Linux 死进程导致数据慢

中午一个查询过程 跑得挺快的，下午就达到了400秒！

DBA 说 系统有问题了

[oracle@backup ~]$ ps -aux
Warning: bad syntax, perhaps a bogus '-'? See /usr/share/doc/procps-3.2.3/FAQ
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND

root 29087 0.0 0.0 5360 972 ? Ss Sep09 0:00 /bin/bash /usr/bin/run-parts /etc/cron.daily
root 29088 0.0 0.0 14980 3460 ? S Sep09 0:00 /usr/bin/perl -w /etc/cron.daily/00-logwatch
root 29089 0.0 0.0 5416 584 ? S Sep09 0:00 awk -v progname=/etc/cron.daily/00-logwatch progname {????? print p
root 29360 0.0 0.0 2644 520 ? S Sep09 0:00 /bin/mail -s LogWatch for backup root
root 29414 0.0 0.0 53772 1132 ? S Sep09 0:00 /bin/bash /etc/log.d/scripts/services/zz-disk_space
root 29416 0.0 0.0 49896 592 ? D Sep09 0:00 df -hP

D 表示死进程

[oracle@backup ~]$ top

top - 16:30:45 up 32 days, 23:22, 3 users, load average: 22.12, 22.05, 21.81
Tasks: 469 total, 1 running, 466 sleeping, 0 stopped, 2 zombie
Cpu(s): 0.0% us, 0.0% sy, 0.0% ni, 100.0% id, 0.0% wa, 0.0% hi, 0.0% si
Mem: 32390016k total, 4907384k used, 27482632k free, 88408k buffers
Swap: 8193140k total, 42020k used, 8151120k free, 4050392k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1311 oracle 16 0 6540 1288 752 R 1 0.0 0:00.14 top
8880 root 15 0 41688 11m 2556 S 0 0.0 102:08.72 X
1 root 16 0 4756 560 460 S 0 0.0 0:12.47 init
2 root RT 0 0 0 0 S 0 0.0 0:02.23 migration/0

[oracle@backup ~]$ cat /proc/loadavg
22.12 22.04 21.80 2/622 1236

重起后的进程负载

[oracle@backup ~]$ top

top - 16:41:35 up 4 min, 1 user, load average: 0.06, 0.10, 0.04
Tasks: 240 total, 1 running, 239 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0% us, 0.0% sy, 0.0% ni, 99.9% id, 0.0% wa, 0.0% hi, 0.0% si
Mem: 32390016k total, 274216k used, 32115800k free, 30632k buffers
Swap: 8193140k total, 0k used, 8193140k free, 117976k cached