[collectd] RRDs on SSD - performance degredation [resend without images]

Cyril Feraudet collectd at feraudet.com
Fri Aug 16 11:46:24 CEST 2013


Try it and you'll see. rrdcached write to disk on demand and at the
latest when the time specified is out. 

I/O may be decreased by 10 or more depending on the "interval" on
collectd side and the '-w' option on rrdcached side. 

There is no migration to plan. Just start properly rrdcached and
configure collectd, ex : 

/usr/bin/rrdcached -w 1800 -z 1800 -t 8 -p /var/run/rrdcached.pid -l
unix:/var/run/rrdcached/rrdcached.sock -j /var/lib/rrdcached/journal 

And make sure the user used to run rrdcached is able to write rrd. 

One more thing : rrdtool graph command need to know the rrdcached socket
to flush data before graph them, ex: 

rrdtool graph --daemon=/var/run/rrdcached/rrdcached.sock -t .... 


Le 2013-08-16 11:19, Jesse Reynolds a écrit : 

> On 16/08/2013, at 5:16 PM, Cyril Feraudet <collectd at feraudet.com> wrote: 
>> Do you use rrdcached ? If not, use it and all you i/o problem will disappear.
> Sounds too good to be true :-) 
> Is the scheduling improved somehow? Is it more efficient with writing the RRD files? It seems that it will still need to update the RRD files as the rrd plugin does now, so not sure how this means there'll be less demands placed on IO. 
> We're planning on switching to opentsdb but that may be a little way off. 
> I have looked at rrdcached. With switching to rrdcached, can you do this while keeping the RRD files in place? Or is there a migration process? 
> Cheers 
> Jesse

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.verplant.org/pipermail/collectd/attachments/20130816/8c239b40/attachment.html>

More information about the collectd mailing list