[collectd] IO usage

[Ricardo J. Barberis]

El Martes 25/12/2018 a las 15:09, George escribió:
> Hi,
>
> Thanks for the suggestion. I did not know something like this exists. I
> have set it up with influxdb.

That's the nice thing about collectd, it has several write plugins for 
different use cases.

> I wish you happy holidays.

You too!

> În lun., 24 dec. 2018 la 22:28, Brandon Arp <brandonarp at gmail.com> a scris:
> > I worked at a fairly large company (as far as servers go) writing data to
> > rrd files.  Long story short, rrd probably isn't the system you want to
> > be using for storing the data.  As you've seen, it has very high IO
> > requirements.  Moving the data from rrd to other systems (happy to
> > elaborate more directly, not on the mailing list) saved us a ton of
> > resources, let us grow the monitoring cluster significantly, and
> > drastically increased the fidelity of data.  I would recommend looking
> > into some of the other time series databases out there.  Many of them
> > will support 400+ clients very easily.

At $WORK we replaced rrd with graphite on the server side (i.e. clients' 
collectd send the data to a central collectd server with write_graphite 
plugin).

It took some configuring but now it's working marvelously.
There is some in-memory caching but since graphite's web API reads from 
disk+memory, your graphs won't lag behind usually.

Cheers!
-- 
Ricardo J. Barberis
Usuario Linux Nº 250625: http://counter.li.org/
Usuario LFS Nº 5121: http://www.linuxfromscratch.org/
Senior SysAdmin / IT Architect - www.DonWeb.com