[mrtg] Re: bad performance: MRTG 2.9.4 / RRDs / rrdtool 1.0.28

[Rainer Bawidamann]

In article <20010109184803.C23575 at nextra.com>,
	bn at nextra.com (Bjorn Nordbo) writes:
> 
> Yes, the irony is that we installed the NFS server to boost the
> performance of MRTG/rateup, as NetApp's has write caching.

The question is whether the client caches read and written buffers.

> It seems, however, that it's simply the bandwidth to the NFS box which
> is the problem (the traffic is trunked to a router for access list
> processing and back to another VLAN). I will try to add another
> interface to the NetApp an attach it to the same VLAN as the MRTG
> collector and see if that helps.

I suppose it's a protocol problem: With all this read-ahead and cacheing
you should be able to get the 20MB/s of your disc over NFS if you read a
big file in one go (on a GigaBit net). But reading small parts of a file
takes some milliseconds every time - it's the network latency (ping
time) which will ruin your day.

rrdtool is optimized for local discs: Few reads/writes. This access
strategy leads to many network packets on NFS (any of the seek/write
cycles of the update function is one packet to the server and one back).

Rainer

PS: rateup is very different in this point: It reads the whole log file
    in one go and (re) writes it completely later.

--
Unsubscribe mailto:mrtg-request at list.ee.ethz.ch?subject=unsubscribe
Archive     http://www.ee.ethz.ch/~slist/mrtg
FAQ         http://faq.mrtg.org    Homepage     http://www.mrtg.org
WebAdmin    http://www.ee.ethz.ch/~slist/lsg2.cgi