UNIX Resource Monitoring

1. The indicator disk exchange rate in UNIX resource monitoring (the same as in Windows OS), if the parameter value has been high, indicates a problem with I/O. Consider replacing a faster hard drive system
2. The indicator memory paging rate (Paging rates) in UNIX resource monitoring, if the value is occasionally higher, indicates that the thread is competing for memory at that time. If it continues to be high, then memory can be a bottleneck. It is also possible that the memory access hit ratio is low.

CPU-related metrics

? CPU utilization (System Mode CPU Utilization +user Mode CPU utilization)--CPU utilization

CPU utilization, which is the percentage of time that the CPU is used. The maximum limit of the indicator is 85%, if the upper limit is exceeded, the system CPU becomes a resource bottleneck, and the rational use range of the indicator is 60%~70%, if the indicator value is lower, it means the waste of resources.

CPU utilization = System CPU Utilization + user CPU utilization? Average load--Average Load

Average number of processes in the "Ready" state at the same time in the last 1 minutes

In general, as long as the current number of active processes per CPU is not greater than 3 then the performance of the system is good, if the number of tasks per CPU is greater than 5, then the performance of this machine is a serious problem. For example, assuming that the system has two cpu,lr monitored with an average load of 8.13, the current number of tasks per CPU is: 8.13/2=4.065. Does this mean that the performance of the system is acceptable? Context Switches Rate

--Context exchange rate

Context Switches/sec refers to the overall rate at which all processors on a computer are transitioning from one thread to another. Context conversion occurs when a running thread automatically discards the processor, either by a higher-priority-ready thread or by converting between user-mode and privileged (kernel) mode to use execution or sub-system services. It is the total number of thread:context switches/sec of all threads running on all processors on the computer and is measured in number of conversions. Context conversion counters on system and thread objects

Frequent page exchanges will degrade system performance. Reducing page swapping will significantly improve system responsiveness? Interrupt rate--Interrupt Rate

Number of device interrupts per second

Memory-related metrics

? Paging Rates (page-in rate +page-out)--memory page switching speed

Number of pages written and read from physical memory per second

If the value is occasionally higher, it indicates that the thread is competing for memory at that time. If it continues to be high, then memory can be a bottleneck? Swap-in rate/swap-out rate--Process-to-swap/process-out switching number of processes input/output

If the swap partition process is frequently exchanged, it also reflects the system memory resource tension.

Physical Disk related metrics

? Disk Rate

--Disk transfer rate

Transfer speed when the physical disk interacts with memory

Network related indicators

? Incoming Packets Rate/outgoing Packets Rate

--Packet receive speed/packet transmit speed

UNIX Resource Monitoring