk and the pool created on this disk where >>> we hoped to get the most performance without getting limited by the >>> hardware specs since we have more disks than CPU threads. >>> >>> The nvme disk was at first partitioned with one partition and the >>> journal on the same disk. The performance on random 4K reads was >>> topped at 50K iops. We then removed the osd and partitioned with 4 >>> data partitions and 4 journals on the same disk. The performance >>> didn't increase significantly. Also, since we run read tests, the >>> journals shouldn't cause performance issues. >>> >>> We then ran 4 fio processes in parallel on the same rbd mounted image >>> and the total iops reached 100K. More parallel fio processes didn't >>> increase the measured iops. >>> >>> Our ceph.conf is pretty basic (debug is set to 0/0 for everything) and >>> the crushmap just defines the different buckets/rules for the disk >>> separation (rotational, ssd, nvme) in order to create the required >>> pools >>> >>> Is the performance of 100.000 iops for random 4K read normal for a >>> disk that on the same benchmark runs at more than 300K iops on the >>> same hardware or are we missing something? >>> >>> Best regards, >>> Kostas >>> _______________________________________________ >>> ceph-users mailing list >>> [email protected] <mailto:[email protected]> >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>> <http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com> >>> >>> >>> >>> >>> _______________________________________________ >>> ceph-users mailing list >>> [email protected] >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>> >> >> _______________________________________________ >> ceph-users mailing list >> [email protected] >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > >
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
