HP Insight Control - Manual (Page 52)

are busy, the metric reads 25%. Average Processor Busy % can be viewed as the fraction of the time
spent doing useful work.
Each processor is assigned an idle thread in the idle process consuming unproductive processor cycles not
used by another thread. Some processors might be more heavily loaded than other processors. In this case,
the total processor time percentage is the average of the loads on each processor.
•
Busiest Processor Utilization %—The average utilization of the logical processor with the highest
utilization. This value is equal to the Average Processor Utilization % if the server is using one processor
core.
•
Processor Busy %—The percentage of time that the processor is executing a non-idle thread.
•
Context Switches/Sec—The number of thread context switches at which all processors on the server
are switched from one thread to another each second. Context switches occur when a running thread
voluntarily relinquishes the processor, is preempted by a higher-priority ready thread, or switches
between user mode and privileged (kernel) mode to use a subsystem service.
•
Interrupts/Sec—The average number of hardware interrupts the processor is receiving and servicing
each second.
Average Processor Utilization % and Highest Processor Utilization % are used to determine processor
performance.
Processors Inventory
•
Processor Support—Lists the number of processors supported by the server
•
Processors—Displays the number of processors installed on the server and a summary of the processors
(type, speed, and cache size)
Memory
The following information is provided for memory.
Memory Status
•
Available MBytes—The amount of memory that is not currently allocated to any process or is unused.
A low Available MBytes value can indicate memory allocation bottlenecks.
•
Page Reads/Sec—The number of times the disk was read to retrieve pages of virtual memory necessary
to resolve page faults each second. Multiple pages can be read during a single disk read operation.
•
Pages Input/Sec—The number of pages read from the disk to resolve memory references to pages that
were not in memory at the time of the reference. This counter includes paging traffic on behalf of the
system cache to access file data for applications. It is important to observe this counter if you are
concerned about excessive memory usage, or thrashing, and the excessive paging that can result.
•
Page Faults/Sec—The average number of page faults each second. A page fault occurs when a process
refers to a virtual memory page that is not in its working set in main memory. A page fault does not
cause the page to be fetched from disk if that page is on the standby list and is already in main memory
or if it is in use by another process with which the page is shared. There are two types of page faults:
•
Hard Page Fault—The most expensive in terms of system resource usage, occurring when a missing
page must be retrieved from the disk
•
Soft Page Fault—Generally not considered a source of memory bottlenecks, occurring when the
missing page is not in the current working set but is located elsewhere in memory and easily
brought into the working set
•
Hard Page Faults %—The ratio of page faults per second to pages input per second. This value is a
primary indication of memory bottlenecks.
Memory performance is determined primarily by the rate at which memory is swapped out to disk. Page
Reads/Sec is the primary factor in determining memory performance issues, but the Hard Page Faults %
and Available MBytes are also considered.
52 HP Insight Control performance management measurement parameter matrix