Nginx worker process hangs and a CPU load reaches 100%

Nginx of the worker process hangs and a CPU load up to 100%

Scenario Description:

#tcp Connection Status [Email protected] ~]# Netstat-nat |awk ' {print $6} ' |grep-v ' Foreign ' |grep-v ' established ' |sort|uniq-c|sort-rn 3010 time_wait 537 established Syn_recv Fin_wait2 Close_wait Fin_wait1 9 LISTEN 3 Last_ack #nginx Process #cpu Use, R status--run , using CPU the time, obviously a other nginx worker not quite the same . [[Email protected] ~]# PS axu|grep nginx root       15878  0.0  0.0    27352  1444?         ss     jul30   0:00 nginx:master   process/use/local/nginx/ Sbin/nginx-c  /use/local/nginx/conf/nginx.conf nobody     15879  0.9  0.3    36432 11756?       & nbsp s    jul30     7:42   Nginx:worker process                                                                                nobody   15881 73.2     0.3  36060 11448?        r     Jul30   626:41 nginx:   worker process                                                                                nobody   15883 72.9     0.3  36116 11428?        r     Jul30   624:24 Nginx:   worker process                                                                               Nobody 15884 0.8 0.3 36372 11776? S Jul30 7:34 Nginx:worker Process # memory usage, no problem . [Email protected] ~]# free-m Total used free shared buffers Cached mem:3018 2605 412 0 508 1251 -/+ buffers/cache:845 2172 swap:2047 0 2047 #nginx error log, no output [Email protected] ~]# tail-f/use/local/nginx/logs/error.log #top details of CPU Information Top-14:19:35 up 308 days, 21:47, 1 user, load average: 2.22, 2.59, 2.62 Tasks:86 Total, 3 running, sleeping, 1 stopped, 0 zombie Cpu0:2.1%us, 2.1%sy, 0.0%ni, 89.0%id, 0.0%wa, 0.0%hi, 6.7%si, 0.0%st Cpu1:100.0%us, 0.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Cpu2:100.0%us, 0.0%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Cpu3:0.0%us, 0.4%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.4%si, 0.0%st mem:3090600k Total, 2701600k used, 389000k free, 521064k buffers swap:2096472k Total, 0k used, 2096472k free, 1294384k cached     PID user      pr  ni    virt  res  SHR S%cpu%mem  ;   time+    command                                                                                                                     15883 nobody    25     0 36116  11m 1520 r 99.8     0.4 635:52.34 Nginx:worker process                                                                                                      15881 nobody    25     0 36060  11m 1520 r 99.5     0.4 638:09.22   Nginx:worker process                                                                                                      13116 Nobody 0 36616 11m 1512 S 3.7 0.4 0:07.63 Nginx:worker process

official bug Description:

This looks very similar to the problem, fixed in 1.1.1/1.0.7: *) Bugfix:nginx hogged CPU If all servers in an upstream were marked as "Down". > There is only one server in Upstream,which marked ' backup '. After some > Test,i found this is the reason. Yes, thank. This is somewhat known issue, ' Backup ' Handling needs attention. Maxim Dounin

this looks very similar to this problem and is fixed in 1.1.1/1.0.7 : *) FIX: nginx If in upstream marked " down > " upstream Span style= "FONT-SIZE:14PX; Font-family: Song body; Background:yellow None repeat scroll 0% 0%; " There is only one server and is marked as " backup Yes, thank you for your report. This is a known issue andthe "backup" process needs to be noted .

Workaround:

Just find a time to reboot.

Restart Nginx

Reference:

Http://bbs.linuxtone.org/thread-17226-1-1.html

Nginx worker process hangs and a CPU load reaches 100%