eG Monitoring
 

Measures reported by pSeriesCpuTest

This test reports the quantity of allocated and unallocated physical CPU resources of the pSeries server, and the percentage of allocated CPU that has been utilized by the LPARs on that server. In the process, the test helps assess the impact of the guest CPU usage on the physical CPU resources of the pSeries server. If the server experiences a CPU contention, then this test will enable you to figure out whether the resource-crunch is owing to improper CPU allocation to the LPARs, or the existence of one/more CPU-intensive processes on the LPARs.

Measurement Description Measurement Unit Interpretation
Installed_proc_units The number of processing units installed on the pSeries server Number  
Avail_proc_units The number of free processing units on the pSeries server Number Typically, a large number of free processing units implies that more logical partitions can be configured on the server. If the value of this measure is very low, it could mean that almost all the CPU resources have been allocated to the LPAR guests. You can use the detailed diagnosis of the Used_proc_units measure to accurately identify the LPAR that has been allocated the maximum CPU.
Used_proc_units The total number of processing units allocated to the LPAR guests on the pSeries server Number If the value of this measure is very high or is close to the value of the Installed_proc_units measure, it could mean that almost all the CPU resources of the host have been allocated to the LPAR guests. In this case, you can use the detailed diagnosis of this measure to understand how many processing units have been allocated to each LPAR, and thus accurately identify the LPAR that has been allocated the maximum CPU.
Utilize_proc_units The percentage of physical CPU resources allocated to the LPAR guests Percent If the value of this measure is very high or is close to 100%, it could mean that almost all the CPU resources of the host have been allocated to the LPAR guests. In this case, you can use the detailed diagnosis of this measure to understand how many processing units have been allocated to each LPAR, and thus accurately identify the LPAR that has been allocated the maximum CPU.
Tot_cpu_consumed The total number of allocated processing units used by LPAR guests Number The detailed diagnosis of this measure reports the number of physical processors consumed by each LPAR guest on the pSeries server. In the event of a CPU contention, you can use this information to accurately identify the LPAR which is consuming the maximum CPU.
Cpu_utilize_allocation The percentage of allocated CPU utilized by the LPAR guests Percent A high value for this measure could indicate that one/more LPARs have resource-intensive processes executing on them.
Physical_proc_utilize The percentage of physical CPU resources utilized by the LPAR guests Percent A high value for this measure could indicate that one/more LPARs are over-utilizing the physical CPU resources.
Tot_phy_processors Indicates the total number of physical processors installed on the pSeries server. Number  
Dedicated_proc The total number of dedicated processors used by the LPAR guests Number A dedicated processor partition has an entire processor that is assigned to a partition. These processors are owned by the partition where they are running and are not shared with other partitions. Also, the amount of processing capacity on the partition is limited by the total processing capacity of the number of processors configured in that partition, and it cannot go over this capacity (unless you add or move more processors from another partition to the partition that is using a dynamic LPAR operation).
Shared_processors The total number of shared processing units used by the LPAR guests Number A partition that has its processors virtualized from a pool of shared physical processors is a shared processor partition. When the processors are in the shared processing pool, an uncapped partition that needs more processing power can use the idle processing resources in the pool.