Re: Uneven CPU load on a 4 node cluster

[Andreas Wagner <an...@googlemail.com>]

Hi all,

I'm experiencing very similar effects. Did you (or anyone for that 
matter) have/solvethis issue?

I have a 3 node cluster with vnodes having the same #tokens (256). 
Infact, all nodes are configured identical and share similar/same 
hardware. Cassandra.yaml settings are fairly standard - nothing fancy.

According to "nodetool status" command everything is perfectly balanced. 
Running "cassandra-stress -d node_ip1,node_ip2,node_ip3" causes a heavy 
load on node_ip1, while node_ip2/3 are almost idle. Data, however, seems 
to be distributed evenly. I even get "UnavailableException" for some 
keys to be inserted on node_ip1.

I also tried a second run with the scheduling set to "roundrobin" and 
made use of the standard "throttlingoption". Unfortunately, nothing changed.

Could someone please provide some pointersand/or insights what I'm doing 
wrong?

Thanks so much!
Andreas