The 'load average' is the average number of processes (programs) that were waiting to run during the last period. Our long term averages use a five minute average. The daily analysis uses the one minute average.
Load Running Wed Peak Wed Average 24 hr 24 hr (1) Peak ========================================= 1 20.1 16.4 0.0 0.1 2 14.7 8.2 0.8 4.9 3 15.5 9.2 9.9 14.2 4 13.4 11.6 15.4 12.8 5 9.3 12.0 16.5 12.1 ----------------------------------------- % < 5 = 73.0 57.4 42.6 44.1 ----------------------------------------- % > 5 = 27.0 42.6 57.4 55.9 ----------------------------------------- <snip...> Note: (1) - This is the running average for Wed. peak usage periods since logging started.Again in the above example, during the Wed. peak utilization period, 55.9% of the one minute load average readings were over 5.0. (...a very bad day)
The table data represents the distribution of load averages for:
Load Running Sat Peak Sat Average 24 hr 24 hr (1) Peak ========================================= < 1 66.1 69.4 69.5 63.5 2 17.8 16.5 16.8 24.2 3 6.7 6.5 6.2 11.0 4 3.2 2.9 2.8 1.4 5 1.8 1.5 1.4 0.0 ----------------------------------------- % < 5 = 95.6 96.8 96.7 100.1 ----------------------------------------- % > 5 = 4.4 3.2 3.3 -0.1 ----------------------------------------- 6 1.1 0.9 0.9 0.0 7 0.7 0.6 0.6 0.0 8 0.5 0.4 0.4 0.0 9 0.4 0.3 0.3 0.0 10 0.3 0.2 0.2 0.0 12.5 0.5 0.3 0.3 0.0 15 0.4 0.1 0.2 0.0 17.5 0.3 0.1 0.1 0.0 20 0.1 0.0 0.1 0.0 25 0.1 0.1 0.2 0.0 30 0.0 0.0 0.0 0.0 < 40 0.0 0.0 0.1 0.0 40+ 0.0 0.0 0.0 0.0 ========================================= Total 100.0 99.8 100.1 100.1 -----------------------------------------
This graph shows the long term distribution analysis of load averages on the CCN 'halifax' machine. The display includes:
This graph shows: