-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

David Rees wrote:
> On Mon, Mar 3, 2008 at 12:08 PM, Tomasz Chmielewski <[EMAIL PROTECTED]> wrote:
>>  RAID5/6 have a performance penalty when compared to other RAID level
>>  because every single write (or, write IO operation) requires four disk
>>  IOs on two drives (two reads, and two writes), possibly harming other IO
>>  operations.
> 
> Correction:
> 
> Small writes (writes smaller than stripe size) require reads from
> disk. Writes that are the size of a stripe or larger do not incur the
> additional read penalty.
> 
> For example if you have a 3-disk RAID 5 and a 256 KB stripe size, two
> disks hold 128 KB of data and the third holds 128 KB of parity data.
> 
> If you write less than 256 KB to a stripe, you first have to read the
> data from the two data disks, calculate the parity with the new data
> and write to all 3 disks.
> 
> But if you are writing 256 KB or more, you can skip the read and
> simply calculate the parity and write all 3 chunks to disk.

So would it then make sense for a backuppc data partition to use a
smaller stripe size since most writes will be very small?

> Having battery backed RAM on the RAID controller can help, because the
> controller can lie to the OS and say the data is written to disk
> immediately instead of waiting for an read-calculate-write cycle,
> since it's sure that if it does lose power, it can store the data that
> should be written to disk later when power is restored in addition to
> buffering the reads/writes so that it can reorder them to reduce the
> amount of seeking required.

Is it possible to instruct linux to use it's memory to do this? If you
have a UPS and feel that it is pretty unlikely to crash, you might be
happy to get this kind of speed improvement.


Regards,
Adam
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.6 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org

iD8DBQFHzLhPGyoxogrTyiURArcmAJ9akT9v/+ru/ogOqRFecAEz8IKQFgCZAT8+
2zjLqBFmjExZWT0adTTuWCc=
=ycqA
-----END PGP SIGNATURE-----

-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
_______________________________________________
BackupPC-users mailing list
BackupPC-users@lists.sourceforge.net
List:    https://lists.sourceforge.net/lists/listinfo/backuppc-users
Wiki:    http://backuppc.wiki.sourceforge.net
Project: http://backuppc.sourceforge.net/

Reply via email to