メインコンテンツへスキップ

マザーボードの問題によるパフォーマンスへの影響とCPU使用率の上昇

Views:
13
Visibility:
Public
Votes:
0
Category:
ontap-9
Specialty:
hw
Last Updated:

問題

  • 障害ノードのマザーボード交換後、CPU使用率が100%になりました。
  • 同じノードのすべてのボリュームで、データサブシステムからのレイテンシが高いことが報告されています。 

cluster::*> qos statistics volume latency show -vserver <vserver-name> -volume testvolume01_cluster1
Workload       ID   Latency   Network   Cluster     Data     Disk   QoS Max   QoS Min 
--------------- ------ ---------- ---------- ---------- ---------- ---------- ---------- ---------- 
-total-        -    9.35ms   750.00us     0ms    7.50ms  1083.00us     0ms     0ms 
testvolume01_..   6564   56.11ms    4.04ms     0ms   51.59ms   482.00us     0ms     0ms 
-total-        -    7.68ms   918.00us     0ms    5.75ms  1005.00us     0ms     0ms 
testvolume01_..   6564   50.03ms    6.07ms     0ms   43.55ms   411.00us     0ms     0ms 
-total-        -    7.93ms   560.00us     0ms    6.75ms   616.00us     0ms     0ms 
testvolume01_..   6564   56.79ms    2.67ms     0ms   53.75ms   370.00us     0ms     0ms 
-total-        -    9.73ms   867.00us     0ms    7.68ms  1174.00us     0ms     0ms 
testvolume01_..   6564   54.80ms    5.03ms     0ms   49.49ms   284.00us     0ms     0ms 
-total-        -   10.19ms   569.00us     0ms    7.95ms    1.67ms     0ms     0ms 

  • ノード上のCPU 使用率は、大きなワークロードがない場合でも、すべての CPU コアで 90 ~ 100% を超える使用率を報告します。 

cluster::> node run -node <node-name> -command sysstat -m -c 30 -s 1
 ANY  AVG  CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 CPU6 CPU7 CPU8 CPU9 CPU10 CPU11 CPU12 CPU13 CPU14 CPU15
100%  95%   96%  95%  96%  96%  95%  95%  96%  95%  95%  95%   95%   95%   95%   95%   96%   95%
100%  98%   97%  98%  98%  97%  98%  97%  98%  97%  98%  98%   97%   98%   98%   97%   98%   98%
100%  89%   91%  88%  90%  88%  89%  89%  88%  88%  90%  88%   89%   88%   87%   89%   92%   86%
100%  99%   99%  99%  99%  99%  99%  99%  99%  99%  99%  99%   99%   99%   99%   99%   99%   99%
100%  96%   96%  95%  95%  96%  95%  95%  95%  95%  95%  96%   96%   95%   96%   96%   96%   95%
100%  97%   96%  97%  96%  97%  95%  98%  97%  96%  96%  96%   97%   97%   96%   96%   97%   98%

cluster::> node run -node <node-name> -command 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
 84%   4455    0    0   4724   1800 101604   89417    24     0    0   43s   89%  100%
 86%   3805    0    0   3933   1942 101654  103804   67209     0    0   50s   93%  100%
 90%   2937    0    0   3028   1534  82590   95313   15497     0    0   45s   94%  100%
 93%   3361    0    0   3470   1464  83808   72377    36     0    0   48s   92%   11%
 93%   3596    0    0   3734   2643  84973   65356   4977     0    0   47s   91%   42%
 91%   3462    0    0   3571   1246  74254   59665    24     0    0   47s   91%   0%
 91%   3912    0    0   4031   2062  75502   65672    24     0    0   48s   90%   38%
 91%   3844    0    0   3950   4401 138075   82362   3455     0    0   48s   93%   26%
 94%   3742    0    0   3851   1097  60757   78074    36     0    0   49s   91%   0%
 94%   3616    0    0   3746   1342 137586   88379     0     0    0   51s   93%   0%
 93%   3662    0    0   3828   2253  59392   96558    24     0    0   52s   96%   0%
 95%   3624    0    0   3857   1247  58682   93645     0     0    0   50s   97%   0%

 

Sign in to view the entire content of this KB article.

New to NetApp?

Learn more about our award-winning Support

NetApp provides no representations or warranties regarding the accuracy or reliability or serviceability of any information or recommendations provided in this publication or with respect to any results that may be obtained by the use of the information or observance of any recommendations provided herein. The information in this document is distributed AS IS and the use of this information or the implementation of any recommendations or techniques herein is a customer's responsibility and depends on the customer's ability to evaluate and integrate them into the customer's operational environment. This document and the information contained herein may be used solely in connection with the NetApp products discussed in this document.