zVRM
| The Velocity Software Resource Manager | zVRM is a real-time facility to manage Linux storage/ram resources and virtual CPU counts, both to meet current workload requirements |
Traditional Linus servers are created very large to ensure that they meet resource requirements as workloads grow. In the z/VM virtualized environment, this becomes a costly objective both in real storage requiremnets, zVRM can reduce the impact on real resources by comparing current requirements to what is available and adjust settings accordingly, allowing more to be done with less hardware.
zVRM manages two resources - Storage and CPU:
- Storage Management - zVRM uses CMM (Collaborative Memory Management) to monitor storage that isn't actively being used and slowly return it to z/VM - without interruption to the Linux server. If the workload grows, storage is returned immediately to the server.
- CPU Management - When not immediately necessary, a lower number of virtual CPUs allows for less spin locks and better performance. A utilization target (30% is the default) is set via zPRO which will allow under utilized virtual CPUs to be varied off. They are varied back on when needed.
zVRM Management:
zVRM management is done via zPRO. This illustration shows
a status for both Storage and CPU, along with commands to
adjust levels.
Verifying Results:
When using zVRM, the results are easy to see. The following command
can be done to see the savings of using ZVRM.
This command is done on the ZVRM machine.
CP SMSG * QUERY SAVINGS
Real Storage Savings by node group
NodeCls: RANCHER 2.1G
NodeCls: REDHAT 316M
NodeCls: SUSE 190M
NodeCls: TheUsrs 1.0G
Total VCPUs OFFLINE: 2
This shows the amount of storage saved in each Node class and the amount of VCPUs that are offline.
