SN6000B top command CPU %wa almost 100%

[lianchenfeng]

 I have 2 x HPE SN6000b, which is running in FOS v8.0.2c.

When I execute the top command. It is no accident that %wa ,shows 95.7%wa, close to 100%, and consistent. How can I solve this problem?

who can help me?

top - 03:59:15 up 545 days, 18:18, 1 user, load average: 1.72, 1.77, 1.46
Tasks: 82 total, 1 running, 81 sleeping, 0 stopped, 0 zombie
Cpu(s): 3.3%us, 1.0%sy, 0.0%ni, 0.0%id, 95.7%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 1024012k total, 946852k used, 77160k free, 148k buffers
Swap: 0k total, 0k used, 0k free, 63920k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1464 0 16 0 75268 4096 2024 S 1.3 0.4 543:55.07 webd0
1503 0 16 0 78516 4996 2188 S 1.3 0.5 8002:59 fcpd0
1568 0 16 0 91552 7212 3800 S 0.7 0.7 2419:37 snmpd
4332 6000 16 0 2816 1292 1036 R 0.7 0.1 0:00.13 top
2559 0 16 0 33976 3276 2028 S 0.3 0.3 0:21.70 sshd
1 0 16 0 1696 160 92 S 0.0 0.0 0:12.63 init
2 0 34 19 0 0 0 S 0.0 0.0 18:55.55 ksoftirqd/0
3 0 10 -5 0 0 0 S 0.0 0.0 26:30.96 events/0
4 0 10 -5 0 0 0 S 0.0 0.0 0:00.03 khelper
5 0 10 -5 0 0 0 S 0.0 0.0 0:00.00 kthread
27 0 10 -5 0 0 0 S 0.0 0.0 0:14.12 kblockd/0
58 0 15 0 0 0 0 S 0.0 0.0 0:01.84 pdflush
59 0 15 0 0 0 0 S 0.0 0.0 0:00.18 pdflush
61 0 19 -5 0 0 0 S 0.0 0.0 0:00.00 aio/0
60 0 15 0 0 0 0 D 0.0 0.0 36:26.62 kswapd0
68 0 15 -5 0 0 0 S 0.0 0.0 0:00.00 kseriod
278 0 15 0 0 0 0 S 0.0 0.0 2:23.92 kjournald
390 0 15 0 0 0 0 S 0.0 0.0 0:00.21 kjournald
609 0 16 0 2116 200 60 S 0.0 0.0 0:00.01 inetd
650 0 16 0 1700 116 44 S 0.0 0.0 0:00.04 klogd
666 0 16 0 1808 204 112 S 0.0 0.0 1:16.58 crond
702 0 3 -15 1676 104 40 S 0.0 0.0 0:00.01 oom_handler
717 0 3 -15 5452 4000 32 S 0.0 0.4 0:00.02 oom_handler
733 0 15 0 0 0 0 S 0.0 0.0 0:03.42 RASLOGK_TH
771 0 18 -5 0 0 0 S 0.0 0.0 0:00.00 XPRT
782 0 15 0 0 0 0 S 0.0 0.0 0:00.00 rasc_kthread
793 0 15 0 0 0 0 S 0.0 0.0 0:00.07 krscmon
1019 0 11 -5 0 0 0 S 0.0 0.0 0:00.00 kwt_nb_thread
1166 0 20 0 0 0 0 S 0.0 0.0 24:43.25 module-7-th

Version:
Kernel: 2.6.14.2
Fabric OS: v8.0.2c
Made on: Tue May 30 17:37:59 2017
Flash: Tue Jun 4 10:56:18 2019
BootProm: 1.0.11

[NimaG]

Hello lianchenfeng,

Comprehensive log analysis can help identify if there are any stuck processes causing this issue.

• wa is the percent of wait time (CPU waiting for I/O access). It indicates that the system is overworked.

Please also note that FOS v8.0.2c is End of Support since 2020

Consider upgrading to an active / latest version, as they handle resources more efficiently.

During the upgrade, the switch will perform ‘hareboot’ which will also take care of any stale / hung processes

The latest FOS for the SN6000b is v8.2.3d

Thanks!