Solaris

VMSTAT Resource Bottleneck Threshold Rules-of-thumb for Solaris

For example to see system activity for 20 seconds with a 5 second reporting interval use:

kthr memory page disk faults cpu
r b w swap free re mf pi po fr de sr m0 m1 m2 m1 in sy cs us sy id
7 3 0 192184440 56771544 9667 7369 14830 1125 1125 0 0 21 18 18 0 17843 371949 23866 42 17 41
2 2 0 187380248 53466360 37064 8896 31638 113 113 0 0 13 12 12 0 31563 708093 42169 40 41 20
1 1 0 187367928 53452864 29771 5974 29165 141 141 0 0 7 7 7 0 31795 774360 42575 37 37 27
7 2 0 187330624 53422136 31521 17863 30731 245 217 0 0 18 18 17 0 26215 625841 37558 44 46 11
0 2 0 187357536 53435712 32837 3354 31817 56 54 0 0 11 10 10 0 28395 894454 38733 30 31 40
0 4 0 187351992 53434424 32517 3214 32138 136 136 0 0 8 7 7 0 29851 880658 40007 29 32 39


In the process (kthr) group of statistics, there are two important statistics:

• r is the number of processes in the run-queue
• b is the number of processes blocked for resources I/O, paging, so forth

In the memory group of statistics, the important statistic is:

• sr is the number of pages scanned and can be an indicator of a RAM shortage.

The CPU group of statistics give a breakdown of the percentage usage of CPU time. On multi-processing systems, this is an average across all processors:

• us is the percentage of user CPU time
• sy is the percentage of system CPU time

CPU Bottleneck

• RULE 1: A significant CPU bottleneck occurs if r > 2 * #CPU or %CPU > 75%
• RULE 2: As critical bottleneck occurs if sy > 0.25us and/or %CPU > 85%

Disk Bottleneck

• RULE 3: A significant bottleneck threshold occurs if b approaches r
• RULE 4: A critical bottleneck threshold occurs if b => r

Memory Bottleneck

• RULE 5: A significant bottleneck threshold occurs if sr > 200 scans/second
• RULE 6: A critical bottleneck occurs if sr > 300 scans/second

This rule could indicate thrashing because active and inactive pages will be stolen from the Process Working Set.