Re: ODA and HCC - current state
From: Hans Forbrich <fuzzy.graybeard_at_gmail.com>
Date: Sun, 26 Aug 2012 18:35:54 -0300
Message-ID: <503A96BA.5010605_at_gmail.com>
On 26/08/2012 4:17 PM, Kevin Closson wrote: >> HCC is a distinct optimization.
> Actually, HCC is merely "allowed" on ZFSSA (S7000) and Pillar. There is no HCC code executing in those storage processors unlike Exadata where decompression of HCC blocks (usually) does occur down in storage.
Poor wording on my part. I meant that HCC is something to seriously consider for a copy-on-write file system. Anything that will reduce the number of blocks should be a significant benefit.
Date: Sun, 26 Aug 2012 18:35:54 -0300
Message-ID: <503A96BA.5010605_at_gmail.com>
On 26/08/2012 4:17 PM, Kevin Closson wrote: >> HCC is a distinct optimization.
> Actually, HCC is merely "allowed" on ZFSSA (S7000) and Pillar. There is no HCC code executing in those storage processors unlike Exadata where decompression of HCC blocks (usually) does occur down in storage.
Poor wording on my part. I meant that HCC is something to seriously consider for a copy-on-write file system. Anything that will reduce the number of blocks should be a significant benefit.
Aside from that, I understand that HCC was actively 'not available' from non-Exadata environments until recently. No idea whether that was just traditional licensing (on your honour not to use it), or it was active in the code.
/Hans
-- http://www.freelists.org/webpage/oracle-lReceived on Sun Aug 26 2012 - 16:35:54 CDT