Figure 4-13. A vmstat report on a very active four-CPU core database server. This particular system has a very dynamic workload. This is why even with around 30% idle time, the run queue frequently exceeds the number of CPU cores.

Figure 4-14 is a sample sar -q report. The runq-sz column shows average CPU run queue, and the information is from the same system shown in Figure 4-13. Key to making this report useful is knowing how many CPU cores exist on the server. This Oracle database server has four CPU cores, so processes are frequently waiting for CPU resources. This is not what we want for an OLTP-centric system.

Do not confuse run queue length with the load average. The load average is available from v$osstat,4 the sar -q, and uptime commands, as well as in the /proc/loadavg file. The load average statistic is calculated differently on various flavors of Unix and Linux. On your system, it may represent the run queue length, but only your experience or analyzing the actual kernel source code will provide an acceptable answer. While the CPU run queue and utilization analyses are consistent across platforms, the load average is not.