Hi Eric, Do you have find any clue about slow random write iops ? I'm doing some benchmark from a kvm guest with fio, random 4K block, fio --filename=$DISK --direct=1 --rw=randwrite --bs=4k --size=200G --numjobs=50 --runtime=90 --group_reporting --name=file1 journal is on tmpfs and storage is 15k drive I can't have more than 1000-2000 iops. I Don't understand why I don't have a lot more iops. If journal is on tmpfs, it should be around 30000iops on a gigabit link (using all the bandwith) I also try use rbd_caching on my kvm guest, didn't change nothing. sequential write with 4MB block can use the full the gigabit link (around 100MB/S) Is the bottleneck the in rbd protocol ? ----- Mail original ----- De: "Eric YH Chen" <Eric_YH_Chen@xxxxxxxxxx> À: "mark nelson" <mark.nelson@xxxxxxxxxxx> Cc: ceph-devel@xxxxxxxxxxxxxxx, "Chris YT Huang" <Chris_YT_Huang@xxxxxxxxxx>, "Victor CY Chang" <Victor_CY_Chang@xxxxxxxxxx> Envoyé: Jeudi 14 Juin 2012 03:26:12 Objet: RE: Performance benchmark of rbd Hi, Mark: I forget to mention one thing, I create the rbd at the same machine and test it. That means the network latency may be lower than normal case. 1. I use ext4 as the backend filesystem and with following attribute. data=writeback,noatime,nodiratime,user_xattr 2. I use the default replication number, I think it is 2, right? 3. On my platform, I have 192GB memory 4. Sorry about the column name is left-right reversal. Here is the correct one Seq-write Seq-read 32 KB 23 MB/s 690 MB/s 512 KB 26 MB/s 960 MB/s 4 MB 27 MB/s 1290 MB/s 32 MB 36 MB/s 1435 MB/s 5. If I put all the journal data on a SSD device (Intel 520). The sequence write performance would reach 135MB/s instead of 27MB/s in original. (object size = 4MB). And others are no different, including random-write. I am curious why the SSD device doesn't help the performance of random-write. 6. For the random read write, the data I provided before was correct. But I can give you the detail. Is it too high than what you expected? rand-write-4k rand-write-16k bw iops bw iops 3,524 881 9,032 564 mix-4k (50/50) r:bw r:iops w:bw w:iops 2,925 731 2,924 731 mix-8k (50/50) r:bw r:iops w:bw w:iops 4,509 563 4,509 563 mix-16k (50/50) r:bw r:iops w:bw w:iops 8,366 522 8,345 521 7. Here is the hw raid cache policy we used now. Write Policy Write Back with BBU Read Policy ReadAhead If you are interested in how HW raid help the performance, I can do for little help, since we also want to know what is the best configuration on our platform. Any test you want to know? Furthermore, is there any suggestion for our platform that can improve the performance? Thanks! -----Original Message----- From: Mark Nelson [mailto:mark.nelson@xxxxxxxxxxx] Sent: Wednesday, June 13, 2012 8:30 PM To: Eric YH Chen/WYHQ/Wiwynn Cc: ceph-devel@xxxxxxxxxxxxxxx Subject: Re: Performance benchmark of rbd Hi Eric! On 6/13/12 5:06 AM, Eric_YH_Chen@xxxxxxxxxx wrote: > Hi, all: > > I am doing some benchmark of rbd. > The platform is on a NAS storage. > > CPU: Intel E5640 2.67GHz > Memory: 192 GB > Hard Disk: SATA 250G * 1, 7200 rpm (H0) + SATA 1T * 12 , 7200rpm > (H1~ H12) > RAID Card: LSI 9260-4i > OS: Ubuntu12.04 with Kernel 3.2.0-24 > Network: 1 Gb/s > > We create 12 OSD on H1 ~ H12 with the journal is put on H0. Just to make sure I understand, you have a single node with 12 OSDs and 3 mons, and all 12 OSDs are using the H0 disk for their journals? What filesystem are you using for the OSDs? How much replication? > We also create 3 MON in the cluster. > In briefly, we setup a ceph cluster all-in-one, with 3 monitors and > 12 OSD. > > The benchmark tool we used is fio 2.0.3. We had 7 basic test case > 1) sequence write with bs=64k > 2) sequence read with bs=64k > 3) random write with bs=4k > 4) random write with bs=16k > 5) mix read/write with bs=4k > 6) mix read/write with bs=8k > 7) mix read/write with bs=16k > > We create several rbd with different object size for the benchmark. > > 1. size = 20G, object size = 32KB > 2. size = 20G, object size = 512KB > 3. size = 20G, object size = 4MB > 4. size = 20G, object size = 32MB Given how much memory you have, you may want to increase the amount of data you are writing during each test to rule out caching. > > We have some conclusion after the benchmark. > > a. We can get better performance of sequence read/write when the > object size is bigger. > Seq-read Seq-write > 32 KB 23 MB/s 690 MB/s > 512 KB 26 MB/s 960 MB/s > 4 MB 27 MB/s 1290 MB/s > 32 MB 36 MB/s 1435 MB/s Which test are these results from? I'm suspicious that the write numbers are so high. Figure that even with a local client and 1X replication, your journals and data partitions are each writing out a copy of the data. You don't have enough disk in that box to sustain 1.4GB/s to both even under perfectly ideal conditions. Given that it sounds like you are using a single 7200rpm disk for 12 journals, I would expect far lower numbers... > > b. There is no obvious influence for random read/write when the > object size is different. > All the result are in a range not more than 10%. > > rand-write-4K rand-write-16K mix-4K > mix-8k mix-16k > 881 iops 564 iops > 1462 iops 1127 iops 1044 iops > > c. It we change the environment, for every 3 hard drive, we bind > them together by RAID0. (LSI 9260-4i RAID card) > So the ceph cluster becomes 3 MONs and 4 OSD (3T for each) > We can get better performance on all items, around 10% ~ 20% > enhancement. Those IOPs numbers are more what I would expect. Using HW raid0 may provide some benefit depending on the number of OSDs per node. It's something we haven't had time to look at yet in detail, but is on our list. > > d. If we change H0 to a SSD device, and we also put all journal > on it. We can get better performance on sequence-write. > It would reach 135MB/s. However, there are no different for other > test items. > > We want to check with you, if all the conclusion are reasonable for > you? Or any seems strange? Thanks! When you say that using an SSD device increases the sequence-write speeds to 135MB/s, what are you comparing that to? Incidentally that level of performance is entirely believable with 12 OSDs sharing a single SSD for journals. The write results with the 7200rpm journal disk do look strange to me, but it's tough to say what's going on. If the numbers are accurate, I'd say writes aren't getting to the disks. If they are mislabeled (IE 1.435MB/s or 1435Mb/s instead 1435MB/s), then things are more believable and I'd try putting your journals on a small partition on each disk (causes some extra seek behavior and lower OSD throughput, but better than stacking the journals up on a single slow disk). > > ==== > > Here is some data if I use command provided by rados. > rados -p rbd bench 120 write -t 8 > > Total time run: 120.751713 > Total writes made: 930 > Write size: 4194304 > Bandwidth (MB/sec): 30.807 > > Average Latency: 1.03807 > Max latency: 2.63197 > Min latency: 0.205726 > > [INF] bench: wrote 1024 MB in blocks of 4096 KB in 13.219819 sec > at 79318 KB/sec That looks much closer to what I would expect if you have 12 journals all sharing a single 7200rpm drive. > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html Mark -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html -- -- Alexandre D e rumier Ingénieur Systèmes et Réseaux Fixe : 03 20 68 88 85 Fax : 03 20 68 90 88 45 Bvd du Général Leclerc 59100 Roubaix 12 rue Marivaux 75002 Paris -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
