3

Performance Tuning/ Monitoring/Latency keeping in mind I see following 4 items & in each item they are lot of tools.

  1. CPU
  2. Memory
  3. IO
  4. Network

What I see following tools we do use.

  • vmstat
  • mpstat
  • sar
  • iostat
  • netstat
  • dstat
  • iptraf
  • netperf
  • ethtool
  • iperf
  • tcptrace
  • numa
  • tuned
  • PCP (Performance Co-Pilot)
  • iotop
  • htop
  • top
  • iftop
  • ifstat
  • strace
  • perf
  • top
  • dtrace
  • stap
  • iostat
  • iotop
  • blktrace
  • pidstat
  • mpstat
  • dstat
  • free
  • tcpdump
  • ip
  • nicstat
  • ping
  • ethtool

If any thing I am missing request you add.

Q1. Recommend tools ? & Best practices/results.
Q2. To getting best results out of X86 server with Linux(Fedora/CentOS/Ubuntu) what are tools to use and why?

Using all of your experience want create one Live CD out these tools.

I don't know serverfault admin will allow such question. Thank in advance to all Guru's out there.

1

2 Answers 2

0

I want to add some tool to helps for get accurate result

 1.Lsof
 2.Psacct or Acct – Monitor User Activity
 3.Monit – Linux Process and Services Monitoring
 4.NetHogs
 5.Monitorix – System and Network Monitoring
 6.Arpwatch – Ethernet Activity Monitor
 7.Suricata – Network Security Monitoring
 8.VnStat PHP – Monitoring Network Bandwidth
 9.Nagios – Network/Server Monitoring
 10.Nmon: Monitor Linux Performance
 11.Collectl: All-in-One Performance Monitoring Tool.
7

Brandan Gregg has made a number of visual diagrams of which tool to use on what part of your system that make really nice cheat sheets:

Tools:

Performance Observability

Which options to use in sar to monitor:

enter image description here

And closely related:

Linux Benchmarking Tools

Translate observations into tuning with:

enter image description here

Not the answer you're looking for? Browse other questions tagged .