[sheepdog-users] Corosync Vs. Zookeeper
Aydelott, Ryan M.
ryade at mcs.anl.gov
Tue Mar 18 20:02:57 CET 2014
re: syntax of /meta and /meta, - thanks for the pointer we started using all of the disks for objects - rerunning the performance tests however yielded the same results - are there any other suggestions here?
Node 0..19:
0 13 GB 24 MB 13 GB 0% /meta/obj
to:
Node 0..19:
0 446 GB 0.0 MB 446 GB 0% /var/lib/sheepdog/disc0
1 443 GB 0.0 MB 443 GB 0% /var/lib/sheepdog/disc1
2 449 GB 104 MB 448 GB 0% /var/lib/sheepdog/disc10
3 441 GB 0.0 MB 441 GB 0% /var/lib/sheepdog/disc11
4 445 GB 0.0 MB 445 GB 0% /var/lib/sheepdog/disc12
5 441 GB 0.0 MB 441 GB 0% /var/lib/sheepdog/disc13
6 448 GB 0.0 MB 448 GB 0% /var/lib/sheepdog/disc2
7 449 GB 0.0 MB 449 GB 0% /var/lib/sheepdog/disc3
8 445 GB 0.0 MB 445 GB 0% /var/lib/sheepdog/disc4
9 457 MB 0.0 MB 457 MB 0% /var/lib/sheepdog/disc6
10 445 GB 0.0 MB 445 GB 0% /var/lib/sheepdog/disc7
11 440 GB 0.0 MB 440 GB 0% /var/lib/sheepdog/disc8
12 450 GB 0.0 MB 450 GB 0% /var/lib/sheepdog/disc9
However it should be noted that the process is still listed as meta with the space (which is probably what caused me to deviate in the first place)
2093 ? Sl 0:46 sheep -n -c corosync:172.21.5.0 /meta /var/lib/sheepdog/disc0,/var/lib/sheepdog/disc1,/var/lib/sheepdog/disc2,/var/lib/sheepdog/disc3,/var/lib/sheepdog/disc4,/var/lib/sheepdog/disc5,/var/lib/sheepdog/disc6,/var/lib/sheepdog/disc7,/var/lib/sheepdog/disc8,/var/lib/sheepdog/disc9,/var/lib/sheepdog/disc10,/var/lib/sheepdog/disc11,/var/lib/sheepdog/disc12,/var/lib/sheepdog/disc13
2094 ? Ss 0:00 sheep -n -c corosync:172.21.5.0 /meta /var/lib/sheepdog/disc0,/var/lib/sheepdog/disc1,/var/lib/sheepdog/disc2,/var/lib/sheepdog/disc3,/var/lib/sheepdog/disc4,/var/lib/sheepdog/disc5,/var/lib/sheepdog/disc6,/var/lib/sheepdog/disc7,/var/lib/sheepdog/disc8,/var/lib/sheepdog/disc9,/var/lib/sheepdog/disc10,/var/lib/sheepdog/disc11,/var/lib/sheepdog/disc12,/var/lib/sheepdog/disc13
rerunning the tests show that the performance is still the same with zookeeper:
Run began: Tue Mar 18 18:32:40 2014
Record Size 128 KB
File size set to 20971520 KB
Command line used: iozone -i0 -i1 -t 1 -r 128#k -s 20G
Output is in Kbytes/sec
Time Resolution = 0.000001 seconds.
Processor cache size set to 1024 Kbytes.
Processor cache line size set to 32 bytes.
File stride size set to 17 * record size.
Throughput test with 1 process
Each process writes a 20971520 Kbyte file in 128 Kbyte records
Children see throughput for 1 initial writers = 41336.98 KB/sec
Parent sees throughput for 1 initial writers = 39010.99 KB/sec
Min throughput per process = 41336.98 KB/sec
Max throughput per process = 41336.98 KB/sec
Avg throughput per process = 41336.98 KB/sec
Min xfer = 20971520.00 KB
Children see throughput for 1 rewriters = 43703.66 KB/sec
Parent sees throughput for 1 rewriters = 41149.12 KB/sec
Min throughput per process = 43703.66 KB/sec
Max throughput per process = 43703.66 KB/sec
Avg throughput per process = 43703.66 KB/sec
Min xfer = 20971520.00 KB
Children see throughput for 1 readers = 63503.92 KB/sec
Parent sees throughput for 1 readers = 63502.66 KB/sec
Min throughput per process = 63503.92 KB/sec
Max throughput per process = 63503.92 KB/sec
Avg throughput per process = 63503.92 KB/sec
Min xfer = 20971520.00 KB
Children see throughput for 1 re-readers = 63532.20 KB/sec
Parent sees throughput for 1 re-readers = 63531.88 KB/sec
Min throughput per process = 63532.20 KB/sec
Max throughput per process = 63532.20 KB/sec
Avg throughput per process = 63532.20 KB/sec
Min xfer = 20971520.00 KB
iozone test complete.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 841 bytes
Desc: Message signed with OpenPGP using GPGMail
URL: <http://lists.wpkg.org/pipermail/sheepdog-users/attachments/20140318/400ec867/attachment-0002.sig>
More information about the sheepdog-users
mailing list