The Activity page contains several charts.
To open the Activity page
Click Activity Summary | Activity.
Charts on the Activity page
|CPU Utilization||The CPU Utilization chart shows the CPU activity of the host machine. If the current activity reaches levels of greater than 100 or less than 0, run vmstat(1) to determine the reason for the erroneous values.|
The Run Queue chart shows the amount of CPU time that will be spent performing tasks. The value is expressed as a fraction.
Divide the value by the number of processors running. If the result of the calculation is greater than 1, you may need more processors.
The lines on the chart show the run queue averaged over 1, 5, and 15 minutes. If the value of the 1 minute line divided by the number of processors exceeds the value 1, there is merely a spike in activity. However, if the value of the 15 minute line divided by the number of processors exceeds 1, you may need more processors.
|Total Disk I/O||The Total Disk I/O chart shows the total number of I/O operations for each disk and NFS server.|
|Network Utilization||The Network Utilization chart represents the current network activity for the machine you are diagnosing. It shows the rate at which packets are being received by the machine and are being sent by the machine.|
The Paging chart shows the rate of data pages read from, and written out to, disk over time. Typically, high paging rates indicate insufficient system memory, a large number of processes, or a number of very large processes.
The unit of measure on the Y-axis is dependent on the Operating System.
|Free Memory||The Free Memory chart shows the amount of available physical memory in the machine. For Solaris, this is typically a low number. If necessary, the page-stealing daemon will seek out memory pages to re-claim them.|
The Disk page contains several charts.
To open the Disk page
Click Activity Summary | Disk.
To view charts on the Disk page
Right-click the Disk page and select View as Chart.
|Disk Reads||The Disk Reads chart shows the rate at which data is being read off each disk.|
|Service Time||The Service Time chart shows the sustained service time for all disks on the machine you are diagnosing. If the sustained service time of any of your disks exceeds 50 milliseconds, move your data onto the under-utilized disks.|
|Disk Writes||The Disk Writes chart shows the rate at which data is being written to each disk.|
|Queue Length||The Queue Length chart shows the average number of write operations waiting to be completed for each disk.|
|Wait Time||The Wait Time chart shows the amount of time that the queue for each disk is not empty. The time is expressed as a percentage of total time.|
|Busy||The Busy chart shows the amount of time each disk spends processing its transactions. The time is expressed as a percentage of total time.|
To view the Disk page as a table
Right-click the Disk page and select View as Grid.
The Memory page contains several charts.
To open the network page
Click Activity Summary | Memory.
Charts on the Memory page
|Physical||The Physical Memory chart shows the total physical memory (RAM) on the Unix host, and the amount of physical memory that is currently free.|
|Virtual||The Virtual Memory chart shows the total amount of memory in use on the Unix host. This includes physical memory plus space in the paging files. A steady increase in virtual memory usage can indicate that a process on the system has a memory leak.|
The Paging chart shows the rate at which pages are being swapped in and out of memory. The chart displays three data series:
A sustained high rate of paging can cause problems with overall system degradation due to disk thrashing and CPU load.
Note: Scan rate is not available for Linux.
|Cache||The Cache chart shows the percentage of recent file requests (read and write) that are satisfied by the memory cache, and that do not require a request to the paging areas on disk.|
The CPU page contains several charts.
To open the network page
Click Activity Summary | CPU.
Charts on the CPU page
|Total CPU Usage||The total CPU utilization for all processors on the Unix host.|
|CPU Usage by Processor||The CPU utilization for each processor on the Unix host. Each processor is represented by a single line on the chart, and by an item in the legend at the top right of the chart.|
|Run Queues||The number of threads (program execution units) that are waiting to run on the Unix host.|
The rate at which the Unix host has been processing context switches.
A context switch occurs when a processor switches from one thread to another. Context switches occur when a running thread voluntarily relinquishes the processor, is pre-empted by a higher priority ready thread, or switches between user-mode and privileged (kernel) mode to invoke a system service.