Sometimes thereโs power in numbers, and todayโs number is 17. The number 17 is so many things; it is a prime number, the number of elementary particles in the physics standard model, a classic Alfred Hitchcock film, and the number of championships won by the Boston Celtics. But for HPE, Intel, and Splunk, 17 is the throughput increase achieved for Splunk indexing per server compared with a traditional approach.
For those who donโt know, Splunk provides industry leading tools and technologies to collect, index, search, and provide insights on data. Splunkโs Data-To-Everything Platform removes the barriers between data and action.
In May 2020, Hewlett Packard Enterprise (HPE) and Intel partnered with guidance from Splunk engineering to apply innovative technologies to Splunkโs software stack. These technologies included 2nd Gen Intel Xeon Scalable processors, Intel 3D NAND NVMe (non-volatile memory express), and SSD drives in HPE ProLiant and Apollo servers. The result? We were able to increase per server ingest rates by more than 3x1. You may be wondering how we achieved such a large increase. We discovered Splunkโs indexing and search functions scale with Intel Xeon cores and frequency--providing faster insights and results.
But that left us wondering, could we do more?
Enter the power of HPE Ezmeral Container Platform. By using the Splunk Operator for Kubernetes and the HPE Ezmeral Container Platform, we added the agility to deploy in minutes plus the ability to independently scale up and out to further optimize the server utilization -- all while bringing new levels of platform administration ease.
To get the most out of the Splunk Operator for Kubernetes, we deployed Splunkโs innovative SmartStore to offload the long-term storage onto the HPE Scalable Object Storage system utilizing Scality RING. Scality RING provides a massively scalable, geographically dispersed object storage system to house the multiple petabytes of data that enterprises require.
Next, we took it a step further, leveraging HPE GreenLake to deliver this Splunk optimized solution as a fully managed and supported Platform as a Service (PaaS). HPE manages everything up through the container and storage layer for you -- thereโs no patching, performance tuning, or maintenance required. And you donโt need hard to find Kubernetes skills; HPE takes care of it.
The Power of the Partnership
By packing 12 Splunk virtual container instances on each physical DL380 server, we were able to improve the indexing rate by up to 17x and utilize all the CPU cores and memory resources in the system.(1) The tight collaboration between HPE, Intel, Scality, and Splunk brings dark data to light by making it simple to collect, analyze, and act upon the untapped value of the Big Data generated by your technology infrastructure, security systems, and business applicationsโgiving you the insights to drive operational performance and business results.
Clearly, there is power in partnership. Without the contributions from each company, these amazing results wouldnโt be possible. Learn more from our session replay at Splunk .conf20, listen to the Splunk-HPE podcast, download the solution brief, and join us on Dec 9th for our HPE GreenLake Day.
(1) Appendix 1. Test Configs: Test by Intel, HPE, and Splunk as of 5/01/20. 10-node HPE DL380, 2x Intel Xeon Platinum 6254 Processor, 28 cores HT On Turbo ON, Total Memory 512 GB (16 slots/32GB/2933 MHz), CentOS 7.7, Network: 20 x HPE Ethernet 10/25Gb 2-port 640SFP28 NIC (2each), Splunk 8.0.3, 7-Indexers, 3-Search Heads, HPE Ezmeral Container Platform. For more complete information about performance and benchmark results, visit www.intel.com/benchmarks.
About the authors:
Elias Alagna is a Chief Technologist in the Hewlett Packard Enterprise North America Hybrid IT office of the CTO. His technical leadership includes working with commercial, government, and education entities across a broad set of products and services. Areas of expertise include ERP system architecture, HPC, business continuity and disaster recovery, OLTP and BIDW database solution architecture and storage hardware and software solutions.
Murali Madhanagopal is an accomplished product and solutions specialist with over 20 years of experience in evaluating and implementing new technologies. He is skilled in building strategic partner relationships, product management, and competitive analysis across a variety of industry segments including AI, graphics, workstations, high performance computing, and gaming. He has also been a frequent speaker at numerous events such as IDF, Siggraph, NAB, Autodesk University, Citrix Synergy and VMware VMworld.
Notices & Disclaimers
Software and workloads used in performance tests have been optimized for performance only on Intel microprocessors.
Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/benchmarks.
Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available โupdates. See backup for configuration details. No product or component can be absolutely secure.
Your costs and results may vary.
Intel technologies may require enabled hardware, software or service activation.
ยฉ Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others. โ
