A loyal customer alerted us toan Oracle blog by Jean-Pierre Dijcks earlier today that showed the Oracle FUD machine is fully revved-up and ready to go. I'd like to offer a rebuttal, however in the interest of not intruding on Jean-Pierre's entry with an overly-long comment, I've just put a short response on his blog post with a pointer to this one.

Misconceptions and Misunderstandings, or Errors and Plain-old FUD?

I’m writing to correct *just a few* of the misconceptions about what is really important in high-performance, scalable data warehouse systems, errors, or just plain-old pure “competitive FUD” points from Jean-Pierre's posting earlier today. We certainly have posted some information recently about the TwinFin product and Curt Monash’s postings late Thursday provided more info. If his readers are interested in learning more, or even signing up for a “Test Drive”, they should visit www.netezza.com.

First off, I think this is a “banner day” for Netezza. We believe that TwinFin (and the other products in the new product family) extend both our performance and price-performance advantage over our competitors. We stand by our marketing statements that we regularly demonstrate 10-100X performance advantages over our competitors, particularly competitive offerings of the major incumbent DW system vendors (“Just who are those incumbents?” Jean-Pierre's readers may ask. Well let’s just say that we see Oracle as the incumbent system and/or a challenger system in over 50% of our deal flow.).

Regarding his claims about DBM being “faster than Netezza” (and I can only assume he meant at “real” data warehouse tasks) - we’re ready whenever Oracle feels up to actually taking one of their Database Machines onsite to a customer for a fair, open customer benchmark. So far, Oracle have been, shall we say, “a little reticent” to do on-site benchmark testing against Netezza.

Next, given the large number of incorrect points in the original posting, I think perhaps that just a few of them will be useful enough for readers to get the gist of just how far afield some of the ‘facts’ are:

• “It all comes down to data scan rates per rack”: Would that it were true that all of data warehousing boiled down to full-stream data scans (as if the entire world of analytics relied on “select count(*) from lineitem” types of queries), then we could all measure “goodness” on how many GB/sec of data could be burst-scanned in our systems. But that’s not the case. So we build Netezza’s data and analytic appliances to deliver the best possible overall performance at the best price and power requirements. As a consequence, and following from those same numbers as-posted, a single rack of TwinFin can process (not just scan) about 400 million rows of data per second. That’s process, as in: “scan, decompress, project, restrict, AND join, etc.”. Need more processing firepower? Netezza’s system performance scales linearly with the addition of more S-Blades: at the low-end, the TwinFin 3 can deliver as much as 100M rows/second of processing horsepower, while the TwinFin 120 can provide you with 4 billion rows/second.  Does a system that still relies on using SMP-based servers running “plain old” Oracle 11g RAC scale similarly for data warehousing?
  

• “Non-open Linux running on FPGAs”: I’m really not sure what (if anything) was meant by this, but saying that Netezza’s FPGAs “are apparently running non-open Linux” is oxymoronic on at least two different levels (FPGAs don’t typically “run” an OS and, “non-open Linux” - really?)
  

• “User data & compresssion”: I also enjoyed the accounting of all that “user data” available to DBM users in the Oracle table and the various comments about compression. When Netezza quotes user data capacities in our systems, the numbers reflect real raw user data space, not space that will be further reduced because of required indexes in an attempt to boost performance. Furthermore, Netezza’s compression & decompression techniques allow us to extract “pure performance” from their use. By not relying on CPU cycles to decompress the data before we can process it any further, the FPGA engines decompress the data, on-the-fly, as fast as it streams off the disk drives. Can Oracle make either of those claims?
  

• “Tolerating node failures without downtime”: In perhaps the most bald-faced inaccuracy, the Oracle blog claimed, that Netezza “continues to lack the ability to tolerate node failures without downtime”. This I can only chock up to pure competitive “FUD-ism” as our capabilities in this area have been quite strong throughout the four generations of Netezza appliances and are further strengthened in TwinFin. Netezza is a fully-redundant system with no single point of failure, even in our smallest systems. Failover in the presence of failures of the disk drives, S-Blades, internal networking or host processors (in short, everything) is automatic and done in-service, with hot-swappable replacement throughout.
  

