Date: Mon, 18 Mar 2013 19:07:25 +0100 From: Davide D'Amico <davide.damico@contactlab.com> To: Steven Hartland <killing@multiplay.co.uk> Cc: freebsd-fs@freebsd.org Subject: Re: FreBSD 9.1 and ZFS v28 performances Message-ID: <514757DD.9030705@contactlab.com> In-Reply-To: <51475267.1050204@contactlab.com> References: <514729BD.2000608@contactlab.com> <810E5C08C2D149DBAC94E30678234995@multiplay.co.uk> <51473D1D.3050306@contactlab.com> <1DD6360145924BE0ABF2D0979287F5F4@multiplay.co.uk> <51474F2F.5040003@contactlab.com> <E106A7DB08744581A08C610BD8A86560@multiplay.co.uk> <51475267.1050204@contactlab.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Il 18/03/13 18:44, Davide D'Amico ha scritto:
> Il 18/03/13 18:42, Steven Hartland ha scritto:
>> ----- Original Message ----- From: "Davide D'Amico"
>> <davide.damico@contactlab.com>
>>
>>>> So RAID10 on just 6 disks in effect just 3 active spindles? If so
>>>> then your
>>>> throughput of 400MB/s is about right.
>>> Well, my RAID10 is on 4 disk (2 spindle) so do I have 400MB/s (3GBps)
>>> because the max throughput is 6Gbps?
>>
>> You'll be limited by the actual disks. For your disks this is stated
>> as 122 to 204MB/s sustained. So if your getting 400MB/s your doing
>> well :)
>>
>
> Thanks, now it's clear.
But now I do other tests using a lua script with sysbench with different
setups:
UFS on RAID10 HW:
General statistics:
total time: 36.1023s
total number of events: 1
total time taken by event execution: 36.1002s
UFS on 1 SSD:
General statistics:
total time: 36.3970s
total number of events: 1
total time taken by event execution: 36.3948s
ZFS (mirror mfid3 mfid4 mirror mfid5 mfid6):
General statistics:
total time: 78.0531s
total number of events: 1
total time taken by event execution: 78.0509s
ZFS with ZIL:
General statistics:
total time: 85.2306s
total number of events: 1
total time taken by event execution: 85.2285s
The workload is always the same (a set of 50k mysql myisam queries), and
as you can see zfs is really slow compared to ufs, and I don't know why :(
The latest check I should do is using a L2ARC, but I'll do tomorrow.
Thanks,
d.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?514757DD.9030705>