War and Peace with HP’s New Gen9

I love my book club. We vote on what books to read and we always choose interesting and enlightening fiction and non-fiction. We always serve great food and drink. And, best of all, you don’t even have to read the book.

So I was really excited last month to hear about the book we would be reading. My good friend said she liked the book and the cover showed a woman in an olive grove. What could be better? Until I actually read the book and realized that there was nothing really that thrilling behind the cover.

And that’s exactly how I felt this week reading about HP’s newest announcement on their x86 HP ProLiant Gen9 servers. I mean, for goodness sake, we are at Gen9 — I’m sure we’ve come so far and there must be some thrilling new features and performance behind them.

But alas, once again, my excitement was thwarted by what I actually read.

There were 3 claims for these new systems:

• Better TCO, optimization, and automation — but only comparing this new Gen9 to G6. I should hope there would be improvement.
• Faster provisioning — The footnote says “Based on anonymous customer results” — hmmm. Plus the software isn’t even available yet for Gen9.
• Improved performance — all it says is “equivalent controllers” in a “controlled environment.” — really hard to say what that means.

When I see claims like these with no real data all I can think is what real data looks like and how IBM Power Systems continue to surpass in performance.

And it reminds me that the olive grove book is no Pride and Prejudice.

At least HP tried to address performance — unlike Cisco, where it was totally ignored.

For next month we are reading Gabriel Garcia Marquez – so at least I will know to expect magic realism.

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance,HP,DL380,Gen9,Cisco,UCS,x86,G6,ProLiant,benchmark,benchmarking

Digging into SAP HANA on HP

All of the snow has finally melted in my backyard. And what that means to me is that I don’t have to shovel for awhile. What that means to my dog is another story.

It’s a field day for him. Now he can get back to what he surely thinks is his real job – digging in the dirt. And what has he found? A plastic flower pot that he can chew on. 3 beat up tennis balls from the summer. A soup bone from 3 months ago. Treasures.

HP just announced this morning that they are delivering a “System with Faster Analytics Engine for SAP HANA Environments.” HP claims a 2x performance advantage over other solutions. Let’s dig into this claim and take a look at the facts:

• The performance claim is based on the SAP BW Extended Mixed Workload Benchmark, a benchmark with only 4 results. And 3 of those results are from, you guessed it, HP.
• The SAP BW-EML benchmark results that HP references in their footnote in this press release are from September 2013 — a lifetime ago in the benchmark world.
• The HP system they reference in the press release is not even the system that is in the benchmark. HP’s new system is not even available.
• Even if you did try to compare the HP and IBM results, it does not make sense. The HP and IBM results are in different categories of the benchmark, using a different number of records. The HP result used an application and database tier; the IBM result is on a central server.
• Even if you ignored the fact that it doesn’t make sense to compare these results, if you do, the HP result used 2.5x the processing cores, 2x the memory, 4x the L1 cache, 2x the L2 cache per core. So the IBM result actually has 28% better throughput per core than the HP result.(1)

Please HP, dig more and come up with some new exciting treasures next time so we readers are not left in the dirt.

************************************************

(1) IBM Power System 7 Express Server Central Server: IBM Power System 750 Express Server, 4 processor / 32 cores / 128 threads, POWER7+, 4.06GHz, 32KB(D) + 32KB(I) L1 cache and 256KB L2 cache per core, 10MB L3 cache per core, 512GB main memory; certification #2013020 (SUSE Linux Enterprise Server 11, DB2 for I 7.1, SAP NetWeaver 7.30, 66,900 ad-hoc navigation steps/hr) vs.
SAP BW-EML Benchmark: Database tier: HP ProLiant DL580 G7, 4 processor / 40 cores / 80 threads, Intel Xeon Processor E7-4870, 2.40GHz, 64KB L1 cache and 256KB L2 cache per core, 30MB L3 cache per processor, 512GB main memory; Application tier: HP ProLiant BL680 G7, 4 processor / 40 cores / 80 threads, Intel Xeon Processor E7-4870, 2.40GHz, 64KB L1 cache and 256KB L2 cache per core, 30MB L3 cache per processor, 512GB main memory; certification #2013027 (SUSE Linux Enterprise Server 11,SAP HANA 1.0,SAP NetWeaver 7.30,129,930 ad-hoc navigation steps/hr)
http://www.sap.com. Results current as of 3/19/14.

SAP and all SAP logos are trademarks or registered trademarks of SAP AG in Germany and in several other countries. Other names may be trademarks of their respective owners.

