gstripe small transaction size

Ivan Voras ivoras at freebsd.org
Tue Sep 28 10:44:48 UTC 2010


On 09/28/10 03:08, Stephen Sanders wrote:
> I'm trying a disk throughput experiment where in two 3ware raid 6's are
> being put into a g_strip raid 0.
>
> The raid 6's are using 8 7200RPM disks. The disk transfer rate is
> ~80MB/s. Using a load generation tool that is using O_DIRECT for I/O,
> I've generated the following short output from iostat. Needless to say,
> the write performance is a lot less than I'm expecting.
>
> We've modified the kernel such that our KB/t figure is closer to 512KB/t
> per disk when measured without the g_strip. With g_strip turned on, the
> KB/t number is more like 60KB/t.
>
> The question is how do I get g_stripe to write larger transactions to
> the disk ?
>
> gstripe label -v -s 131072 roadkill /dev/da0 /dev/da2

No pratical way. You have a gstripe array of two drives and with MAXPHYS 
of 128 KiB each would in fact see at most 64 KiB transactions. It gets 
worse when you add drives.

> newfs /dev/stripe/roadkill

Depending on what you are doing, adding "-U" would help you here.




More information about the freebsd-performance mailing list