Abstract: Described herein are techniques to decompose a measurement of the latency experienced by a virtual machine into its additive components (e.g., host latency, kernel latency, network latency and storage latency). The host latency may be determined as the aggregate latency reported from the virtual disk of the virtual machine minus the aggregate latency reported from the datastore on which the virtual disk is stored. The network latency may be determined as the device latency reported from the datastore minus the storage latency reported by a storage system. Various sensor measurements (e.g., aggregate latency reported from the virtual disk and/or datastore) may be first pre-processed to compensate for non-idealities before being combined with other sensor measurements.

Abstract: A hyperconverged data storage system including a storage array. A first node includes hardware and a virtualization layer supporting guest virtual machines running first applications. An active first virtual storage controller executing in the first virtualization layer is configured for handling IOs accessing the storage array. A second node includes hardware and a second virtualization layer supporting guest virtual machines running second applications. A second virtual storage controller executing in the second virtualization layer operates in a standby mode to the first virtual storage controller. An internal communication network facilitates communications between the first node and the second node. The first virtual storage controller when operating in active mode is configured for handling IOs originating from the first applications and the second applications.