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance,HP,SAP,HANA,ConvergedSystem,500,DB2,BW-EML,Power,analytics,benchmark,benchmarking

HP Hamming It Up

It was a cold and snowy day last January when I pulled into the parking lot in Streetsboro, Ohio. I was really pleased to be having lunch unexpectedly with two family members. I was not so pleased with the place we were going to have lunch — what I thought was a “fast food” joint that only served ham.

But oh how different from my expectations — incredibly nice staff, a wonderful place to sit, and the choice of exactly what you wanted on your sandwich — all of which made for an awesome lunch.

So I was excited this morning to see this same organization highlighted in a new press release from HP. Storage upgrades were discussed, along with claims of an amazing performance boost. Seasonal demands for ham would now be able to be addressed.

The problem of course is not with the ham but with the claims and the lack of data:

• Was the bottleneck actually with the batch window for sales data?
• Was it only during peak time of the holiday period?
• Did the upgrade really also reduce transaction processing times?
• What were the before and after results?
• The data center refresh also included networking and servers. How were these claims attributed to the storage?
• How would any improvements compare with other vendor products? How do the Storage Performance Council (SPC) industry standard results stack up?

 

Unfortunately the one footnote merely states “Based on customer results.”

But the most important question of course is will I get my ham sandwich much much faster next time ?

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, HP, Converged,Storage,3PAR,StoreServ,ProLiant, DL360,7500,switch,benchmark,benchmarking

 

Law & Order: Special Benchmarks Unit

Long ago my dream was to become a math teacher. Or a doctor. Or a computer programmer, whatever that was. But never, never, never a lawyer.

So it’s very interesting that I’ve been thinking a lot lately about the law.

Maybe it’s the Trayvon Martin shooting case. Maybe it’s the sensational John Edwards trial. Maybe it’s the Tyler Clementi surprise verdict. Or maybe it’s just the latest John Grisham book I just finished.

In any case I’ve been thinking a lot about the law. A lot about the law . . . and benchmarks.

• Like how important it is to read the fine print legal disclaimers so you know exactly what is tuned and what is measured. Some vendors may not perform a valid comparison when comparing systems. I saw a presentation recently that stated “Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors.” Very interesting.
• Like how important it is to peruse all the court documents. Hard to believe but some vendors allegedly hide server product plans from clients for financial gain.
• Like how important it is to understand legal clauses containing prohibitions on running certain benchmarks. Some hardware/software vendors expressly prohibit others from publishing benchmarks with their software using severe license restrictions around performance evaluations. Could the software possibly run better on other hardware? And the question becomes “What are they trying to hide?” In fact, years ago a New York Supreme Court ruling barred this practice. “Such clauses censoring speech and criticism chill not only consumers’ speech, but also prevent academics, consumer advocates, and technology experts alike from openly and freely discussing software products,” said then New York attorney general Eliot Spitzer — who ironically faced his own legal circus years later.

So if I had gone to law school I might have a better handle on these legal intricacies with benchmarks. But then I probably wouldn’t know how to program or how to be an IT Specialist. You just never know. I recently read an article in the newspaper about a lawyer who just left the legal profession. He wanted to make more of a difference and found that he really loved his new profession. His new job was in a school. Teaching. 6th grade. Math.

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, benchmarking, Intel,Oracle,hardware,HP,law,power,benchmark,software,database,

license,architecture,microprocessor,tuning,document,practices,

benchmarking

HP’s Converged Infrastructure, You Blockhead!!!

A few days ago, home for Thanksgiving, I encountered one of my old friends from childhood. A little wooden wagon, bright red with a pull string, now peeling paint. It holds as cargo about 50 wooden blocks of various shapes, sizes and colors. I remember wheeling these blocks around and then lovingly building towers that would come crashing down. You can’t get much better than that.

So I thought it was ironic this morning to read an article in the newspaper that stated that toy building blocks are finally back in style. There are now block workshops, block classes, even block consultants. Educators are finally realizing, once again, that blocks contribute to absorption of math concepts, higher test scores, and better language acquisition.

This is new news? There have been studies on this since the mid 20th century. Papers have been written on this topic, several major ones in the last decade. I could have told any researcher about this link — when I was six.

I had this same feeling looking at HP’s recent server announcement of future intentions. Project “Odyssey” is advertised as a development roadmap of UNIX and x86 architectures aimed at mission-critical computing focused on availability and performance. Here are my thoughts:

First and foremost, this is a roadmap folks. Roadmaps are nice. They help us look into the future. Just like with Itanium. And HP’s PC business. (Oh, right, that’s back on again, isn’t it?)

