Re: mfi driver performance


On 09/10/12 11:35, Andrey Zonov wrote:
> On 9/10/12 9:14 PM, matt wrote:
>> On 09/10/12 05:38, Achim Patzner wrote:
>>> Hi!
>>>
>>> We=92re testing a new Intel S2600GL-based server with their recommend=
ed RAID adapter ("Intel(R) Integrated RAID Module RMS25CB080=94) which is=
 identified as
>>>
>>> mfi0: <ThunderBolt> port 0x2000-0x20ff mem 0xd0c60000-0xd0c63fff,0xd0=
c00000-0xd0c3ffff irq 34 at device 0.0 on pci5
>>> mfi0: Using MSI
>>> mfi0: Megaraid SAS driver Ver 4.23=20
>>> mfi0: MaxCmd =3D 3f0 MaxSgl =3D 46 state =3D b75003f0=20
>>>
>>> or
>>>
>>> mfi0@pci0:5:0:0:        class=3D0x010400 card=3D0x35138086 chip=3D0x0=
05b1000 rev=3D0x03 hdr=3D0x00
>>>     vendor     =3D 'LSI Logic / Symbios Logic'
>>>     device     =3D 'MegaRAID SAS 2208 [Thunderbolt]'
>>>     class      =3D mass storage
>>>     subclass   =3D RAID
>>>
>>> and seems to be doing quite well.
>>>
>>> As long as it isn=92t used=85
>>>
>>> When the system is getting a bit more IO load it is getting close to =
unusable as soon as there are a few writes (independent of configuration,=
 it is even sucking  as a glorified S-ATA controller). Equipping it with =
an older (unsupported) controller like an SRCSASRB
>>> (mfi0@pci0:10:0:0:       class=3D0x010400 card=3D0x100a8086 chip=3D0x=
00601000 rev=3D0x04 hdr=3D0x00
>>>     vendor     =3D 'LSI Logic / Symbios Logic'
>>>     device     =3D 'MegaRAID SAS 1078'
>>>     class      =3D mass storage
>>>     subclass   =3D RAID) solves the problem but won=92t make Intel=92=
s support happy.
>>>
>>> Has anybody similar experiences with the mfi driver? Any good ideas b=
esides running an unsupported configuration?
>>>
>>>
>>> Achim
>>>
>>> _______________________________________________
>>> freebsd-current@freebsd.org mailing list
>>> http://lists.freebsd.org/mailman/listinfo/freebsd-current
>>> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd=
=2Eorg"
>> I just set up an IBM m1015 (aka LSI 9240lite aka Drake Skinny) with mf=
i.
>> Performance was excellent for mfisyspd volumes, as I compared using th=
e
>> same hardware but with firmware (2108it.bin) that attaches under mps.
>> Bonnie++ results on random disks were very close if not identical
>> between mfi and mps. ZFS performance was also identical between a
>> mfisysd JBOD volume and a mps "da" raw volume. It was also quite clear=

>> mfisyspd volumes are true sector-for-sector pass through devices.
>>
>> However, I could not get smartctl to see an mfisyspd volume (it claime=
d
>> there was no such file...?) and so I flashed the controller back to mp=
s
>> for now. A shame, because I really like the mfi driver better, and
>> mfiutil worked great (even to flash firmware updates).
>>
> Have you got /dev/pass* when the controller run under mfi driver?  If
> so, try to run smartctl on them.  If not, add 'device mfip' in your
> kernel config file.
>
I will try mfi firmware again tonight. With ZFS it seemed happy whether
the pool was /dev/da* or /dev/mfisyspd*. Is the mfisyspd device name set
in stone? It's quite long!


Matt

_______________________________________________
freebsd-current@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-current
To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org"