building a RAID system

Mark Hahn hahn at physics.mcmaster.ca
Wed Oct 8 20:23:28 EDT 2003


> 	- get those drives w/ 8MB buffer disk cache

what reason do you have to regard 8M as other than a useless
marketing feature?  I mean, the kenel has a cache that's 100x
bigger, and a lot faster.

> 	- slower rpm disks ... usually it tops out at 7200rpm

unless your workload is dominated by tiny, random seeks,
the RPM of the disk isn't going to be noticable.

> 	- it supposedly can sustain 133MB/sec transfers

it's not hard to saturate a 133 MBps PCI with 2-3 normal IDE
disks in raid0.  interestingly, the chipset controller is normally
not competing for the same bandwidth as the PCI, so even with 
entry-level hardware, it's not hard to break 133.

> 	- if you use software raid, you can monitor the raid status

this is the main and VERY GOOD reason to use sw raid.

> 	- some say scsi disks are faster ... 

usually lower-latency, often not higher bandwidth.  interestingly,
ide disks usually fall off to about half peak bandwidth on inner 
tracks.  scsi disks fall off too, but usually less so - they 
don't push capacity quite as hard.

> 	- it supposedly can sustain 320MB/sec transfers

that's silly, of course.  outer tracks of current disks run at 
between 50 and 100 MB/s, so that's the max sustained.  you can even
argue that's not really 'sustained', since you'll eventually get
to slower inner tracks.

> independent of which raid system is built, you wil need 2 or 3
> more backup systems to backup your Terabyte sized raid systems

backup is hard.  you can get 160 or 200G tapes, but they're almost 
as expensive as IDE disks, not to mention the little matter of a 
tape drive that costs as much as a server.  raid5 makes backup
less about robustness than about archiving or rogue-rm-protection.
I think the next step is primarily a software one - 
some means of managing storage, versioning, archiving, etc...

_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf



More information about the Beowulf mailing list