Hardware availability dates are “around two years.” Wouldn’t bet my business on that one. Remember that the original Odyssey around the time of the Trojan war took ten years.

Some of these integrated hardware/software architecture plans sound a bit to me like trying to force a square block into a round hole. It was always hard to do this when I was a kid.

HP is touting that clients need to be able to choose the best environment for their needs. Gee, wow, sounds a lot like the established and well-respected IBM Fit for Purpose methodology.

HP is promoting scale up and scale out abilities, application mobility, migration tools, sophisticated virtualization capabilities, RAS, and resiliency. Again, this is sounding very familiar to me. With IBM, you can get this NOW.

Meg needed to do something in light of Itanium/HP-UX decline. But instead of an “Odyssey” to Mars, it’s really just realizing what is basic to mission-critical computing — an area that IBM has excelled in for many, many years.

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, HP, Superdome,Integrity,x86,Itanium,HP-UX,Odyssey,benchmark,benchmarking

On HP’s New Strategy

As we all know, HP is currently evaluating “strategic alternatives” for its Personal Systems Group. This plan may involve a “spin-off or other transaction.”

This — let’s sort of say but not really say what we are doing — strategy has also spilled over into more technical press releases with an HP announcement today of new 3PAR storage systems.

I can see them thinking in Palo Alto: Let’s address performance using footnoting because it looks cool — but not really footnote anything useful.

• It used to be that footnotes were designed to give the reader more details on what was being said.
• It used to be that footnotes were long and elegant. Sort of like a Euclidean proof.
• It used to be that footnotes included actual data with descriptions on how that data was actually obtained.
• And it used to be that footnotes contained wonderful sources like white papers and web links.

One footnote HP used today merely repeated a fact that was already in the body of the press release — that performance claims were based on comparisons to previous versions of the same system. One would hope the new system would be better than previous versions.

Another footnote HP used today merely stated that performance and capacity claims were “based on documented experiences and business results in client deployments.” Fancy words for one customer who wrote something down on a napkin at lunch ?

HP’s new strategy also involved the coining of “nano-reclamation” which simply seems to mean reclaiming unused storage. And not a groundbreaking environmental science discovery using nanotechnology, which would actually be awesome now that I think about it.

One of HP’s goals for this latest plan is transformation. If transformation means becoming indefinite, unclear, and imprecise, then the strategy is working just fine.

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, HP, strategy,PC,3PAR,storage,federated,footnotes,benchmark,nano,reclamation,V400,V800,converged,capacity,benchmarking

Doing the Right Thing: Another SAP #1 on POWER7

Sometimes it seems as if everything around us is one big DON’T.

• Don’t say bad things about the lives of your ex-fans, like LeBron.
• Don’t tweet pictures of yourself from the gym.
• Don’t forget to lock your door in a hotel room.
• Don’t hike in shorts during black fly season.
• And don’t publish a benchmark — unless you have something cool to say about it.

Which IBM just did this week – a lovely jewel of a present for the IBM 100th birthday. A new #1 SAP SD 2-tier 12-core result on the IBM Power 730 POWER7 system — with Linux SLES 11 and DB2.(1)

This IBM result handily surpassed the HP SLES 11 result on the 12-core DL380.(2)

And for more on doing the right thing see what IBM is working on this week.

************************************************

(1)SAP SD 2-tier result of 5250 SAP SD benchmark users, IBM Power 730, POWER7, 3.7 GHz (2 processors / 12 cores / 48 threads), SLES 11, IBM DB2 9.7, SAP enhancement package 4 for the SAP ERP 6.0 (Unicode), 0.98 seconds average dialog response time, Certification #2011022.

(2)SAP SD 2-tier result of 4757 SAP SD benchmark users, HP DL380 G7, Xeon X5680, 3.33 GHz (2 processors / 12 cores / 24 threads), SLES 11, MaxDB 7.8, SAP enhancement package 4 for the SAP ERP 6.0 (Unicode), 0.98 seconds average dialog response time, Certification #2011001.

Source: http://www.sap.com/benchmark. Results current as of 6/15/11.

SAP, mySAP and other SAP product and service names mentioned herein as well as their respective
logos are trademarks or registered trademarks of SAP AG in Germany and in several other countries all
over the world.

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, POWER7, Xeon,730,Linux,SLES,SAP,gcc,DB2,9.7,HP,DL380,Xeon,X5680,MaxDB,benchmark,benchmarking

 

Who Killed HP?

