【原创】大叔经验分享(90)linux服务器iowait和负载很高

# top

top - 21:21:51 up 207 days,  1:30,  5 users,  load average: 0.90, 0.79, 1.62
Tasks: 249 total,   1 running, 246 sleeping,   2 stopped,   0 zombie
%Cpu(s): 49.2 us,  2.0 sy,  0.0 ni, 48.1 id,  0.0 wa,  0.0 hi,  0.6 si,  0.0 st

如果load average很大(参考核数),则系统负载很高,其中一种可能是由于iowait很大,具体可见%Cpu中的wa,通常wa=0.0,

iowait很大有两种可能,一种是网络,一种是磁盘,并且极有可能是磁盘,检查磁盘io,有多种命令:

1)iotop

Total DISK READ :       0.00 B/s | Total DISK WRITE :       0.00 B/s
Actual DISK READ:       0.00 B/s | Actual DISK WRITE:       0.00 B/s
  TID  PRIO  USER     DISK READ  DISK WRITE  SWAPIN      IO    COMMAND
    1 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % systemd --switched-root --system --deserialize 22
    2 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [kthreadd]
    3 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [ksoftirqd/0]

# iotop -b -n 5 -d 2

以非交互方式每隔2s运行5次

可以发现读写io很高的进程;

2)iostat

Linux 3.10.0-957.5.1.el7.x86_64 (002)     01/11/2019     _x86_64_    (8 CPU)

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
          15.42    0.00    2.19    1.06    0.00   81.33

Device:            tps    kB_read/s    kB_wrtn/s    kB_read    kB_wrtn
vda              33.36       100.93       420.00 1805775696 7514000609
vdb              48.99       460.82      5627.92 8244424473 100686856544
vdc               3.77        91.20       262.15 1631539193 4689931576
vdd               0.74        26.14       106.88  467597777 1912213584

# iostat -x 2 5

每隔2s运行5次

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           6.73    0.00   15.63   58.83    0.00   18.81

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s avgrq-sz avgqu-sz   await r_await w_await  svctm  %util
vda               0.00     7.00    0.50    6.00     2.00    54.00    17.23     0.00    0.54    0.00    0.58   0.38   0.25
vdb               0.00     5.00    0.00    1.50     0.00    26.00    34.67     0.00    0.67    0.00    0.67   0.67   0.10
vdc               0.00     0.00    1.00    0.00    64.00     0.00   128.00    37.88 23500.00 23500.00    0.00 619.00  61.90
vdd               0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00    0.00    0.00   0.00   0.00

可以发现读写io很高的磁盘;

如果发现一个磁盘读写io很高,怎么查看是哪些进程导致的?

# lsof /dev/vdc1

COMMAND   PID    USER   FD   TYPE DEVICE SIZE/OFF    NODE NAME
java     2688    hdfs  299uW  REG 253,33       16 3407875 /data/dfs/dn/in_use.lock
java     9982 jenkins  mem    REG 253,33   304183 1181098 /data/jenkins/plugins/github-branch-source/WEB-INF/lib/github-branch-source.jar

如何查看一个进程有哪些io?

# lsof -p $pid

COMMAND   PID USER   FD      TYPE             DEVICE  SIZE/OFF       NODE NAME
java    19891 hdfs  cwd       DIR               0,38       400 1047556664 /opt/cloudera-manager/cm-5.16.1/run/cloudera-scm-agent/process/806-hdfs-DATANODE
java    19891 hdfs  rtd       DIR              253,1      4096          2 /

猜你喜欢

转载自www.cnblogs.com/barneywill/p/11838674.html