• “Appliance simplicity”: One thing Jean-Pierre didn’t address that might have been humorous to see his take on is the notion of “appliance simplicity” - basically the ability to build, support and maintain large to very large-sized data warehouses, with heavy workloads, with no or minimal tuning, partitioning, indexing or other “performance duct tape” required. Routinely, this capability in the Netezza systems is what delights our customers most and we have customers managing systems with several hundreds of terabytes of user data (not indexes + data, mind you - real data) with fractions of an FTE (full-time employee) devoted to them.
  

I hope that clears up some of the misconceptions. If any of Jean-Pierre's readers or Oracle customers would like to see or hear more about TwinFin for themselves, we definitely would invite them to come stop by our booth (#207) at TDWI or come to one or our regional Enzee Universe events coming to a location near you.

Just trying to clarify. Curt Monash's informative blog on the coming Netezza system and family of products includes the following:

...which seems to beg further clarification.

While Curt suggests big changes are afoot in Netezza's “architecture” - I think a more appropriate viewpoint would be that it's “the same architecture with a new physical implementation”. That is, the concept of data streaming from disk through the system is just as important now as it ever was.

True, we did move the "disk controller" function to a pair of HBA (Host Bus Adapter) cards that interface with the disk enclosures using multiple, redundant SAS (Serial-Attached SCSI), and providing more than ample bandwidth to stream all the drives per rack continuously to the blades. For those who click-thru on Curt's blog, this function is embedded in the device labeled “SAS Expander Module” (one on both the blade server and the "DB accelerator") in the 3rd chart of the PDF file (and also shown above) and allows data to stream from disk through to memory and then on to the FPGA without delay.

To move data between the blade server and the DB accelerator cards, we use IBM's expansion card (formerly known as "sidecar") technology to provide multiple parallel high-speed PCIe (peripheral component interconnect express) channels delivering the data streams from the disk drives to the memory on each blade server and providing very high-speed interconnect between the FPGA devices and that same memory, using DMA (direct memory access) to effect high-speed memory access without encumbering the CPU to get at it.

With all this high-speed interconnectivity, Netezza has been able to alter the data flow so that data streams to the memory first and then to the various FAST engines (see above diagram and/or refer to Issue 16: The Latest Addition to Netezza's FAST Engines Framework) in the FPGA. Those engines act as a "turbocharger" for query processing, implementing data decompression, restricting, projecting and applying the appropriate visibility rules in a pipelined process; typically filtering out well over 95% of the data scanned. From the FPGA, the resulting reduced data set is passed on to the CPU memory for additional processing to complete the process.

So, the logical streaming model of data from from disk to FPGA to CPU is retained, with significantly higher throughput as a result. But there's an added benefit: the fact that the originally-scanned data can remain in memory, still in compressed & unfiltered form, to be used as a cache avoiding disk scan activity where possible and helping boost system performance even more. In short, "Change, but no Change."

I hope that helps - with Curt's architecture viewpoint as well as with questions about our use of PCIe interconnects to raise performance.

We came across a series of blog posts the other day which seemed to insinuate that Netezza and other competitors might be trying to shape our 10-100X performance message on the backs of comparisons to antiquated, end-of-service life systems and not comparing to current competitors' platforms . When we got to this one - "Database Customer Benchmarketing Reports" - I felt we just had to correct the record, so I wrote a response to Greg Rahn's posting to give Netezza's side of the story, namely that

• we are as up-front as possible with prospective customers and use the customer benchmark testing/POC process to prove out Netezza's performance, value and simplicity value propositions;

• the results of other products' performance come from our prospects/customers and not the result of Netezza running the tests on those platforms;

• not only do we test against the incumbent systems, but there is almost always at least one other current competitive system that is included in the POC process;

• the PowerPoint deck on which Greg was doing his analysis contained some rather ancient (in enzee-years, anyway) comparisons with versions of the NPS appliance that we have not sold in as much as 4.5 years & was really not much of a data set on which to base his analysis; and

• the "proof of the pudding is in the tasting" - Netezza's success rate of converting prospects to customers through the customer benchmarking process remains very strong.

