Hi!
Of course, it isn't cheap at all, but we use Intel DC S3700 200Gb for ceph journals
and DC S3700 400Gb in the SSD pool: same hosts, separate root in crushmap.
SSD pool are not yet in production, journаlling SSDs works under production load
for 10 months. They're in good condition - no faults, no degradation.
We specially take 200Gb SSD for journals to reduce costs, and also have a higher
than recommended OSD/SSD ratio: 1 SSD per 10-12 ODS, whille recommended
1/3 to 1/6.
So, as a conclusion - I'll recommend you to get a bigger budget and buy durable
and fast SSDs for Ceph.
Megov Igor
CIO, Yuterra
Of course, it isn't cheap at all, but we use Intel DC S3700 200Gb for ceph journals
and DC S3700 400Gb in the SSD pool: same hosts, separate root in crushmap.
SSD pool are not yet in production, journаlling SSDs works under production load
for 10 months. They're in good condition - no faults, no degradation.
We specially take 200Gb SSD for journals to reduce costs, and also have a higher
than recommended OSD/SSD ratio: 1 SSD per 10-12 ODS, whille recommended
1/3 to 1/6.
So, as a conclusion - I'll recommend you to get a bigger budget and buy durable
and fast SSDs for Ceph.
Megov Igor
CIO, Yuterra
От: ceph-users <ceph-users-bounces@xxxxxxxxxxxxxx> от имени Voloshanenko Igor <igor.voloshanenko@xxxxxxxxx>
Отправлено: 13 августа 2015 г. 15:54
Кому: Jan Schermer
Копия: ceph-users@xxxxxxxxxxxxxx
Тема: Re: CEPH cache layer. Very slow
Отправлено: 13 августа 2015 г. 15:54
Кому: Jan Schermer
Копия: ceph-users@xxxxxxxxxxxxxx
Тема: Re: CEPH cache layer. Very slow
So, good, but price for 845 DC PRO 400 GB higher in about 2x times than intel S3500 240G (((
Any other models? (((
2015-08-13 15:45 GMT+03:00 Jan Schermer
<jan@xxxxxxxxxxx>:
I tested and can recommend the Samsung 845 DC PRO (make sure it is DC PRO and not just "PRO" or "DC EVO"!).Those were very cheap but are out of stock at the moment (here).Faster than Intels, cheaper, and slightly different technology (3D V-NAND) which IMO makes them superior without needing many tricks to do its job.
Jan
On 13 Aug 2015, at 14:40, Voloshanenko Igor <igor.voloshanenko@xxxxxxxxx> wrote:
Tnx, Irek! Will try!
but another question to all, which SSD good enough for CEPH now?
I'm looking into S3500 240G (I have some S3500 120G which show great results. Around 8x times better than Samsung)
Possible you can give advice about other vendors/models with same or below price level as S3500 240G?_______________________________________________
2015-08-13 12:11 GMT+03:00 Irek Fasikhov <malmyzh@xxxxxxxxx>:
Hi, Igor.Try to roll the patch here:
P.S. I am no longer tracks changes in this direction(kernel), because we use already recommended SSD
С уважением, Фасихов Ирек НургаязовичМоб.: +79229045757
2015-08-13 11:56 GMT+03:00 Voloshanenko Igor <igor.voloshanenko@xxxxxxxxx>:
So, after testing SSD (i wipe 1 SSD, and used it for tests)