I’m not one for conspiracy theories. Except of course in novels and films. After all these years, one of my favorite movies is still Capricorn One.

But you’ve got to admit that HP may have something here with the claims that Oracle is refusing to publish HP benchmark results.

For whatever reason:

The last time HP published a TPC-C result with Oracle was August 2010.

The last time HP published a TPC-H result with Oracle was April 2010.

The last time HP published an SAP SD 2-tier result with Oracle was in 2008. That was with the old kit.

The last time HP published a SPECjAppServer2004 result with Oracle was August 2010. And none with SPECjEnterprise2010.

For some benchmarks they’ve even had to use something called MaxDB . . .

So believe what you will. And maybe we will soon see Oracle added to this list of conspiracy theories. And in the greatest irony seen yet, Wikipedia, in its magnificent wisdom on article sources, makes sure to note that the list may contain “unverifiable claims.”

************************************************

Sources: http://www.tpc.org, http://www.spec.org, http://www.sap.com/benchmark.

TPC-H, TPC-C, and TPC-E are trademarks of the Transaction Performance Processing Council (TPPC).

SPEC, SPECint, SPECfp, SPECjbb, SPECweb, SPECjAppServer, SPECjEnterprise, SPECjvm, SPECvirt, SPECompM, SPECompL, SPECsfs, SPECpower, SPEC MPI and SPECpower_ssj are trademarks of the Standard Performance Evaluation Corporation (SPEC).

SAP, mySAP and other SAP product and service names mentioned herein as well as their respective
logos are trademarks or registered trademarks of SAP AG in Germany and in several other countries all
over the world.

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, Oracle, HP,TPC-C,SAP,SD,MaxDB,TPC-H,SPECjEnterprise,SPECjAppServer,benchmark,benchmarking

IBM #1 in Oracle Benchmark

Oracle provides a suite of vendor benchmarks to measure the performance of Oracle applications called the Oracle E-Business Suite Standard Benchmark. This benchmark is a comparable standard workload which demonstrates the performance and scalability of Oracle applications and provides metrics for the comparison of performance on different system configurations.

IBM just published another #1 POWER7 benchmark result on one of Oracle’s own benchmarks. The IBM Power 710 6-core system now leads in the R12 Order-to-Cash Medium Model. IBM surpassed Cisco and HP in this benchmark by over 2 times the performance per core. (1)

So my question here is what happens when Oracle decides to have a hardware presence in this specific benchmark? Are we taking bets?

************************************************

(1)A 6-core IBM Power 710 (3.72 GHz) achieved the best medium two-tier Order-to-Cash batch result (213,523 lines per hour) running AIX 6.1 and IBM System Storage DS5100. A 12-core Cisco UCS B200 (3.33 GHz) achieved medium two-tier Order-to-Cash batch result (185,643 lines per hour). An 8-core HP DL380 (3.16 GHz) achieved medium two-tier Order-to-Cash batch result (108,108 lines per hour).

Source: http://www.oracle.com/us/solutions/benchmark/apps-benchmark/results-166922.html. Results current as of 3/11/11.

Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners.

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, Oracle, 710,applications,HP,DL380,order-to-cash,Cisco,benchmark,UCS,POWER7,B200,DS5100,storage,Xeon,medium,model,AIX,Power,Express,benchmarking

True Grit Benchmarking

A few weeks ago, I went to see True Grit. This comic-serious western, adapted by Joel and Ethan Coen from the novel by Charles Portis, focuses on a 14-year-old Arkansas girl who hires a man with "true grit" to hunt down her father’s killer. It’s hard to put your finger on exactly what makes up true grit but I think it has something to do with being bold and gutsy, but with the backbone, bravery, courage and valor behind it.

Yesterday, HP published a press release on new appliances with Microsoft. The only reference to performance is a claim that the HP Enterprise Data Warehouse Appliance delivers amazingly faster queries than traditional SQL Server deployments. The footnote is very interesting. It basically says this claim is based on what some unnamed customer saw.

What is true grit when it comes to performance?

True grit is participating in an industry standard benchmark.

True grit is producing a white paper with detailed performance testing results.

True grit is publishing real results from a proof of concept at a client.

True grit is not saying you are x times faster than something based on what someone told you.

“The wicked flee when none pursueth.”

************************************************

The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

technorati tags: IBM, systems, performance, workload, HP,appliance,Microsoft,data warehouse,True Grit,SQL Server,benchmark,Enterprise,platform,data center,publication,benchmarking