Linux系统监控与性能优化实战
需积分: 10 63 浏览量
更新于2024-07-23
收藏 1.2MB PDF 举报
本文档是一篇关于Linux系统与性能监控的专业指南，由Darren Hoch撰写，旨在帮助读者理解和管理Linux服务器的监控指标。作者深入浅出地解释了几个关键的监控技术，让读者能够更好地理解和优化服务器性能。
首先，文章介绍了如何查看单个或多个CPU的使用情况。通过运行`#top -d1`命令并按下数字1，用户可以切换到显示所有CPU使用状态的视图。每个CPU的利用率、系统占用、空闲时间等信息一目了然，例如`Cpu0:1.0%us,3.0%sy,0.0%ni,96.0%id,0.0%wa,0.0%hi,0.0%si,0.0%st`，其中us代表用户空间CPU时间，sy代表系统内核时间，ni代表正在等待I/O操作完成的进程时间，id代表空闲时间，wa表示等待I/O的进程时间，hi和si分别代表硬件中断处理时间和软件中断处理时间，st代表CPU停止状态。
其次，文章指导用户如何确认系统是多核还是多CPU，通过查看`/proc/cpuinfo`文件中的"processor"字段，如果看到多个类似于"processor:0"和"processor:1"的行，则表明系统是多核或多CPU架构。
接着，讲解了如何追踪特定进程在哪个CPU上运行。使用`#top -d1`命令后，通过进入top的CurrentFields设置页面，并选择显示"j:P=Lastusedcpu(SMP)"，可以看到进程占用的CPU核心编号。
文章还强调了Linux内核配置对于支持多核的重要性，指出在内核配置时必须启用`CONFIG_SMP`选项来启用对对称多处理（SMP）的支持。此外，用户可以通过`#uname -a`命令查看当前内核版本和其是否支持SMP。
针对Linux 2.6版本的SMP负载平衡，文章解释了在多核系统中，任务会被分配到特定的CPU队列中，可能会导致初始分配不均衡。Linux 2.6的调度器采用负载均衡策略，每200毫秒会自动调整任务在不同CPU之间的分布，以保持整体系统的稳定和高效。
这篇Linux经验集提供了实用的工具和技术，帮助管理员监控和优化多核Linux服务器的性能，确保资源的有效利用和系统的高效运行。无论是对Linux新手还是有经验的运维人员，都能从中受益匪浅。
Linux System and Network Performance Monitoring
Copyright 2009 Darren Hoch. All rights reserved. 8 of 43
1.2 Determining Baseline Statistics
System utilization is contingent on administrator expectations and system
specifications. The only way to understand if a system is having performance
issues is to understand what is expected of the system. What kind of
performance should be expected and what do those numbers look like? The only
way to establish this is to create a baseline. Statistics must be available for a
system under acceptable performance so it can be compared later against
unacceptable performance.
In the following example, a baseline snapshot of system performance is
compared against a snapshot of the system under heavy utilization.
# vmstat 1
procs memory swap io system cpu
r b swpd free buff cache si so bi bo in cs us sy wa id
1 0 138592 17932 126272 214244 0 0 1 18 109 19 2 1 1 96
0 0 138592 17932 126272 214244 0 0 0 0 105 46 0 1 0 99
0 0 138592 17932 126272 214244 0 0 0 0 198 62 40 14 0 45
0 0 138592 17932 126272 214244 0 0 0 0 117 49 0 0 0 100
0 0 138592 17924 126272 214244 0 0 0 176 220 938 3 4 13 80
0 0 138592 17924 126272 214244 0 0 0 0 358 1522 8 17 0 75
1 0 138592 17924 126272 214244 0 0 0 0 368 1447 4 24 0 72
0 0 138592 17924 126272 214244 0 0 0 0 352 1277 9 12 0 79
# vmstat 1
procs memory swap io system cpu
r b swpd free buff cache si so bi bo in cs us sy wa id
2 0 145940 17752 118600 215592 0 1 1 18 109 19 2 1 1 96
2 0 145940 15856 118604 215652 0 0 0 468 789 108 86 14 0 0
3 0 146208 13884 118600 214640 0 360 0 360 498 71 91 9 0 0
2 0 146388 13764 118600 213788 0 340 0 340 672 41 87 13 0 0
2 0 147092 13788 118600 212452 0 740 0 1324 620 61 92 8 0 0
2 0 147360 13848 118600 211580 0 720 0 720 690 41 96 4 0 0
2 0 147912 13744 118192 210592 0 720 0 720 605 44 95 5 0 0
2 0 148452 13900 118192 209260 0 372 0 372 639 45 81 19 0 0
2 0 149132 13692 117824 208412 0 372 0 372 457 47 90 10 0 0
Just by looking at the numbers in the last column (id) which represent idle time,
we can see that under baseline conditions, the CPU is idle for 79% - 100% of the
time. In the second output, we can see that the system is 100% utilized and not
idle. What needs to be determined is whether or not the system at CPU utilization
is managing.
2.0 Installing Monitoring Tools
Most *nix systems ship with a series of standard monitoring commands. These
monitoring commands have been a part of *nix since its inception. Linux provides these
monitoring tools as part of the base installation or add-ons. Ultimately, there are
packages available for most distributions with these tools. Although there are multiple
open source and 3
rd
party monitoring tools, the goal of this paper is to use tools included
with a Linux distribution.
This paper describes how to monitor performance using the following tools.
期望值是什么?
你有什么样的应用?
你期望系统表现是怎样的?
创建性能基线 baseline
CPU空闲状态减少了,
变忙了
剩余42页未读，继续阅读
点击了解资源详情
点击了解资源详情
点击了解资源详情
154 浏览量
2011-04-21 上传
2007-04-10 上传
2019-08-10 上传
2008-07-31 上传
2008-06-11 上传
坚强2002
- 粉丝: 387
- 资源: 3
我的内容管理
展开
