iozone results

iozone results

[doiggl]

iozone results
source info from http://www.citi.umich.edu/projects/asci/benchmarks.html

# iozone -ec -t 1 -r 4M -s 100M -+n -i 0 -i 1
        Iozone: Performance Test of File I/O
                Version $Revision: 3.300 $
                Compiled for 64 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, Benny Halevy,
                     Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root.

        Run began: Fri Aug  1 23:30:32 2008

        Include fsync in write timing
        Include close in write timing
        Record Size 4096 KB
        File size set to 102400 KB
        No retest option selected
        Command line used: iozone -ec -t 1 -r 4M -s 100M -+n -i 0 -i 1
        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 102400 Kbyte file in 4096 Kbyte records

        Children see throughput for  1 initial writers  =  220451.12 KB/sec
        Parent sees throughput for  1 initial writers   =  218488.69 KB/sec
        Min throughput per process                      =  220451.12 KB/sec
        Max throughput per process                      =  220451.12 KB/sec
        Avg throughput per process                      =  220451.12 KB/sec
        Min xfer                                        =  102400.00 KB

        Children see throughput for  1 readers          =  749124.19 KB/sec
        Parent sees throughput for  1 readers           =  734250.46 KB/sec
        Min throughput per process                      =  749124.19 KB/sec
        Max throughput per process                      =  749124.19 KB/sec
        Avg throughput per process                      =  749124.19 KB/sec
        Min xfer                                        =  102400.00 KB
-----------
Here are some basic specifications:
- Opteron 2350
- Operating system (Opensuse 11) 64 bit on one disk. Reiser4 formatted on
another data disk(SATA)
- Disk formatted in the following way:

# mkfs.reiser4 -o create=ccreg40,compress=lzo1 /dev/sda -fy
# fsck.reiser4 --fix /dev/sda -y
# mkdir /reiser4
# mount -t reiser4 /dev/sda /reiser4

Glenn

Re: iozone results

[Edward Shishkin]

doiggl@velocitynet.com.au wrote:
> iozone results
> source info from http://www.citi.umich.edu/projects/asci/benchmarks.html
>
> # iozone -ec -t 1 -r 4M -s 100M -+n -i 0 -i 1
>         Iozone: Performance Test of File I/O
>                 Version $Revision: 3.300 $
>                 Compiled for 64 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, Benny Halevy,
>                      Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root.
>
>         Run began: Fri Aug  1 23:30:32 2008
>
>         Include fsync in write timing
>         Include close in write timing
>         Record Size 4096 KB
>         File size set to 102400 KB
>         No retest option selected
>         Command line used: iozone -ec -t 1 -r 4M -s 100M -+n -i 0 -i 1
>         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 102400 Kbyte file in 4096 Kbyte records
>
>         Children see throughput for  1 initial writers  =  220451.12 KB/sec
>         Parent sees throughput for  1 initial writers   =  218488.69 KB/sec
>         Min throughput per process                      =  220451.12 KB/sec
>         Max throughput per process                      =  220451.12 KB/sec
>         Avg throughput per process                      =  220451.12 KB/sec
>         Min xfer                                        =  102400.00 KB
>
>         Children see throughput for  1 readers          =  749124.19 KB/sec
>         Parent sees throughput for  1 readers           =  734250.46 KB/sec
>         Min throughput per process                      =  749124.19 KB/sec
>         Max throughput per process                      =  749124.19 KB/sec
>         Avg throughput per process                      =  749124.19 KB/sec
>         Min xfer                                        =  102400.00 KB
> -----------
> Here are some basic specifications:
> - Opteron 2350
> - Operating system (Opensuse 11) 64 bit on one disk. Reiser4 formatted on
> another data disk(SATA)
> - Disk formatted in the following way:
>
> # mkfs.reiser4 -o create=ccreg40,compress=lzo1 /dev/sda -fy
>   

I am sorry, but iozone doesn't take care of file content and writes
something
like well compressible zeros. So the results above are meaningless.

Thanks,
Edward.

> # fsck.reiser4 --fix /dev/sda -y
> # mkdir /reiser4
> # mount -t reiser4 /dev/sda /reiser4
>
> Glenn
>
> --
> To unsubscribe from this list: send the line "unsubscribe reiserfs-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
>   

Re: iozone results

[doiggl]

Questions for Edward:
1. What are  good tests/or scripts you use (which is available and are
valid)  to measure throughput on a reiser4 partition ?
2. Do you have an example I can use, or try ?
Thank you
Glenn.

> Edward wrote:
> I am sorry, but iozone doesn't take care of file content and writes
> something like well compressible zeros. So the results above are
> meaningless.
>
> Thanks,
> Edward.

Re: iozone results

[Edward Shishkin]

doiggl@velocitynet.com.au wrote:
> Questions for Edward:
> 1. What are  good tests/or scripts you use (which is available and are
> valid)  to measure throughput on a reiser4 partition ?
> 2. Do you have an example I can use, or try ?
>   

If you want to play with compressed data, then I don't know
such tests: transparent compression is rather new feature for
a file system and all existing public benchmarks are old.

There is a namesys corporative benchmark (mongo.pl).
It also doesn't take care about file content. However, it is
possible to add an option so that mongo will use a content of
specified file (in ramfs). If it seems interesting for you, then let
me know and I'll send you the stuff.

Edward.

> Thank you
> Glenn.
>
>   
>> Edward wrote:
>> I am sorry, but iozone doesn't take care of file content and writes
>> something like well compressible zeros. So the results above are
>> meaningless.
>>
>> Thanks,
>> Edward.
>>     
>
>
>
>