InfoScale™ Operations Manager 9.0 User's Guide

About write-back caching in SmartIO

SmartIO supports write-back caching for applications running on VxFS file systems. In this case, the application reads and writes are satisfied from the cache whenever possible. In write-back mode, the data is written to the SmartIO cache, and the write operation is marked as a success. At a later time, SmartIO transfers the data to the disk and flushes the cache area. Write-back caching expects to improve the latencies of synchronous user data writes. When write-back caching is enabled, read caching is implicitly enabled. Reads are satisfied from the cache if possible, and the file system transparently loads file data into the cache. Both read and write-back caching may be enabled for the same file at the same time.

If a cache device fails, a file that is cached in write-back mode may not be completely present on the disk. SmartIO has a mechanism to flush the data from the cache device when the device comes back online. Storage Foundation Cluster File System High Availability (CFS) provides additional protection from data loss with cache reflection. In the case of CFS, when write-back caching is enabled, SmartIO mirrors the write-back data at the file system level to the other node's SSD cache. This behavior, called cache reflection, prevents loss of write-back data if a node fails.

If a node fails, the other node flushes the mirrored data of the lost node as part of reconfiguration. Cache reflection ensures that write-back data is not lost even if a node fails with pending data.

To enable read, or write-back caching on a VxFS file system, you can select appropriate check boxes while creating a file system and mounting or remounting a clustered or non-clustered file system. You can then also select separate cache areas to enable read and write-back caching.