Optimize the Value of Your Mainframe

Editor's Notes

• #6: Why does that matter? Well….it turns out that mainframes are still the backbone for the biggest organizations in the world 71% of the fortune 500 rely on the mainframe for their mission critical transactional systems They span every vertical from FinServ to Insurance to Retail When talking to these organizations, it’s not unusual to hear that up to 80% of their corporate data originates on the mainframe. That’s Big Data. And organizations cannot afford to neglect it.
• #7: Most large enterprises have made major investments in data environments over a period of many years - legacy data can provide a treasure-trove of information that can transform your business when leveraged via a streaming paradigm These environments contain the data that these business run on and that today power the strategic initiatives driving the business forward – machine learning, AI and predictive analytics Legacy platforms (mainframe and IBM i) continue to adapt with each new wave of technology and are not going away anytime soon Integrating legacy data into your projects brings several advantages such as: Connect applications together, leveraging the existing transactional capabilities of the current application platform, and the wealth of new capabilities of the cloud Feed analytics with up-to-date information so your business runs on current insight Port workloads to less-expensive, strategic platforms
• #14: Eliminate Risk Developed to provide rapid /efficient migration between IMS and Db2 Applications remain unchanged Set of powerful mapping and migrations tools Stop worrying about keeping IMS skills and using third party IMS tools Increased Access to Information Data can be locked up in IMS Db2 is more accessible solution Reduced software expenses by eliminate IMS Transparent Migration No need to rewrite software Applications continue to issue requests as before Proven Solution Many reference-able customers success stories
• #23: Q: [Bill} Thanks for joining us today Denise. Why don’t we start off with you telling us a little about your role here at Precisely? A: [Denise] Direct from the university, I started my career at a state agency, learning MVS systems programming skills with a small but highly intelligent group of people. They mentored me for several years, and I learned the basics of maintaining several systems, but then focused on Db2. From there, I became a production and application Db2 DBA and then transitioned to a vendor company. I am fortunate enough to have held positions in technical support and sales engineering, where I really enjoyed being a customer advocate and internal liaison across the different departments. This was a natural segue into my current experience in Product Management, where I’ve been for several years. I joined Precisely in early 2020, and I’m currently responsible for the mainframe and capacity management products. I love working with customers, listening to their challenges and formulating solutions that meet their needs. In order to do that, of course, I need to work closely with sales, support, engineering, marketing, and of course, our IBM partnership feeds into that collaboration as well.
• #24: Q: [Bill] You mentioned you need to work closely with IBM. Tell us a little about the interactions you have with IBM people or departments. A: [Denise} We have a very close relationship with IBM – the Db2 Utility team, the z/OS hardware architects, and the DFSMS engineering team know us very well. We have been working with the Db2 Utility team for almost 10 years to develop the IBM Db2 SORT product together. About 5 years ago, we started work with the z/OS Poughkeepsie team and hardware architects for z15’s integrated accelerator for Z SORT research. And finally, about 2 years ago, we started work with the DFSMS team to implement the EXCP encryption API for basic and large format datasets. This collaboration allows us to provide a performant solution for sorting with encryption (more on that later). We will continue to work with IBM in the future to ensure that we take advantage of any opportunities provided by their engineers.
