The company made this announcement in concert with the launch of a number of other virtual machine (VM) types that are specifically geared toward running high-memory workloads — and the standard use cases for this is running the SAP Hana in-memory database service.
The execution time variation of tasks is efficiently captured by a memory access workload model.
Memcached is memory-bound workload, so disk IO performance-per-watt characterization may not be applicable for Memcached.
There is a big split between CPU-bound versus memory-bound workloads.
Implementation is performed on Xen 4.1.4 hypervisor and evaluation is performed under various memory-intensive workloads.
LRU policy is also susceptible to memory-intensive workloads where a working set is greater than the available cache size.
This has come at a time with the push for faster and lower power computing capabilities that continue to grow rapidly due to AI, AR, big-data analytics and other memory-starved workloads.
The demand for these processors are due to the inability of the conventional processor to meet higher performance memory-intensive workloads, which in turn may lead to high cache miss rates.
The pre-copy approach synchronizes the VM states at both source and destination sides that increase the network traffic, application downtime, and migration cost especially for memory-intensive workloads.
