Re: Journaling without commitment control (WAS iSeries and SSD drives)

[Charles Wilt <charles.wilt@xxxxxxxxx>]

without journaling = 100 %
with journaling without commitment control 35%
with journaling and commitment control (or journal cache option)  96%

Yeah...it's that big....
http://www.quser.org/Docs/JournalCaching.pdf

And yes the hardware has changed, but the fundamental reasons for the
difference has not nor will it unless we get permanent storage that's as
fast as memory.  (even SSD's are still orders of magnitude slower than
RAM.)  Spend a little time with the documents provided and you'll
understand.

The above doc is from 2008.  See also links here from 2011
http://www.iprodeveloper.com/article/databasesql/journal-insights--journal-caching-revisited-how-does-it-work-65778


HTH,
Charles




On Fri, Jan 18, 2013 at 10:44 AM, D*B <dieter.bender@xxxxxxxxxxxx> wrote:

> Charles,
>
> what percentage would you estimate for a real world workload running on a
> balanced system?
> without jorunaling = 100 %
> with journaling without commitment controll x % ??
> with journaling an commitment controll y % ??
>
> I'm recommending and using journaling and commitment controll since about
> 20 years in most custumor environments and in my experience there are other
> issues dominating performance .
>
> D*B
> --
> This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list
> To post a message email: MIDRANGE-L@xxxxxxxxxxxx
> To subscribe, unsubscribe, or change list options,
> visit: http://lists.midrange.com/mailman/listinfo/midrange-l
> or email: MIDRANGE-L-request@xxxxxxxxxxxx
> Before posting, please take a moment to review the archives
> at http://archive.midrange.com/midrange-l.