Nutanix Hardware Platform * 3 x Intel 6-core Xeon E5-2620v2 processor * 200GB SSD; 2TB HDD Capacity
Core Data Services
MapReduce Tiering: Intelligent Distributed Data Tiering
Flash storage is used both as a cache and as a persistent data tier in a Nutanix system. Data is intelligently placed in the optimal storage tier — flash or HDD — to yield the fastest possible performance. MapReduce tiering technology ensures that the most frequently accessed data is available in the SSD or cache tier. As data becomes ‘cold,’ it is demoted into the higher capacity HDD tier. This is ensures that SSD and cache capacity remains available for new ‘hot’ data.
Nutanix incorporates the powerful Snappy compression algorithm to increase the effective storage capacity of the system up to 4X. Unlike traditional storage solutions that perform compression for entire LUNs or disks, Nutanix compresses data at the sub-block level for increased efficiency and greater simplicity. Chunk sizes up to 128 KB enable very high compression ratios.
MapReduce Compression: Distributed Post-process Compression
Administrators can set policies to run the Nutanix compression feature post-process to eliminate any performance impact on the write path. MapReduce Compression is distributed across all nodes in the cluster and scales out as the cluster grows.
Elastic Deduplication: Fine-grained Inline and Post-process Deduplication
Nutanix systems offer two flavors of data deduplication, together called Elastic Deduplication – Inline Performance Deduplication in the content cache (SSD and memory) reduces the cache footprint of the application working set yielding significant performance improvements, while global, post-process MapReduce Deduplication in the capacity tier increases the effective storage capacity of a cluster.
Data is fingerprinted using a SHA-1 hash on ingest, with fingerprint information stored in the Nutanix metadata layer. Deduplication operations are software-driven, and leverage the hardware-assist capabilities of the Intel chipset for SHA-1 hash generation for the fastest possible performance.
For applications with large common working sets, such as virtual desktop infrastructure (VDI) deployments, inline deduplication increases effective flash and memory resources by up to 10x and delivers nearly instantaneous application response times. MapReduce Deduplication is global and distributed across all nodes in the cluster, effectively minimizing any performance overhead.