Penguin

Differences between version 8 and previous revision of RAID.

Other diffs: Previous Major Revision, Previous Author, or view the Annotated Edit History

Newer page: version 8 Last edited on Monday, February 21, 2005 5:03:57 pm by PerryLorier Revert
Older page: version 7 Last edited on Friday, August 6, 2004 11:42:30 am by PerryLorier Revert
@@ -10,8 +10,9 @@
 !Advantages: 
 * No parity generation 
 * Easy to implement in software and hardware 
 * Cheap to implement 
+  
 * Utilise full disk capacity, no space is wasted storing redundant pages 
  
 http://www.raidarray.eu.com/raid0.html or http://www.acnc.com/raid.html 
  
@@ -101,4 +102,10 @@
 * Lots of wasted disk space 
 * If two disks on opposing arrays die, you lose the entire array, where 1+0 would require two disks in the same position to die before you lose the array which is far less probable. 
  
 http://www.raidarray.eu.com/raid0+1.html 
+----  
+One suggested way of calculating the Stripe size for RAID systems that are doing a lot of random I/O (machines that are serving multiple users, eg email, compute servers etc) is to figure out the maximum throughput you can get through your disks (including controllers, PCI bus bandwidth etc). Then plug it into this formula:  
+ stripesize = throughput / (drives * RPM/60)  
+then round down the stripesize to the nearest multiple of your filesystem cluster size (usually 4k).  
+  
+Suggestions for the improvement of the estimation of optimal stripe size is solicited.