Exadata: Oracle finally answers the data warehouse challengers
Oracle, in partnership with HP, has announced a new data warehouse appliance product line, cleverly branded “Exadata.” The basic idea seems to be that database processing is split among two sets of servers:
- (The new stuff) A set of back-end servers — the Oracle Exadata Storage Servers — that gets data off of disk and does some preliminary query processing.
- (The old stuff) A conventional Oracle RAC cluster on the front-end.
Numbers are being thrown around suggesting that, unlike prior Oracle offerings, the Oracle Exadata-based appliance at least has scalability and price/performance worth comparing to Teradata — hey, Exa is bigger than Tera! — Netezza, et al.
Kevin Closson, who evidently worked on the project, offers the most useful and detailed description of Oracle Exadata I’ve seen so far. In particular, he and Oracle seem to claim:
- I/O will no longer be a bottleneck, due to direct-attached storage (DAS), Infiniband, and so on. (That sounds plausible.)
- Oracle Exadata files will be optimized simultaneously for sequential table scans and conventional block-based random I/O. (Huh?)
If for the sake of argument we grant the claims so far, it’s still not clear to me whether Oracle’s approach is fully competitive with Teradata, Netezza, et al. Whatever query processing isn’t already done at the Oracle Exadata Storage end has to be done in Oracle RAC. But what exactly does RAC bring to query parallelization? Well, it should help with concurrency. Whatever performance Oracle can get with a small number of users shouldn’t degrade too badly as the user load grows. Oracle’s Exadata-based appliance will probably prove to have much better concurrency than startup vendors’ Release 1s typically have.
That’s the good-news side of my guessing. The other traditional Release 1 bottleneck is that too much data is shipped to the “fat head,” and query processing isn’t really parallelized in more than a simple-minded way. So far, I’ve seen nothing to suggest that Oracle isn’t as subject to that problem as any other vendor.
As for Oracle’s sophisticated query accelerations such as sophisticated materialized views and so on — I think users increasingly want all queries to run quickly, rather than just the ones that were previously planned for. So I’m not sure how much of an advantage those will prove to be.
And of course Oracle’s management tools are robust and its prices high. Those are both givens.
Related links
- Dividing the data warehousing work among MPP nodes
- SANs vs. DAS in MPP data warehousing
- Three ways Oracle or Microsoft could go MPP
Comments
18 Responses to “Exadata: Oracle finally answers the data warehouse challengers”
Leave a Reply
[…] listed with >16 TB, which is fairly consistent with Larry Ellison’s confession during the Exadata announcement that Oracle has trouble over 10 TB (which is something I’ve gotten a lot of […]
[…] addition to my previously posted thoughts on the Oracle Exadata/data warehouse appliance announcement, let me offer some more concise […]
[…] is the most sophisticated on the planet (even ahead of IBM’s, I’d say). But in all the Exadata discussion — and also in a good, comprehensive review of Oracle’s data warehouse […]
[…] the big news this week is Exadata, and its parallelization or lack thereof. But let’s not forget the rest of Oracle’s […]
[…] Oracle Exadata was pre-teased as “Extreme performance.” Some incorrect speculation shortly before the announcement focused on the possibility of OLTP without disk, which clearly would speed things up a lot. I interpret that in part as being wishful thinking. […]
What does this mean for HP Neoview? Have HP sacrificed it in order to boost hardware sales? A big chunk of the money for the Oracle Warehouse Machine is tied up in the Oracle database license fees, HP would make more out of a Neoview appliance.
[…] Автор: Curt Monash Дата публикации оригинала – 2008-09-24 Перевод: Константин Лисянский Источник: Блог Курта Монаша […]
[…] Oracle Exadata could produce those appliance sales. So where does HP Neoview fit […]
Good question, Vincent — so I blogged about it. 🙂
http://www.dbms2.com/2008/09/26/so-what-does-oracle-exadata-mean-for-hp-neoview/
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…)
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
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.
[…] That almost sounds as if Exadata is an immature, Release 1 data warehouse appliance! Share: These icons link to social bookmarking […]
[…] 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 […]
[…] 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’ […]
[…] 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 […]
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.
[…] 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 […]