如何测量CPU利用率
This article may include metadata, visibility, validation state, and related support guidance.
适用场景
ONTAP 9
问题解答
- 作为系统整体视图的一部分、请使用命令行实时查看CPU利用率：
- 注意：CPU域在文章中作为计算资源列出、CPU域在ONTAP 9中进行了说明
- 使用以下命令验证CPU利用率：
- 使用sysstat -M 1
::> set diag
Warning: These diagnostic commands are for use by NetApp personnel only.
Do you want to continue? {y|n}: y
::*> node run -node netapp-01 sysstat -M 1
ANY1+ ANY2+ ANY3+ ANY4+ ANY5+ ANY6+ ANY7+ ANY8+ ANY9+ ANY10+ ANY11+ ANY12+ ANY13+ ANY14+ ANY15+ ANY16+ AVG
100% 100% 100% 99% 98% 96% 94% 91% 86% 81% 76% 70% 64% 57% 48% 37% 81%
CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 CPU6 CPU7 CPU8 CPU9 CPU10 CPU11 CPU12 CPU13 CPU14 CPU15
78% 76% 77% 83% 82% 83% 82% 82% 82% 82% 83% 84% 83% 82% 83% 82%
Nwk_Excl Nwk_Lg Nwk_Exmpt Protocol Cluster Storage Raid Raid_Ex Target Kahuna WAFL_Ex(Kahu)
3% 2% 450% 0% 0% 49% 2% 136% 0% 4% 511%( 94%)
WAFL_XClean SM_Exempt Cifs Exempt SSAN_Ex Intr Host Ops/s CP
0% 0% 0% 112% 0% 28% 8% 47111 0%
- 在上面的示例中、16个核心的平均CPU利用率为81%
最繁忙的域：
- WAFL豁免率为511-%
- 网络免除450/%
- RAID豁免率为136%、豁免率为120%。
- WAFL的样本间隔98%(Kahu+Kahuna)处于活动状态、4%(Kahuna)用于串行处理、94%(Kahu)用于并行处理
- 由于WAFL串行处理速度非常低、因此并行WAFL可能会完成更多工作
- 如果没有其他性能指标、在采样间隔内98%处于活动状态不是一个问题
- 整体CPU资源变得稀缺、从而增加了CPU工作排队的可能性、从而可能影响客户端延迟
- 使用sysstat -x 1.
::> set diag
Warning: These diagnostic commands are for use by NetApp personnel only.
Do you want to continue? {y|n}: y
::*> node run -node cluster1-01 sysstat -x 1
CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP
in out read write read write age hit time
2% 0 0 0 24 7 7 12 0 0 0 >60 100% 0%
2% 0 0 0 5 11 4 0 24 0 0 >60 100% 0%
4% 0 0 0 0 9 9 20 1274 0 0 >60 100% 1%
4% 0 0 0 3 7 8 12 36 0 0 >60 - 0%
1% 0 0 0 1 4 5 0 0 0 0 >60 100% 0%
2% 0 0 0 20 6 5 0 0 0 0 >60 - 0%
5% 0 0 0 8 5 6 12 24 0 0 >60 - 0%
1% 0 0 0 0 12 13 12 0 0 0 >60 - 0%
2% 0 0 0 0 3 4 0 36 0 0 >60 - 0%
- 在以上示例中、可以从第一列(即2%)查看CPU利用率