root@ix-s2:~# sudo fio --filename=/dev/sda --direct=1 --sync=1 --rw=write --bs=4k --numjobs=1 --iodepth=1 --runtime=60 --time_based --gr[53/1800]ting --name=journal-testjournal-test: (g=0): rw=write, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=1fio-2.1.3Starting 1 processJobs: 1 (f=1): [W] [100.0% done] [0KB/1152KB/0KB /s] [0/288/0 iops] [eta 00m:00s]journal-test: (groupid=0, jobs=1): err= 0: pid=2849460: Thu Aug 13 10:46:42 2015write: io=68972KB, bw=1149.6KB/s, iops=287, runt= 60001msecclat (msec): min=2, max=15, avg= 3.48, stdev= 1.08lat (msec): min=2, max=15, avg= 3.48, stdev= 1.08clat percentiles (usec):| 1.00th=[ 2704], 5.00th=[ 2800], 10.00th=[ 2864], 20.00th=[ 2928],| 30.00th=[ 3024], 40.00th=[ 3088], 50.00th=[ 3280], 60.00th=[ 3408],| 70.00th=[ 3504], 80.00th=[ 3728], 90.00th=[ 3856], 95.00th=[ 4016],| 99.00th=[ 9024], 99.50th=[ 9280], 99.90th=[ 9792], 99.95th=[10048],| 99.99th=[14912]bw (KB /s): min= 1064, max= 1213, per=100.00%, avg=1150.07, stdev=34.31lat (msec) : 4=94.99%, 10=4.96%, 20=0.05%cpu : usr=0.13%, sys=0.57%, ctx=17248, majf=0, minf=7IO depths : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%issued : total=r=0/w=17243/d=0, short=r=0/w=0/d=0
Run status group 0 (all jobs):WRITE: io=68972KB, aggrb=1149KB/s, minb=1149KB/s, maxb=1149KB/s, mint=60001msec, maxt=60001msec
Disk stats (read/write):sda: ios=0/17224, merge=0/0, ticks=0/59584, in_queue=59576, util=99.30%
So, it's pain... SSD do only 287 iops on 4K... 1,1 MB/s
I try to change cache mode :echo temporary write through > /sys/class/scsi_disk/2:0:0:0/cache_typeecho temporary write through > /sys/class/scsi_disk/3:0:0:0/cache_type
no luck, still same shit results, also i found this article:https://lkml.org/lkml/2013/11/20/264 pointed to old very simple patch, which disable CMD_FLUSH
Has everybody better ideas, how to improve this? (or disable CMD_FLUSH without recompile kernel, i used ubuntu and 4.0.4 for now (4.x branch because SSD 850 Pro have issue with NCQ TRIM< and before 4.0.4 this exception was not included into libsata.c)
2015-08-12 19:17 GMT+03:00 Pieter Koorts <pieter.koorts@xxxxxx>:
Hi Igor
I suspect you have very much the same problem as me.
Basically Samsung drives (like many SATA SSD's) are very much hit and miss so you will need to test them like described here to see if they are any good. http://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/
To give you an idea my average performance went from 11MB/s (with Samsung SSD) to 30MB/s (without any SSD) on write performance. This is a very small cluster.
PieterHi all, we have setup CEPH cluster with 60 OSD (2 diff types) (5 nodes, 12 disks on each, 10 HDD, 2 SSD)
Also we cover this with custom crushmap with 2 root leaf
ID WEIGHT TYPE NAME UP/DOWN REWEIGHT PRIMARY-AFFINITY-100 5.00000 root ssd-102 1.00000 host ix-s2-ssd2 1.00000 osd.2 up 1.00000 1.000009 1.00000 osd.9 up 1.00000 1.00000-103 1.00000 host ix-s3-ssd3 1.00000 osd.3 up 1.00000 1.000007 1.00000 osd.7 up 1.00000 1.00000-104 1.00000 host ix-s5-ssd1 1.00000 osd.1 up 1.00000 1.000006 1.00000 osd.6 up 1.00000 1.00000-105 1.00000 host ix-s6-ssd4 1.00000 osd.4 up 1.00000 1.000008 1.00000 osd.8 up 1.00000 1.00000-106 1.00000 host ix-s7-ssd0 1.00000 osd.0 up 1.00000 1.000005 1.00000 osd.5 up 1.00000 1.00000-1 5.00000 root platter-2 1.00000 host ix-s2-platter13 1.00000 osd.13 up 1.00000 1.0000017 1.00000 osd.17 up 1.00000 1.0000021 1.00000 osd.21 up 1.00000 1.0000027 1.00000 osd.27 up 1.00000 1.0000032 1.00000 osd.32 up 1.00000 1.0000037 1.00000 osd.37 up 1.00000 1.0000044 1.00000 osd.44 up 1.00000 1.0000048 1.00000 osd.48 up 1.00000 1.0000055 1.00000 osd.55 up 1.00000 1.0000059 1.00000 osd.59 up 1.00000 1.00000-3 1.00000 host ix-s3-platter14 1.00000 osd.14 up 1.00000 1.0000018 1.00000 osd.18 up 1.00000 1.0000023 1.00000 osd.23 up 1.00000 1.0000028 1.00000 osd.28 up 1.00000 1.0000033 1.00000 osd.33 up 1.00000 1.0000039 1.00000 osd.39 up 1.00000 1.0000043 1.00000 osd.43 up 1.00000 1.0000047 1.00000 osd.47 up 1.00000 1.0000054 1.00000 osd.54 up 1.00000 1.0000058 1.00000 osd.58 up 1.00000 1.00000-4 1.00000 host ix-s5-platter11 1.00000 osd.11 up 1.00000 1.0000016 1.00000 osd.16 up 1.00000 1.0000022 1.00000 osd.22 up 1.00000 1.0000026 1.00000 osd.26 up 1.00000 1.0000031 1.00000 osd.31 up 1.00000 1.0000036 1.00000 osd.36 up 1.00000 1.0000041 1.00000 osd.41 up 1.00000 1.0000046 1.00000 osd.46 up 1.00000 1.0000051 1.00000 osd.51 up 1.00000 1.0000056 1.00000 osd.56 up 1.00000 1.00000-5 1.00000 host ix-s6-platter12 1.00000 osd.12 up 1.00000 1.0000019 1.00000 osd.19 up 1.00000 1.0000024 1.00000 osd.24 up 1.00000 1.0000029 1.00000 osd.29 up 1.00000 1.0000034 1.00000 osd.34 up 1.00000 1.0000038 1.00000 osd.38 up 1.00000 1.0000042 1.00000 osd.42 up 1.00000 1.0000050 1.00000 osd.50 up 1.00000 1.0000053 1.00000 osd.53 up 1.00000 1.0000057 1.00000 osd.57 up 1.00000 1.00000-6 1.00000 host ix-s7-platter10 1.00000 osd.10 up 1.00000 1.0000015 1.00000 osd.15 up 1.00000 1.0000020 1.00000 osd.20 up 1.00000 1.0000025 1.00000 osd.25 up 1.00000 1.0000030 1.00000 osd.30 up 1.00000 1.0000035 1.00000 osd.35 up 1.00000 1.0000040 1.00000 osd.40 up 1.00000 1.0000045 1.00000 osd.45 up 1.00000 1.0000049 1.00000 osd.49 up 1.00000 1.0000052 1.00000 osd.52 up 1.00000 1.00000
Then create 2 pools, 1 on HDD (platters), 1 on SSD/and put SSD pul in from of HDD pool (cache tier)
now we receive very bad performance results from cluster.Even with rados bench we received very unstable performance with even zero speed. So it's create very big issues for our clients.
I try to tune all possible values, including OSD, but still no luck.
Also very unbelievble situation, when i doceph tell... bench on SSD OSD - i receive about 20MB/sIf for HDD - 67 MB/s...
I don;t understand why cache pools which consist of SSD works so bad... We used Samsung 850 Pro 256 Gb as SSDs
Can you guys give me advice please...
Also very idiotic thing, when i set cache-mode to forward and try to flush-evict all object (not all object evicted, some busy (locked on KVM sides). but now i receive quite stable results for rados bench
Total time run: 30.275871Total writes made: 2076Write size: 4194304Bandwidth (MB/sec): 274.278
Stddev Bandwidth: 75.1445Max bandwidth (MB/sec): 368Min bandwidth (MB/sec): 0Average Latency: 0.232892Stddev Latency: 0.240356Max latency: 2.01436Min latency: 0.0716344
Without zeros, etc... So i don't understand how it's possible.
Also interesting thing, when i disable overlay for pool, rados bench become around 70MB/s as for ordinary HDD, but in same time rados bench for SSD pool, which not used anymore show same bad results...
So please, give me some direction to deeg...
_______________________________________________
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
