Dieter Plaetinck

these all describe the same thing: * MemoryStore (in api server) (easily confused with store plugins) * Tank (in exported metrics and a couple places in the docs) (not very...

Looks useful : https://github.com/uber-go/automaxprocs

Document hardware requirements

1

@woodsaj is most familiar with this

I want to make sure that for newcomers, they understand better in what kind of topologies/configurations they can deploy metrictank, and what the tradeoffs are. While our docs document how...

what happens on kafka write node lag, look at largest chunk. increase retention if needed to prevent data loss

noticed this in #1194

profiletrigger too eager

3

in one of our environments, we use 0.5.7-5-ga191306 with : ``` # inspect status frequency. set to 0 to disable proftrigger-freq = 60s # path to store triggered profiles proftrigger-path...

issues with schemaId / storage-schemas.conf in place cluster upgrades

1

we have a few bugs that manifest when doing a rolling upgrade of storage-schemas.conf to a cluster. During the upgrade, different nodes will have different storage-schemas.conf rules and thus a...

MT cpu spike due to GC -> requests can easily take >5s to get answered

7

i'm going to look into techniques to lower GC cpu overhead. we currently reference a lot of data through pointers, i suspect we may be able to lower GC quite...

msgp: too few bytes left to read object

5

``` 2018/03/16 10:29:00 [dataprocessor.go:221 func1()] [E] DP getTargetsRemote: error unmarshaling body from mt-read00-12574-medium-ops-b-2445396050-vdcg2/getdata: "msgp: too few bytes left to r> 2018/03/16 10:29:00 [graphite.go:766 executePlan()] [E] HTTP Render msgp: too few...