• #25: Q: [Bill] Thanks Denise… obviously we value our close working relationship with IBM very highly. I would like to move us into the meat of our discussion today. Here at Precisely, we have number of products designed to help customers get the most from their IBM Z platform. Across our portfolio, what projects are you working on that will help customers as they continue to optimize their IBM Z Platform environments? A: [Denise] Over the past few months, we’ve delivered a couple of major enhancements to assist our customers who want to process encrypted datasets and take advantage of some new hardware on the z15 machine
• #26: Q: [Bill] Q: [Bill] So for the project to improve sorting for encrypted data sets with pervasive encryption, could you explain in details why our customers need that improvement, what solution has been implemented into our products and any performance benchmark information you can share here? A: [Denise] Let me first explain our need to support the encryption initiatives of our customers. Regulatory requirements such as GDPR and CCPA, are designed to protect data and safeguard privacy. Loss of data or compromised information can come with high penalties, and new innovations to assist with this data protection have been implemented to fortify security. The IBM Z Pervasive Encryption solution is a method to enable extensive encryption of data in-flight and at-rest to meet these protection standards. This solution is enabled by administrative policy controls and is designed to be application transparent, without requiring application changes. Data set encryption provides data security at the data set level using DFSMS access methods. This system-wide solution is more cost effective than traditional software encryption solutions. And DFSMS access methods provide data set encryption for sequential, basic, large, and extended format datasets. The challenge to implementing data encryption is it consumes processor cycles, so it doesn’t come without penalty. And although mainframe customers love the pervasive encryption approach, no one likes the additional resource consumption. For Syncsort MFX users, if the input or output data set is encrypted, BSAM must be used instead of our high performant low level IO access methods, and there is an extra cost from that perspective. Last year, IBM’s DFSMS team developed an EXCP encryption API solution called IGGENC to help vendors like us use our low-level IO for encrypted data sets and improve encryption performance. DFSMS splits the encryption/decryption processing from the I/O processing, so we will use our low-level IO methods to read and write the data sets and use IGGENC to encrypt and decrypt data on the zIIP processors. This will significantly reduce the CPU cost and elapsed time. We’ve seen some great performance improvements from our preliminary benchmark testing. For Syncsort MFX, we have seen up to 45% CPU and 40% elapsed savings, and for ZPSaver we have seen up to 80% CPU and 40% elapsed time savings when processing encrypted, basic and large format datasets.
• #27: Q: [Bill] You also mentioned you are working on a project to improve sorting performance using the integrated accelerator for Z SORT. What is the integrated accelerator for Z SORT? Any performance improvement have you seen by leveraging Z SORT technology? A: [Denise] The IBM Integrated Accelerator for Z Sort is a new coprocessor designed for the z15. Z Sort can help reduce CPU usage and improve elapsed time for eligible workloads by speeding up sorting, shorten batch windows, and improve select database functions. The challenge to taking advantage of this new hardware is that customers need our utilities, Syncsort MFX and its zIIP-offload capabilities, to optimize sorting workload and achieve performance gains. As I mentioned before, we worked closely with the IBM z/OS Poughkeepsie team and hardware architects for the sort accelerator. We have developed new algorithms in Syncsort MFX to take advantage of the coprocessor and with the new algorithms, our customers can see dramatic improvements to batch sort job performance. In the Precisely lab, we conducted some benchmarks in several modes to compare performance metrics with and without the sort acclerator. We have seen average savings of 26% CPU and 19% Elapsed time savings using the accelerator, however, ZPSaver and its zIIP offload capabilities still offer superior performance advantages. We also collaborated with the Db2 Utilities team to develop Z Sort enablement in Db2 Sort – used in the LOAD, REBUILD INDEX and REORG utilities. The support was delivered at the end of 2020, and Db2 Sort customers can see both CPU and elapsed time benefits up to 37% better than using DFSORT (which only supports the Db2 REORG utility).
• #28: Q: [Bill] Those sound like really impactful enhancements for our IBM Z Platform customers. Precisely has a long history … over 50 years… of software solutions for mainframe customers? As you look at continuing that long support, what are some of the areas of innovation you are looking forward to? A: [Denise] We are always assessing performance and efficiency improvements to make to our products, so we will be focusing on these in the future. In addition to that, as new technologies come from IBM, we will examine them to see if we can exploit them for further performance boosts. We’re currently working with IBM to address similar challenges this year and will continue to collaborate with them to help our mutual customers. By the way, Bill, we have spent the majority of time discussing MFX, but I will remind our audience that we have performance and efficiency solutions that address Db2, IMS, IDMS, and Network challenges for the z/OS platform. Ironstream and Connect will solve problems for our mainframe clients as well.