Israel Garcia napsal(a):
Can you help me?


Hi,
Hi Josef, thanks for your answer. :-)

1) try adjusting cache parameters:

<Plugin rrdtool>
        DataDir "/var/lib/collectd/rrd"
        CacheTimeout 485
        CacheFlush 1800
</Plugin>
OK, I'll try with this config

The more sec you keep cache, the less io collectd generates. Tradeof is
in "lag" of graphs behind current time.

2) try adjusting filesystem params, if you are using ext3, try mount
options noatime,commit=600
Now, "/var/lib/collectd/rrd" is in the same OS filesystem, I'll add a
second hdd to my VM and put rrd files in this partition and set all
this parameters in fstab.

3) change your raid configuration to raid0 or 10
I can'nt this server only support raid 1 and 5. :-(

4) add more ram if your system is swaping
The server is not using any swap.

5) adjust rrd files "time precision" if you do not need acuracy to
seconds, this will keep whole dataset smaller.
Can you explain me this a little>?

Thanks again Josef
regards
Israel.

According to collectd man page, rrd files are usually created with step size set to interval. If you change interval eg. to 30sec from 5sec, your rrd files are still with stepsize 5s,
since they were created with previously used config file.

Bigger interval means smaller rrd files, which could hopefully fit into filesystem caches.

If you want to try impact of changing this, you can easily move wholo your rrd collection to backup location, retart collectd and let it recreate rrd files with new interval.
       rrdtool dump filename.rrd >filename.xml
       edit filename.xml
       rrdtool restore --force-overwrite filename.xml filename.rrd


If you want to keep old data and change rrd files step size, it is a bit more difficult, AFAIK. You have to dump rrd files using rrdtool dump to xml, then edit xml (with some script) and load edited xml back to rrd file using rrdtool restore

StepSize Seconds

Force the stepsize of newly created RRD-files. Ideally (and per default) this setting is unset and the stepsize is set to the interval in which the data is collected. Do not use this option unless you absolutely have to for some reason. Setting this option may cause problems with the snmp plugin, the exec plugin or when the daemon is set up to receive data from other hosts.

*
*
--

S pozdravem
Josef Liška

CHL | system care

Telefon: +420.272048055
Fax: +420.272048064
Mobil: +420.776026526 denně 9:00 - 17:30
Jabber: [email protected]
https://www.chl.cz/






--

S pozdravem
Josef Liška

CHL | system care

Telefon: +420.272048055
Fax: +420.272048064
Mobil: +420.776026526 denně 9:00 - 17:30
Jabber: [email protected]
https://www.chl.cz/

<<attachment: jl.vcf>>

_______________________________________________
collectd mailing list
[email protected]
http://mailman.verplant.org/listinfo/collectd

Reply via email to