1.CPU
如果%sys比较高，可能的原因有：换页（换页时%wio一般不会高）、出现栓锁、bug等
(1)iostat监控所有CPU的平均信息
# iostat -x 1 2
Linux 2.6.32-358.el6.x86_64 (oracledb1) 03/22/2016 _x86_64_ (40 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
0.37 0.00 0.21 0.07 0.00 99.35
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util
sda 0.00 90.78 0.18 12.60 38.13 822.64 67.34 0.30 23.68 0.26 0.34
dm-0 0.00 0.00 0.16 78.40 37.30 627.20 8.46 0.25 3.14 0.03 0.22
(2)vmstat查看CPU队列信息
# vmstat procs --------------memory------------ ---swap-- -----io---- --system-- -----cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 4 0 0 61348052 368504 31984096 0 0 7 4 0 0 0 0 99 0 0
(3)mpstat能查看单个和所有的CPU信息
# mpstat Linux 2.6.32-358.el6.x86_64 (odb) 03/22/2014 _x86_64_ (40 CPU) 09:24:36 AM CPU %usr %nice %sys %iowait %irq %soft %steal %guest %idle 09:24:36 AM all 0.37 0.00 0.21 0.07 0.00 0.01 0.00 0.00 99.35
(4)top(top命令后，按1可以查看单个cpu信息)
top - 09:26:57 up 86 days, 20:44, 1 user, load average: 0.07, 0.11, 0.09 Tasks: 1132 total, 1 running, 1131 sleeping, 0 stopped, 0 zombie Cpu(s): 0.1%us, 0.1%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 99040048k total, 34672768k used, 64367280k free, 15112k buffers Swap: 70352888k total, 0k used, 70352888k free, 28789784k cached
2.内存
top、vmstat、free等命令
Linux中查看某个进程占用内存的情况，执行如下命令即可，将其中的[pid]替换成相应进程的PID号：
cat /proc/[pid]/status
# ps aux
RSS：进程实际占用物理内存大小
VSZ：任务虚拟地址空间的大小
# ps aux USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND root 1 0.0 0.0 19348 1460 ? Ss 2015 1:21 /sbin/init root 2 0.0 0.0 0 0 ? S 2015 0:00 [kthreadd] root 3 0.0 0.0 0 0 ? S 2015 0:31 [migration/0] oracle 8747 0.0 13.4 30005180 13292640 ? Ss 2015 29:07 oracleorcl1 (LOCAL=NO) oracle 8749 0.0 13.5 30005184 13385272 ? Ss 2015 29:13 oracleorcl1 (LOCAL=NO) oracle 8751 0.0 13.5 30005184 13460944 ? Ss 2015 30:15 oracleorcl1 (LOCAL=NO) oracle 8765 0.0 13.3 30005184 13183100 ? Ss 2015 29:14 oracleorcl1 (LOCAL=NO) oracle 8810 0.0 13.5 30005180 13434660 ? Ss 2015 29:22 oracleorcl1 (LOCAL=NO)
3.IO
vmstat、iostat、sar等
4.网络
监控网卡上的丢包和BUFFER OVERFLOW，监控网络流量
# sar -n DEV 1 2 Linux 2.6.32-358.el6.x86_64 (odb) 03/22/2014 _x86_64_ (40 CPU) 09:48:54 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s 09:48:55 AM lo 37.00 37.00 22.76 22.76 0.00 0.00 0.00 09:48:55 AM eth0 14.00 9.00 1.10 0.82 0.00 0.00 0.00 09:48:55 AM eth1 164.00 153.00 176.77 161.36 0.00 0.00 0.00 09:48:55 AM eth2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 09:48:55 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s 09:48:56 AM lo 6.00 6.00 9.54 9.54 0.00 0.00 0.00 09:48:56 AM eth0 17.00 7.00 1.89 1.27 0.00 0.00 2.00 09:48:56 AM eth1 30.00 34.00 15.01 22.64 0.00 0.00 0.00 09:48:56 AM eth2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 Average: IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s Average: lo 21.50 21.50 16.15 16.15 0.00 0.00 0.00 Average: eth0 15.50 8.00 1.50 1.05 0.00 0.00 1.00 Average: eth1 97.00 93.50 95.89 92.00 0.00 0.00 0.00 Average: eth2 0.00 0.00 0.00 0.00 0.00 0.00 0.00