Dstat: Versatile resource statistics tool
Dstat is a versatile replacement for vmstat, iostat, netstat
and ifstat. Dstat overcomes some of their limitations and adds some extra
features, more counters and flexibility. Dstat is handy for monitoring systems
during performance tuning tests, benchmarks or troubleshooting.
Dstat
allows you to view all of your system resources in real-time, you can eg.
compare disk utilization in combination with interrupts from your IDE
controller, or compare the network bandwidth numbers directly with the disk
throughput (in the same interval).
Dstat gives you detailed selective
information in columns and clearly indicates in what magnitude and unit the
output is displayed. Less confusion, less mistakes. And most importantly, it
makes it very easy to write plugins to collect your own counters and extend in
ways you never expected.
Dstat's output by default is designed for being interpreted by humans in
real-time, however you can export details to CSV output to a file to be imported
later into Gnumeric or Excel to generate graphs.
- Combines vmstat, iostat, ifstat, netstat information and more
- Shows stats in exactly the same timeframe
- Enable/order counters as they make most sense during
analysis/troubleshooting
- Modular design
- Written in python so easily extendable for the task at hand
- Easy to extend, add your own counters (please contribute those)
- Includes many external plugins to show how easy it is to add counters
- Can summarize grouped block/network devices and give total numbers
- Can show interrupts per device
- Very accurate timeframes, no timeshifts when system is stressed
- Shows exact units and limits conversion mistakes
- Indicate different units with different colors
- Show intermediate results when delay > 1
- Allows to export CSV output, which can be imported in Gnumeric and Excel to
make graphs
Here are the existing plugins, send me your own plugins.
[dag@moria ~]# dstat --list
···略···
See the for options and a summary of
each external plugin.
- Add /etc/dstat.conf configuration file to customize
- Create a complete counter/object model structure
- Interface directly with rrdtool for real-time graphing
- Create client-server application model for remote graphing
- See for more
details
[dag@moria ~]$ dstat --help
···略···
----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
usr sys idl wai hiq siq| read writ| recv send| in out | int csw
5 0 93 0 0 0| 154k 84k| 0 0 | 0 0 |1081 1116
13 0 87 0 0 0| 0 0 | 0 0 | 0 0 |1036 696
8 0 92 0 1 0| 0 8192B| 0 0 | 0 0 |1073 936
0 0 99 0 0 1| 0 0 | 0 0 | 0 0 |1072 940
1 1 97 0 2 0| 0 0 | 0 0 | 0 0 |1252 1727
1 1 98 0 1 0| 0 0 | 0 0 | 0 0 |1126 1191
1 0 99 0 0 0| 0 0 | 0 0 | 0 0 |1045 908
0 0 99 0 0 0| 0 44k| 0 0 | 0 0 |1051 904
1 1 99 0 0 0| 0 0 | 0 0 | 0 0 |1036 850
1 0 100 0 0 0| 0 0 | 0 0 | 0 0 |1029 757
[dag@moria ~]$
dstat -c --top-cpu -d --top-bio --top-latency ----total-cpu-usage---- -most-expensive- -dsk/total- ----most-expensive---- --highest-total--
usr sys idl wai hiq siq| cpu process | read writ| block i/o process | latency process
5 0 94 0 0 0|firefox 3.6| 148k 81k|init [5] 98k 50B|pdflush 21
2 1 98 0 0 0|wnck-applet 0.5| 0 0 | |at-spi-regist 5
2 1 98 0 0 0|firefox 0.5| 0 0 | |Xorg 1
1 2 97 0 0 1| | 0 0 | |Xorg 1
1 1 98 0 0 0| | 0 0 | |ksoftirqd/1 10
1 1 97 0 0 0|firefox 0.5| 0 0 | |ksoftirqd/0 5
2 1 97 0 0 0|firefox 0.5| 0 0 |firefox 0 28k|ksoftirqd/0 5
2 1 97 0 0 0|firefox 0.5| 0 0 | |Xorg 1
1 1 97 0 0 0|firefox 0.5| 0 0 | |ksoftirqd/0 6
2 1 98 0 0 0|firefox 0.5| 0 0 | |ksoftirqd/0 6
1 2 98 0 0 0| | 0 0 | |ksoftirqd/1 8
2 1 98 0 0 0|iwlagn 0.5| 0 72k|kjournald 0 32k|ksoftirqd/1 12
1 1 97 0 0 0| | 0 0 | |iwlagn/0 1
1 1 98 0 0 0|firefox 0.5| 0 0 | |ksoftirqd/1 8
[root@monitor tool]# dstat -lasmt
—load-avg— —-total-cpu-usage—- -dsk/total- -net/total- —paging– —system– —-swap— ——memory-usage—– —–time—–
1m 5m 15m |usr sys idl wai hiq siq| read writ| recv send| in out | int csw | used free| used buff cach free| date/time
1.2 0.8 0.6| 10 3 86 0 0 0|3026B 3286k| 0 0 | 0 0 | 531 2275 | 132k 18G| 10G 232M 4625M 442M|22-03 11:01:43
1.2 0.8 0.6| 22 7 71 0 0 0| 0 0 | 39k 25k| 0 0 |1421 2913 | 132k 18G| 10G 232M 4626M 439M|22-03 11:01:44
1.1 0.8 0.6| 1 0 99 0 0 0| 0 0 | 86k 20k| 0 0 |1036 393 | 132k 18G| 10G 232M 4626M 468M|22-03 11:01:45
1.1 0.8 0.6| 0 0 99 0 0 0| 0 5704k|1288B 1796B| 0 0 |1175 418 | 132k 18G| 10G 232M 4626M 481M|22-03 11:01:46
Here are 2
screenshots of older dstat versions in action.
Dstat 0.4 on a Power5
system that is being stress tested.
Dsta 0.3 (first
release) on 5 RHEL3 nodes in a cluster from a Windows terminal.
If you've found a bug,
please check the for known problems and send me updates if you have more
information to provide.
Please also copy&paste the output of the
problem, with a description, the version of the kernel and if appropriate the
involved /proc entries.
Dstat has a --debug option to profile plugins
and show what plugins and /proc entries are affected. Dstat also shows some more
information with the --version option that might be useful.
The following packages (in
order of appearance) are available.
or grab the latest
0.7.2 tarball at:
There's a mailinglist
about dstat and some other related tools at:
You can have access to
the latest changes via subversion from:
The current
asciidoc manual page is found here:
Subversion also holds the
current documentation and example config-files, so please look there for more
information. If you have improvements, found a bug or have a great idea, please
mail me so we can look at how to integrate it.
I found some comments about dstat on blogs, here's what they say:
阅读(2126) | 评论(0) | 转发(0) |
