Email Subscription Notifications Suspended Temporarily
We are in the process of making navigation in the Servers and Operating Systems forums simpler and more direct. While doing this, we have to temporarily suspend email notifications for subscriptions. If you are subscribed to one or more discussion boards or blogs in the community, please check them daily to see new content. Notifications will be turned back on in a few days. We apologize for any inconvenience this may cause. Thanks, Warren_Admin
Disk Enclosures
cancel
Showing results for 
Search instead for 
Did you mean: 

anyone tell me the default stripe size in xp1024 raid 0/1 ?

Xiang Zhao_1
Advisor

anyone tell me the default stripe size in xp1024 raid 0/1 ?

now we use 2d+2d raid0/1 (open-L), and will use 4d+4d later.
Is the stripe size configurable?

-Xiang
1 REPLY
samsondows
Occasional Contributor

Re: anyone tell me the default stripe size in xp1024 raid 0/1 ?

Internal Transfer Quanta (Stripe Chunk)

On all generations of SE9900 storage prior to SE9990, all OPEN device emulations used
a slot/track size of 48k. A stripe chunk consisted of 8 slots (384k). A full stripe ranged
from 768k to 2688k, depending on the number of data chunks in the RAID type.
For example, the stripe size for RAID1 2+2 was (2)(384) = 768k.  
Eight parity cycles were required to generate parity for each stripe chunk.

With the introduction of SE9990, there have been two significant architectural changes.
The SE9990 cache slot size has  increased from 64k to 256k, and the OPEN-V
track/slot size has also been raised to 256k. The OPEN-V stripe chunk size will be 512k
(2 tracks), and thus only 2 parity cycles will be required for each stripe chunk.
Therefore on SE9990, we can simplify and gain efficiencies in cache management by
using the OPEN-V emulation. These advantages will be realized because the OPEN-V
track size matches the cache slot size, and because 75% fewer parity cycles are required for a stripe chunk that includes 128k more data than other emulations.

Therefore, more data can be moved with less overhead.