[collectd] terrible perfomance of collectd

[Josef Liška]

Israel Garcia napsal(a):
> Hi list, I'm running collectd 4.7.2 on a xen  domU(debian lenny) and
> on a Dual Intel 1.4GHz, RAID1 with 2x36GB SCSI 10,500RPM . I'm
> collecting information of more than 100 servers (a lot of rrd files),
> so cpu load is always at 100% iowait, the load is  always over 3, disk
> is doing over 400 IOPS and 3MB/s througput. No more domU's are running
> in this dom0 server. How can I improve the performance in this server?
> Can you help me?
>
>   
Hi,
1) try adjusting cache parameters:

<Plugin rrdtool>
        DataDir "/var/lib/collectd/rrd"
        CacheTimeout 485
        CacheFlush 1800
</Plugin>

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

3) change your raid configuration to raid0 or 10

4) add more ram if your system is swaping

5) adjust rrd files "time precision" if you do not need acuracy to 
seconds, this will keep whole dataset smaller.
-- 

S pozdravem
Josef Liška

CHL | system care

Telefon: +420.272048055
Fax: +420.272048064
Mobil: +420.776026526 denně 9:00 - 17:30
Jabber: jl at chl.cz
https://www.chl.cz/

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.verplant.org/pipermail/collectd/attachments/20091115/22dc30b4/attachment.htm 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: jl.vcf
Type: text/x-vcard
Size: 433 bytes
Desc: not available
Url : http://mailman.verplant.org/pipermail/collectd/attachments/20091115/22dc30b4/attachment.vcf