FreBSD 9.1 and ZFS v28 performances
Davide D'Amico
davide.damico at contactlab.com
Tue Mar 19 09:28:24 UTC 2013
Il 19/03/13 10:26, Steven Hartland ha scritto:
>
> ----- Original Message ----- From: "Davide D'Amico"
> <davide.damico at contactlab.com>
>>>> [...]
>>>>> I'd recommend doing the same test on the SSD with ZFS as well as that
>>>>> would
>>>>> give you a simple like for like comparison.
>>>>
>>>> Here we are:
>>>>
>>>> # zpool create DATAZFS mfid2
>>>>
>>>> 1° round:
>>>> General statistics:
>>>> total time: 90.1662s
>>>> total number of events: 1
>>>> total time taken by event execution: 90.1631s
>>>>
>>>> 2° round:
>>>> General statistics:
>>>> total time: 82.3333s
>>>> total number of events: 1
>>>> total time taken by event execution: 82.3307s
>>>>
>>>> 3° round:
>>>> General statistics:
>>>> total time: 81.5421s
>>>> total number of events: 1
>>>> total time taken by event execution: 81.5399s
>>>>
>>>> 4° round:
>>>> General statistics:
>>>> total time: 82.1657s
>>>> total number of events: 1
>>>> total time taken by event execution: 82.1636s
>>>>
>>>>
>>>> # zfs get all DATAZFS
>>>> NAME PROPERTY VALUE SOURCE
>>>> DATAZFS type filesystem -
>>>> DATAZFS creation Tue Mar 19 7:36 2013 -
>>>> DATAZFS used 52.0G -
>>>> DATAZFS available 64.2G -
>>>> DATAZFS referenced 52.0G -
>>>> DATAZFS compressratio 1.00x -
>>>> DATAZFS mounted yes -
>>>> DATAZFS quota none default
>>>> DATAZFS reservation none default
>>>> DATAZFS recordsize 128K default
>>>> DATAZFS mountpoint /DATAZFS default
>>>> DATAZFS sharenfs off default
>>>> DATAZFS checksum on default
>>>> DATAZFS compression off default
>>>> DATAZFS atime off local
>>>> DATAZFS devices on default
>>>> DATAZFS exec on default
>>>> DATAZFS setuid on default
>>>> DATAZFS readonly off default
>>>> DATAZFS jailed off default
>>>> DATAZFS snapdir hidden default
>>>> DATAZFS aclmode discard default
>>>> DATAZFS aclinherit restricted default
>>>> DATAZFS canmount on default
>>>> DATAZFS xattr off temporary
>>>> DATAZFS copies 1 default
>>>> DATAZFS version 5 -
>>>> DATAZFS utf8only off -
>>>> DATAZFS normalization none -
>>>> DATAZFS casesensitivity sensitive -
>>>> DATAZFS vscan off default
>>>> DATAZFS nbmand off default
>>>> DATAZFS sharesmb off default
>>>> DATAZFS refquota none default
>>>> DATAZFS refreservation none default
>>>> DATAZFS primarycache all default
>>>> DATAZFS secondarycache all default
>>>> DATAZFS usedbysnapshots 0 -
>>>> DATAZFS usedbydataset 52.0G -
>>>> DATAZFS usedbychildren 225K -
>>>> DATAZFS usedbyrefreservation 0 -
>>>> DATAZFS logbias latency default
>>>> DATAZFS dedup off default
>>>> DATAZFS mlslabel -
>>>> DATAZFS sync standard default
>>>> DATAZFS refcompressratio 1.00x -
>>>> DATAZFS written 52.0G -
>>>
>>> That's got the wrong record size for mysql :(
>>
>> Sorry, my fault (I've made so many tests...). I'll modify it asap,
>> copy the mysql/* files again and posting here the results.
>
> Is this a test I could possibly run here? I have a machine on test for
> mysql so if its something you can let me have the data for I can run
> some tests locally too.
i don't know if you have installed sysbench 0.5.0 somewhere in you
server, but we could test using *standard* oltp tests (the dataset I'm
using is strictly private) included in sysbench package.
Is it possible, for you?
I'm using mysql-5.6.10 enterprise (but I think the one you find in the
ports tree it's a good choice, too).
Thanks,
d.
More information about the freebsd-fs
mailing list