GigaSpaces Flash Memory Summit 2014
Download as PPTX, PDF1 like764 views
Shay Hassidim, Deputy CTO of GigaSpaces, discusses the capabilities of their ultra massive application storage solution, XAP MemoryXtend, which utilizes high-density SSD servers for managing large volumes of data efficiently. The presentation highlights the advantages of speed, scalability, and simplicity in data processing, benchmarking its performance against RAM and other data storage solutions. Key points of consideration include SSD price-performance metrics and architectural considerations for optimal usage in real-time applications.
GigaSpaces Flash Memory Summit 2014
- 1. Ultra Massive application storage capacity for real-time applications A True Limitless Capacity Data Grid Shay Hassidim , Deputy CTO , GigaSpaces Flash Memory Summit 2014 Santa Clara, CA 1 shay@gigaspaces.com @ShayHassidim
- 2. About myself – Shay Hassidim • GigaSpaces Deputy CTO • More than 20 years of SW development • Java , .Net , C++ , DB , Dist. Systems , Cloud … • 11 years with GigaSpaces • From the time we have been startup at the garage… • Oversight the entire technical operations within the Americas, Customer focused. • Located in GigaSpaces NYC HQ Flash Memory Summit 2014 Santa Clara, CA 2
- 3. GigaSpaces Business Card 3 HealthcareTravel & Trans. Founded 2000 300+ Direct Customers 30,000 Sites running GigaSpaces 75+ Cloud Customers 25+ ISVs
- 5. What they all want? – The 3 S 5 Speed Scalability Simplicity
- 6. The mantra… Do more with less $ 6
- 7. What's your largest in-memory compute data grid? 7
- 8. SSD is Everywhere - Big Time and it’s Not That Expensive! 8 http://www.extremetech.com/computing/153879-storage-pricewatch-hdds-back-to-pre-flood-prices-ssds-grow-as-gb-holds-steady
- 10. What’s the Motivation Moving into a SSD-based Data Grid? 10
- 11. Data Lookup Pattern Challenge 11 http://www.contaque.com/contaque/blogs/ - Posted by : Abhay Gupta http://www.sbp-romania.com/Blog/2014/03/05/sql-vs-nosql.aspx
- 12. Data Consistency Challenge 12 http://smist08.wordpress.com/2012/01/28/nosql-for-erp/
- 14. What is XAP MemoryXtend ? XAP MemoryXtend manages large amount of data in a grid configuration using high density SSD capacity servers. Built on top of SanDisk ZetaScale™ 14
- 15. XAP MemoryXtend Position 15 Big Data IMDB IMDG RDBMS RT Analytics Applications Complexity
- 16. 16 Typical Usage Scenario - RT Big Data Event Stream Cloudify Elastic management Real time batch Cloudify Elastic management XAP In-Memory elastic processing - Counting, Aggregating , Validating … Multi TB capacity- – RAM +SSD Storage User backend environment Multi PB capacity - HDD Storage RAM + SSD Open API Open API
- 18. Tier 1 Bank eCom Current Architecture Cannot perform well due-to complex data model 18 Non- Scalable
- 19. XAP SSD Usage Scenario - Mainframe offload Architecture No Oracle DB anywhere , Less Load on the Mainframe !
- 20. Performance Benchmark 20 SSD is slower than RAM - No surprise! * The benchmark was running on HP DL 380 server with 2 sockets 2.8GHz CPU with total 24 cores, 148G DRAM , CentOS 5.8 ,2 FusionIO SLC PCIe cards with software raid 0. The payload is 1KB object size, Single String based key. Uniform read distribution. * Based on test conducted by SanDisk 339000 124000 1127000 242000 0 200000 400000 600000 800000 1000000 1200000 RAM Write SSD Write RAM Read SSD Read TPS RAM XAP IMDG vs. SSD XAP IMDG Absolute Write/Read Benchmark Results No database on any HW platform can deliver such performance !
- 21. 16.95 62 56.35 121 0 20 40 60 80 100 120 140 RAM Write SSD Write RAM Read SSD Read Price-Performance Price-Performance XAP RAM IMDG vs. XAP SSD IMDG Price-Performance Benchmark 21 - We assume 1TB SSD price is $2K, 1TB RAM price is $20K. SSD is 3.6X better SSD is 2.1X better
- 22. An Important Difference between the RAM IMDG and SSD IMDG Benchmark… 22 The RAM data grid benchmark executed with 20GB total capacity where the SSD data grid benchmark performed with a total of 1TB data capacity! 1:50 Capacity Ratio!
- 23. Data Grid sizing example… HP DL 580 or Cisco UCS B420/B440 series, comes with built-in support for 2TB RAM and 8 SSD card slots. Intel , Sandisk, FusionIO or Tegile, offer up to 3TB SSD per card. You can have upto 24 TB SSD capacity per server. 4 servers delivers 8 TB data in RAM and 96 TB SSD! 231:10 ratio RAM:SSD Ratio
- 24. 24 Application In-Memory Data Grid GSCGSC Partition 1 Sync Replication BackupPrimary GSCGSC Partition n Sync Replication BackupPrimary Processing Processing XAP MemoryXtend Deployment XAP SSD Storage module running within each data grid instance XAP SSD Storage module running within each data grid instance XAP SSD Storage module running within each data grid instance XAP SSD Storage module running within each data grid instance Java/.Net/ C++/Scala/ Web service API
- 25. Raw Data XAP MemoryXtend Internal Architecture GSC Space Instance Heap (-Xmx) Perm Gem (-XXMaxPermSize) Stack (-Xss) Extra Memory high_watermark_percentage (95%) write_only_block_percentage (85%) write_only_check_percentage (76%) indexes , space class meta data , transactions , replication redolog , leases , statistics cache-entries-percentage (20%) blob-store-cache-size-MB (100MB) ZetaScale Off-heap in-process serialized LRU cache On-heap de- serialized LRU cache
- 26. Summary XAP brings Dramatic Cost Savings Server Consolidation 60-80% Reduced HW footprint 100X data per node From 30GB to 3TB! 28
- 27. XAP MemoryXtend Available for download from www.gigaspaces.com 30