graphite-dev team mailing list archive

[Cliff Pracht <question227319@xxxxxxxxxxxxxxxxxxxxx>]

Question #227319 on Graphite changed:
https://answers.launchpad.net/graphite/+question/227319

Cliff Pracht posted a new comment:

We are seeing sufficient (not great) write performance with Netapp/NFS.    At one point we had the whisper files on local VMDK volume (which was also over NFS) and performance was better.    Moving it to native NFS (IE not on VMDK) caused an increase in response times but was adequate – think it went from .001 to .003 for the average update time.   We are doing at peak about 1million committed points per minute (at least according to carbon agent stats, I believe it is per minute).    With that said we are seeing great deduplication savings at over 80%.

I am assuming that Vmware NFS is sending much smaller packets to filer
and reason for better response time.  We are using 32K read/writes for
NFS mounts which is probably WAY to high – will look to tweak that to
see if it helps.

I was not aware of the cluster  feature of graphite until you had
brought that up(thanks!)  and would like to take a look at that as a
possibility, as well.

Cliff

-- 
You received this question notification because you are a member of
graphite-dev, which is an answer contact for Graphite.