10-26-2007
Announcing collectl - new performance linux performance monitor
About 4 years ago I wrote this tool inspired by Rob Urban's collect tool for DEC's Tru64 Unix. What makes this tool as different as collect was in its day is its ability to run at a low overhead and collect tons of stuff. I've expanded the general concept and even include data not available in any other tool such as Infiniband or Lustre data. Collectl can collect it all and present it in a consistent output format. There's even an option to let you generate the data in plottable format.
Far to many features to talk about here but they are discussed on the website for
collectl
Ever wonder why ALL tools that monitor linux network stats at 1 second intervals report the wrong numbers? The short answer is because the stats are only updated once ever 0.9765 seconds and unless you have a monitor that can run at fractional intervals like collectl, you'll get wrong numbers! You can read more about it on collectl's website but don't take my word for it. Download it and try it out.
-mark
8 More Discussions You Might Find Interesting
1. AIX
I am an old HP 3000 systems administrator who had to retire the 3000 for some nice pseries AIX boxes. We are a Symitar site and the powers that be do not think we are ready for root acess. I need to find ways within my chains to view system statistics. Being able to wow someone in management... (3 Replies)
Discussion started by: Beetlejuice
3 Replies
2. Red Hat
Hi everyone,
The last two days I'm researching results of NFS operations on Linux, and I noticed some time difference when read and write.
cat /proc/version : Linux version 2.6.9-42.ELsmp (bhcompile@hs20-bc1-1.build.redhat.com) (gcc version 3.4.6 20060404 (Red Hat 3.4.6-2)) #1 SMP Wed Jul 12... (1 Reply)
Discussion started by: sysgate
1 Replies
3. HP-UX
Hello,
there. We want to write application on HP-UX to monitor system resource,such as CPU,Network Traffic Load,Disk Usage,etc. Anyone know these API functions except the system command ? thanks. (6 Replies)
Discussion started by: Frank2004
6 Replies
4. Red Hat
I am getting absolutely dreadful iowait stats on my disks when I am trying to install some applications.
I have 2 physical disks on which I have created 2 separate logical volume groups and a logical volume in each. I have dumped some stats as below
My dual core CPU is not being over utilised... (3 Replies)
Discussion started by: jimthompson
3 Replies
5. AIX
Dear experts ,
Pls advice for any good Tool to monitor the CPU and performance of AIX the system ..
to keep monitoring to show me the utilization of that system .. (12 Replies)
Discussion started by: Mr.AIX
12 Replies
6. UNIX for Dummies Questions & Answers
One of our database server is suddenly became very slow and i have no clue what to do .Please help. I m sharing the performance inforamtion regarding cpu,harddisk,ram .
########CPU Information########
Machine Uptime Information:
uptime
10:25:06 up 16:50, 1 user, load average: 5.84, 5.65,... (10 Replies)
Discussion started by: pinga123
10 Replies
7. Programming
Hi,
May i know the tools which will give the below details in a consolidated fashion for some 'X' duration in single and multicore processors,
1) How many times and how long scheduler code and kernel threads are executing ?
2) Details about each process, time spent in each state (run, wait... (0 Replies)
Discussion started by: tkarthi85
0 Replies
8. Red Hat
IN solaris, for network high-availability we are using IPMP concept, can u tell me in REDHAT LINUX what we are using... also pls share good step to read & understand the that concept...
Also performance issue in linux what are step & cmd can u tell me??? (2 Replies)
Discussion started by: tiger09
2 Replies
LEARN ABOUT CENTOS
collectl2pcp
COLLECTL2PCP(1) General Commands Manual COLLECTL2PCP(1)
NAME
collectl2pcp - import collectl data to a PCP archive
SYNOPSIS
collectl2pcp [-F] [-v] [-?] file [file ...] archive
DESCRIPTION
collectl2pcp reads raw collectl(1) data from each file and creates a new PCP archive with basename archive. Each input file may be gzipped
(with .gz suffix). The PCP archive and at least one input file are required arguments.
The options to collectl2pcp are as follows.
-F Overwrite archive (and the index and meta files) if it already exists.
-v Report progress and errors verbosely. This also reports a count of unsupported metric data in the collectl(1) input file(s), which
is normally silently skipped.
file [file ...]
These are the collectl(1) input files. If more than one is given, they must contain data for the same host and be given in time-
stamp chronological order on the command line. Note that when collectl(1) is run as a service, it normally creates files with date
based names that will sort chronologically (e.g. /var/log/collectl/*.gz will be sorted correctly).
PCP ENVIRONMENT
Environment variables with the prefix PCP_ are used to parameterize the file and directory names used by PCP. On each installation, the
file /etc/pcp.conf contains the local values for these variables. The $PCP_CONF variable may be used to specify an alternative configura-
tion file, as described in pcp.conf(5).
SEE ALSO
collectl(1), pmcollectl(1), PCPIntro(1), LOGIMPORT(3), pcp.conf(5), pcp.env(5) and pmns(5).
Performance Co-Pilot PCP COLLECTL2PCP(1)