In short - we make every effort to keep the Netezza website contents both accurate and clear and we definitely feel confident in standing by our 10-100X performance claims. It would be great to have more than the Netezza "product marketing guy" clarify things - while I know some of the excellent results recent customers have seen in POC, no one knows them better than our customers & SI partners themselves.

Okay I'll admit that my first posting about the new Oracle Data Warehouse Appliance (DWA) tonight was a tad on the "snarky" side. But I have to say that I think it was because of all influences in the environment all around me. Straight away since the announcement yesterday afternoon, there's been a healthy degree of skepticism from industry insiders.

Beyond his commentary on Larry Ellison's hairstyle, Gavin Clarke of the UK's Channel Register virtually flogged Larry for flogging the "Oracle server appliance alliance with HP". Some of the best snippets included:

• Gavin's subtitle: "(Not) a hardware provider"

• "And so to chief executive Larry Ellison, who Wednesday afternoon announced Oracle's third effort in 10 years bundling his company's software with someone else's hardware. This time, it's a high-performance, Oracle data and storage server stack locking arms with old favorite Hewlett-Packard."

And after taking several informative paragraphs to expound on Oracle's two previously-failed attempts at ‘appliantization' - most recently the "Network Computer" initiative circa-2000 - to draw the clear analogy to yesterday's announcement, Clarke closed out his piece with this stinger:

• "In a telling sign of how much faith Ellison places in his latest appliance, he did not sit down for his traditional, open-mic smack-down session with OpenWorld attendees to field questions."

Analyst/blogger Curt Monash summarized more than a few skeptical digs in his Oracle Exadata and Oracle data warehouse appliance sound bites posting earlier today. For example, here are a few "bites" from Curt's post:

• "Oracle Exadata Release 1 is hardly going to put Teradata, Netezza, or Greenplum out of business."

• "After long denying it, Oracle has finally admitted that putting more than 10 TB on Oracle had been an extremely painful thing to do."

• "Oracle's Exadata-based appliance doesn't have the out-of-the-box simplicity that other appliances and analytic DBMS do."

VP & Global Marketing CTO Chuck Hollis of EMC weighed in with a couple good shots on his Chuck's Blog post: Oracle does hardware (emphasis mine):

• "Of course, there's little in the way of performance comparisons to help us evaluate just how fast this beast might go, except the ‘Up To 10x Faster' which smells a bit optimistic, never mind that it's Oracle comparing with itself, rather than other data warehousing appliances."

• "Every year at Oracle Open World, we hear about many "new initiatives" from Oracle. Well, not to be harsh here, but it's my impression that very few of them get talked about at next year's Oracle Open World. I routinely dig up past announcements from previous years, and it's relatively consistent pattern. I think it's fair to ask the question -- just how serious is Oracle about all of this?"

But the lead cynic was none other than Oracle CEO Larry Ellison himself. After years of denying performance issues at scale with various generations of Oracle DBMS software for data warehousing, Larry dropped this 11g-megaton bombshell about Oracle's data warehouse scalability, pre-Exadata - laying out the fundamental reason why Netezza has become the industry leader in Data Warehouse Appliances (source: ZDNet's Larry Dignan):

"Ellison, speaking at Oracle's OpenWorld conference, said large databases are creating a fundamental problem: Disk storage systems can't cope with data that has to be moved off of drives to database servers. He called it a ‘data bandwidth problem.'

"As data gets larger the slowdowns become more unbearable. At one terabyte you will notice data bandwidth slippage. At 10 terabytes, storage systems crawl. ‘At one terabyte the problem rears its ugly head and it gets worse every year,' said Ellison."

And that's not all - the barbs, skepticism and "bites" go on in site-after-site, and commentary-after-commentary. So please forgive my snarky-ness - I blame it on the "nuture" of my environment, not my personal "nature", per se.

