一.理解linux调优指标
1.cpu指标
cpu利用率
应用程序执行的时间
系统执行的时间
cpu等待I/O处理所需要的时间
空间时间
nice处理所需要的时间
cpu负载
能够处理的任务数
i/o操作被阻止的任务数
中断数
2.内存指标
空闲内存大小(Free memory)
swap分区大小
buffer和cache
slabs
Active versus inactive memory
3.网卡
包的收发率
收发包的大小
每秒冲突数
丢包情况
网卡buffer溢出情况
包的错误情况
4.块设备
iowait
平均队列的长列
平均wait
每秒读写的block数
每秒读写的字节数
二.系统调优工具
top Process activity
vmstat System activity, Hardware and system information
uptime, w Average system load
ps, pstree Displays the processes
free Memory usage
iostat Average CPU load, disk activity
sar Collect and report system activity
mpstat Multiprocessor usage
numastat NUMA-related statistics
pmap Process memory usage
netstat Network statistics
iptraf Real-time network statistics
tcpdump, ethereal Detailed network traffic analysis
nmon Collect and report system activity
strace System calls
Proc file system Various kernel statistics
KDE system guard Real-time systems reporting and graphing
Gnome System Monitor Real-time systems reporting and graphing
lmbench Microbenchmark for operating system functions
iozone File system benchmark
netperf Network performance benchmark