Thoughts on SAP HANA’s Availability on Power Systems

Edit: Still the best place to run it.

Originally posted January 26, 2016 on AIXchange

I assume you’ve heard by now that SAP HANA is available on IBM Power Systems.

With this release, SAP HANA on IBM Power Systems is supported for customers running SAP Business Warehouse on IBM Power Systems. This solution is available on SUSE Linux, for configurations initially scaling-up to 3TB. This is available within the Tailored Datacenter Integration (TDI) model, which will enable customers to leverage their existing investments in infrastructure.

A large pharmaceutical company had a 100X improvement in query performance, and an 88% reduction in ETL execution time compared to what they had running the same workload on their legacy database. In another instance, a large energy provider saw a 95% reduction in query response times compared to running those same queries against a legacy database.

There was also this interesting post from Alfred Freudenberger, North America Power Systems sales executive, IBM Power Systems for SAP Environments. Some highlights:

In November, 2015, SAP unleashed a large assortment of support for HoP. First, they released a first of a kind support for running more than 1 production instance using virtualization on a system. For those that don’t recall, SAP limits systems running HANA in production on VMware to one, count that as 1, total VMs on the entire system.

SAP took the next step and increased the memory per core ratio on high end systems; i.e. the E870 and E880, to 50GB/core for BW workloads thereby increasing the total memory supported in a scale-up configuration to 4.8TB.

What does this mean for SAP customers? It means that the long wait is over. Finally, a robust, reliable, scalable and flexible platform is available to support a wide variety of HANA environments, especially those considered to be mission critical. Those customers that were waiting for a bet-your-business solution need wait no more.

Here’s another perspective:

In that blog, he did an excellent job of explaining how technical enhancements at a processor and memory subsystem level can result in dramatic improvement in the way that HANA operates. Now, I know what you are thinking; he likes what Dr. Plattner has to say about a competitor’s technology? Strange as it may seem, yes … in that he has pointed out a number of relevant features that, as good as Haswell-EX might be, POWER8 surpassed, even before Haswell-EX was announced.

All of these technical features and discussion are quite interesting to us propeller heads. Most business people, on the other hand, would probably prefer to discuss how to improve HANA operational characteristics, deliver flexibility to respond to changing business demands and meet end user SLAs including response time and continuous availability. This is where POWER8 really shines. With PowerVM at its core, Power Systems can be tailored to deliver capacity for HANA production to ensure consistent response time and peak load capacity during high demand times and allow other applications and partitions to utilize capacity unused by the HANA production partition. It can easily mix production with other production and non-production partitions. It features the ability to utilize shared network and SAN resources, if desired, to reduce data center cost and complexity. POWER8 delivers unmatched reliability by default, not as an option or a tradeoff against performance.

By comparison, SAP has only one certified benchmark for which HANA systems have been utilized called BW-EML. Haswell-EX cpus were used in the 2B row Dell PowerEdge 930 benchmark and delivered an impressive 172,450 Ad-hoc Navigation Steps/Hr. This is impressive in that it surpassed the previous IvyBridge based benchmark of 137,010 Ad-hoc Navigation Steps/Hr on the Dell PowerEdge R920, an increase of almost 26% which would normally be impressive if it weren’t for the fact that the system includes 20% more cores and 50% more memory. By comparison, POWER8 delivered 192,750 Ad-hoc Navigation Steps/Hr with the IBM Power Enterprise System 870 or 12% more performance with 45% fewer cores and 33% less memory resulting in twice the performance per core.

Finally, check this out:

Take for example, the SAP BW Enhanced Mixed Load (BW-EML) Standard Application Benchmark on four-socket servers. This benchmark has documented that POWER8 cores out-perform Haswell EX cores by two times while running SAP HANA analytics workloads.

That’s not even the best part. I have been impressed with the capability of the POWER8 line to scale to much higher core counts. The scaling ability of POWER8-based servers is key to both enabling workload consolidation and removing the need to break large datasets across multiple nodes which would otherwise negatively impact the latency of queries.

Of course, the performance and scaling attributes of Power Systems are only part of the story. The enterprise-grade resiliency and flexible capacity features that Power Systems are known for become increasingly important to clients as they deploy in-memory analytics capabilities. SAP HANA availability across the entire POWER8 product line allows our existing clients to quickly and easily extend these benefits to HANA by simply allocating additional capacity on their infrastructure.

We continue to collaborate and partner with SAP to optimize and tune in-memory database performance for Power Systems, including further leveraging of SIMD instructions, transactional memory, and other acceleration features in POWER. With the successes we’ve seen in running these challenging in-memory workloads on our enterprise-class servers, we’re off to a great start, one that clients are sure to find highly beneficial while balancing the explosion of data in their day to day business operations.

If your enterprise is considering deploying SAP HANA, have you thought about running it on Power Systems?