"And one of his partners asked, 'Has he vertigo?' and the other glanced out and down and said, 'Oh no, only about ten feet more.'"
— Ogden Nash, American writer and humorous poet (1902-1971)

Today's News: Netezza and EMC Partner to Simplify Data Warehousing for the Enterprise
This is hot! No, I mean it's really hot. I'm here in Las Vegas this week, attending the EMC World show in support of today's partnership announcement with EMC and yesterday the temperature crossed 110 degrees Fahrenheit (43 Celsius). Oh yes, and our announcement here this morning is hot as well - stirring up interest around the EMC World show floor. We had several great discussions with EMC field staff, their partners and some customers yesterday. In the imperfect domain of trade show tsotchkes as metric, in just four short hours yesterday we ran through nearly 400 tee-shirt give-aways. Of course, as an aside, I would subjectively say our shirt was clearly a "best-in-show" candidate here - witness these front & back photos:

Complementary Technology and Co-marketing for Success
"So what is this announcement all about?" you ask. From the viewpoint of our customers and prospects, it's primarily about Netezza partnering with the industry-leader in information infrastructure to bring the performance horsepower of the NPS^® data warehouse appliance into the enterprise data center in an even simpler, more efficient way than we already have been. It's consistent with their continuing evolution of data warehouse appliance deployments - as business-critical systems that are used enterprise-wide. And it provides them with both operational flexibility and performance in supporting the requisite data management functions.

From Netezza's business perspective this makes the NPS appliance even more well-suited to a broader sweep of customers. We'll provide provide familiar, enterprise-class data backup, replication and disaster recovery capabilities that extend Netezza's simple appliance approach by embedding EMC's CLARiiON^® storage arrays and Navisphere^® & MirrorView™ software. But just as important, we'll work with EMC on co-marketing initiatives in bringing these configurations to market. As a result we anticipate being able to extend our market penetration, both with new customers and broadening our footprint in current accounts.

How does this partnership change an NPS system?
The partnering initiative with EMC involves two basic configurations of the CLARiiON AX4 storage arrays. Both configurations will be deployed within the NPS data warehouse systems themselves and will require no additional data center footprint, with very minimal impact on the system's very low power and cooling requirements.

First off, let me say straight-away that this partnership in no way changes the basic NPS system architecture that Netezza has made use of through three generations of the its data warehouse appliance. The NPS system still will achieve its scalable, high performance through the unique AMPP™ architecture, including the Snippet Processing Units (SPUs) whose design is unaffected as a result of this partnership.

Instead, the EMC storage arrays will be used to provide near-line storage for the NPS systems in order to stage data for all of the primary bulk data movement operations: loading, unloading, backup, data replication and disaster recovery. In short, the most basic functional block diagram of the NPS appliance will evolve
from this: to this:

The two types of embedded CLARiiON configurations are as follow:

Storage Pad™
Deployed as part of the standard equipage in our two-rack (NPS 10200) and larger systems, the Storage Pad configuration will support up to 5 TB of near-line data capacity for staging ETL data loads, data unloads and incremental backup images. Applying an approach that I've come to call Tivo for data warehousing, the Storage Pad allows customers to time-shift data management functions to suit their operational requirements. For example, customers might make use of the Storage Pad to move backup data from the data warehouse rapidly and then move the backup data from the Storage Pad to a tape or disk archive at the rate that the data center network, media and operations scheduling will allow.

By comparison, other vendors may charge as much as $100,000 for just 1.5 TB of capacity for similar functionality.

Storage Pad XL™
As the name suggests, this optional configuration is scalable to high capacities that scale in-line with the NPS systems in which they will be deployed. The Storage Pad XL configurations will be available on all NPS 10000 series models and will support up to 10 TB of near-line data capacity per NPS rack - up to 80 TB for the 8-rack NPS 10800 system. Just like above, the Storage Pad XL can be used to for data staging, but now full images of the NPS tables or databases can be captured for high-speed backup.

In addition, this configuration will also be support the deployment of EMC's MirrorView software package for enterprise-class data replication and DR.

"Netezza - Now with added CLARiiON!" is the fun spin we put on the marketing look of our booth at EMC World this week but we think this partnership will provide our enterprise customers with an excellent, simple toolset for bringing the appliance paradigm to data management functions; and through our co-marketing initiatives with EMC, it will bring the NPS data warehouse appliance into more of our customers' data centers.

]]>