[Gluster-users] Re :Performance of GlusterFs and NFS
Keith Freedman
freedman at FreeFormIT.com
Mon Jan 12 13:27:04 UTC 2009
check back to some of the previous messages in this list about performance.
also, which version of Gluster you use makes a difference.
As for smaller block sizes being a performance issue, I think mostly
fuse is the problem with small block sizes.
I think 4K is what fuse' block size is? SO I'm thinking that should
be ok for testing.
I also believe gluster 2.0 is much faster with smaller files than
1.3, so you should get better results with 2.0
if you benchmarked with 1.3, please try again with 2.0 and let us
know your results.
At 02:09 AM 1/12/2009, mohan L wrote:
>Dear All,
>
>I am benchmarking NFS and GlusterFS . I running Iozone in multi
>thread mode .from the test conclued that GlusterFS performs better
>then NFS in single server and single client at file size 100MB. Any
>commant and Idea . Is it correct? .Here I am using file size 100MB
>and 128 KB record size .In 100 MB file size GlusterFS performs
>better then NFS . but when I am testing 128 KB file size and 4KB
>record size ,in this case NFS performs better then GlusterFS .what
>is the reson for that? GlusterFS will perform better only in case
>of large file size ?
>
>
>===============================================
>NFS Performance in Iozone Thread mode:
>
>[root at localhost nfs]# iozone -R -t 5 -r 128K -s 100M +-n -i 0 -i 1
> Iozone: Performance Test of File I/O
> Version $Revision: 3.239 $
> Compiled for 32 bit mode.
> Build: linux
>
> Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
> Al Slater, Scott Rhine, Mike Wisner, Ken Goss
> Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
> Randy Dunlap, Mark Montague, Dan Million,
> Jean-Marc Zucconi, Jeff Blomberg,
> Erik Habbinga, Kris Strecker, Walter Wong.
>
> Run began: Mon Jan 12 20:29:37 2009
>
> Excel chart generation enabled
> Record Size 128 KB
> File size set to 102400 KB
> Command line used: iozone -R -t 5 -r 128K -s 100M -i 0 -i 1 +-n
> 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 5 processes
> Each process writes a 102400 Kbyte file in 128 Kbyte records
>
> Children see throughput for 5 initial writers = 9269.31 KB/sec
> Parent sees throughput for 5 initial writers = 8506.71 KB/sec
> Min throughput per process = 1802.63 KB/sec
> Max throughput per process = 1914.05 KB/sec
> Avg throughput per process = 1853.86 KB/sec
> Min xfer = 96384.00 KB
>
> Children see throughput for 5 rewriters = 7869.36 KB/sec
> Parent sees throughput for 5 rewriters = 7533.62 KB/sec
> Min throughput per process = 1499.05 KB/sec
> Max throughput per process = 1650.54 KB/sec
> Avg throughput per process = 1573.87 KB/sec
> Min xfer = 93312.00 KB
>
> Children see throughput for 5 readers = 8779.71 KB/sec
> Parent sees throughput for 5 readers = 8753.18 KB/sec
> Min throughput per process = 1741.74 KB/sec
> Max throughput per process = 1781.11 KB/sec
> Avg throughput per process = 1755.94 KB/sec
> Min xfer = 100608.00 KB
>
> Children see throughput for 5 re-readers = 8785.78 KB/sec
> Parent sees throughput for 5 re-readers = 8765.13 KB/sec
> Min throughput per process = 1732.58 KB/sec
> Max throughput per process = 1788.77 KB/sec
> Avg throughput per process = 1757.16 KB/sec
> Min xfer = 99584.00 KB
>
>
>
>"Throughput report Y-axis is type of test X-axis is number of processes"
>"Record size = 128 Kbytes "
>"Output is in Kbytes/sec"
>
>" Initial write " 9269.31
>
>" Rewrite " 7869.36
>
>" Read " 8779.71
>
>" Re-read " 8785.78
>
>
>iozone test complete.
>
>
>======================================================
>GlusterFS performance in Iozone Tread mode :
>
>[root at localhost glusterfs]# iozone -R -t 5 -r 128K -s 100M +-n -i 0 -i 1
> Iozone: Performance Test of File I/O
> Version $Revision: 3.239 $
> Compiled for 32 bit mode.
> Build: linux
>
> Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
> Al Slater, Scott Rhine, Mike Wisner, Ken Goss
> Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
> Randy Dunlap, Mark Montague, Dan Million,
> Jean-Marc Zucconi, Jeff Blomberg,
> Erik Habbinga, Kris Strecker, Walter Wong.
>
> Run began: Mon Jan 12 20:35:56 2009
>
> Excel chart generation enabled
> Record Size 128 KB
> File size set to 102400 KB
> Command line used: iozone -R -t 5 -r 128K -s 100M -i 0 -i 1 +-n
> 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 5 processes
> Each process writes a 102400 Kbyte file in 128 Kbyte records
>
> Children see throughput for 5 initial writers = 11305.49 KB/sec
> Parent sees throughput for 5 initial writers = 10658.86 KB/sec
> Min throughput per process = 2113.47 KB/sec
> Max throughput per process = 2320.99 KB/sec
> Avg throughput per process = 2261.10 KB/sec
> Min xfer = 93312.00 KB
>
> Children see throughput for 5 rewriters = 10245.67 KB/sec
> Parent sees throughput for 5 rewriters = 10052.28 KB/sec
> Min throughput per process = 1984.79 KB/sec
> Max throughput per process = 2150.17 KB/sec
> Avg throughput per process = 2049.13 KB/sec
> Min xfer = 94592.00 KB
>
> Children see throughput for 5 readers = 10172.49 KB/sec
> Parent sees throughput for 5 readers = 10124.65 KB/sec
> Min throughput per process = 1128.39 KB/sec
> Max throughput per process = 2271.28 KB/sec
> Avg throughput per process = 2034.50 KB/sec
> Min xfer = 51072.00 KB
>
> Children see throughput for 5 re-readers = 10253.22 KB/sec
> Parent sees throughput for 5 re-readers = 10193.55 KB/sec
> Min throughput per process = 1137.78 KB/sec
> Max throughput per process = 2290.00 KB/sec
> Avg throughput per process = 2050.64 KB/sec
> Min xfer = 51072.00 KB
>
>
>
>"Throughput report Y-axis is type of test X-axis is number of processes"
>"Record size = 128 Kbytes "
>"Output is in Kbytes/sec"
>
>" Initial write " 11305.49
>
>" Rewrite " 10245.67
>
>" Read " 10172.49
>
>" Re-read " 10253.22
>
>
>iozone test complete.
>
>Thanks for your time .
>
>Thanks
>L.Mohan
>
>
>
>_______________________________________________
>Gluster-users mailing list
>Gluster-users at gluster.org
>http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
More information about the Gluster-users
mailing list