Comments on: Exadata: Oracle finally answers the data warehouse challengers

By: Of friends and enemies « Observations from Hong Kong

Of friends and enemies « Observations from Hong Kong — Thu, 20 May 2010 02:59:57 +0000

[...] with all the knowledge gained from the first Exadata, HP brings a lot of knowledge to bear. Still I think the new SAP appliance will have a tough time [...]

By: Jacky

Jacky — Thu, 02 Oct 2008 13:39:35 +0000

I guess Exadata is the assemblage of the best of what is in shared nothing and shared all architectures that have all some problems we know about…so the honor is for Oracle and thanks.

By: Exadata and Oracle Database Machine parallelization clarified | DBMS2 -- DataBase Management System Services

Mon, 29 Sep 2008 02:41:36 +0000

[...] with different CPUs talking to different disk drives Until last week’s announcement of Exadata, Oracle was the most prominent holdout against this view. (That dubious honor now goes to [...]

By: Oracle Database Machine performance and compression | DBMS2 -- DataBase Management System Services

Sun, 28 Sep 2008 20:51:44 +0000

[...] Rahn was kind enough to recite in his blog what Oracle has disclosed about the first Exadata testers. I don’t track hardware model details, so I don’t know how the testers’ [...]

By: Oracle Exadata list pricing | DBMS2 -- DataBase Management System Services

Oracle Exadata list pricing | DBMS2 -- DataBase Management System Services — Sun, 28 Sep 2008 05:37:44 +0000

[...] been trying to figure out how much Oracle Exadata actually costs. My first cut comes up with prices of $58-190K/TB (user data), based on a total [...]

By: Oracle Exadata Smart Scan Join Processing | DBMS2 -- DataBase Management System Services

Fri, 26 Sep 2008 12:14:39 +0000

[...] That almost sounds as if Exadata is an immature, Release 1 data warehouse appliance! Share: These icons link to social bookmarking [...]

By: Curt Monash

Curt Monash — Fri, 26 Sep 2008 11:53:38 +0000

Seriously:

If Oracle publishes TPC-H results that look good, it just means everybody else has to do it too. So I hope they don’t pursue that course.

I’d be surprised if at the end of that process Oracle had the best benchmark results, or close to them, on a cost-weighted basis.

By: Curt Monash

Curt Monash — Fri, 26 Sep 2008 11:51:58 +0000

Like TPC-H? Given Oracle’s predilection for publishing TPC-H results in the past, I imagine we’ll be seeing some for this product too.

If not — well, maybe they’ll just have decided this is the time to finally get out of the benchmark game.

CAM

By: Mike Tuchen

Mike Tuchen — Fri, 26 Sep 2008 11:43:58 +0000

This is very cool sounding technology, but I’m noticing a conspicuous absence of what normally accompanies this kind of announcement, namely a benchmark result or two. How does it really stack up vs. the current benchmark champs in raw perf and price/perf? Did I just miss it in all the noise? (Yes, we can all insert as many caveats as we want about various real world scenarios’ lack of correlation to benchmark results, but at least they are a very specific well-defined workload and a very stringent apples to apples perf and price comparison. Oracle certainly hasn’t been shy about publishing them in the past when they have a good story to tell…)

By: Curt Monash

Curt Monash — Fri, 26 Sep 2008 04:58:05 +0000

Good question, Vincent — so I blogged about it.

http://www.dbms2.com/2008/09/26/so-what-does-oracle-exadata-mean-for-hp-neoview/