RE: What are those changes for fixing the RAID0 performance?

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Greetings,

I am guessing that this behavior is due to kernel virtual memeory management
and as a result porting may be rough. Here are some overall server tuning
suggestions that include VM suggestions I hope will help you and not require
you to do a lot of porting:

http://people.redhat.com/alikins/system_tuning.html

Regards,

Effrem Norwood

> I have been looking for "what changes are made to fix/improve the parallel
> access(?) to disks simultanously?".
> I noticed as follow;
>
> Up to Linux2.4.9  it got the same performance for RAID0(2-way
> stripe) and a
> single disk(JBOD),
> about 15 MB/sec with DMA on(hdparm -tT /dev/mdx).
>
> On Linux 2.4.10 it improves to about 25 MB/sec for RAID0, 15 MB/sec for
> single disk.
> On Linux 2.4.18 it got the right performance; about 31 MB/sec for RAID0.
>
> I tried to port the difference on /driver/ide and /drivers/md, but it did
> not help.
> I think there were changes on other functions to fix the parallel
> access(?)
> to disks simultanously OR
> to improve the RAID0 performance .
>
> Why am I doing this kind of homework?
>
> I can not migrate our linux to 2.4.18 so I want to port ONLY the fixes for
> this performance
> issue. I use Linux2.4.5.
>
> Please help me if you know how I can work around.
>
> Thanks in advance,
>
> Bo


-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [Linux RAID Wiki]     [ATA RAID]     [Linux SCSI Target Infrastructure]     [Linux Block]     [Linux IDE]     [Linux SCSI]     [Linux Hams]     [Device Mapper]     [Device Mapper Cryptographics]     [Kernel]     [Linux Admin]     [Linux Net]     [GFS]     [RPM]     [git]     [Yosemite Forum]


  Powered by Linux