persistent connection among cluster nodes
while looking at netstat table i observed that my cluster nodes not using persistent connection to talk among themselves on port 9160 to redirect request. I also observed that local write latency is around 30-40 microsecond, while its takes around .5 miliseconds if the chosen node is not the node responsible for the key for 50K QPS. I think this attributes to connection making time among servers as my servers are on same rack. does cassandra support this feature to maintain persistent connection among cluster nodes
Re: persistent connection among cluster nodes
Yes, look at OutboundTCPConnection. It only reconnects if there is a problem. You can enable TRACE logging on that class to see what it happens. On Tue, Oct 2, 2012 at 4:52 AM, Niteesh kumar wrote: > while looking at netstat table i observed that my cluster nodes not using > persistent connection to talk among themselves on port 9160 to redirect > request. I also observed that local write latency is around 30-40 > microsecond, while its takes around .5 miliseconds if the chosen node is not > the node responsible for the key for 50K QPS. I think this attributes to > connection making time among servers as my servers are on same rack. > > > does cassandra support this feature to maintain persistent connection among > cluster nodes -- Jonathan Ellis Project Chair, Apache Cassandra co-founder of DataStax, the source for professional Cassandra support http://www.datastax.com
Re: persistent connection among cluster nodes
On Tue, Oct 2, 2012 at 4:52 AM, Niteesh kumar wrote: > while looking at netstat table i observed that my cluster nodes not using > persistent connection to talk among themselves on port 9160 to redirect > request. 9160 is the thrift port. This basically means your client sucks if it's not pooling. -Brandon
RE: persistent connection among cluster nodes
Cluster nodes don't talk on 9160. Pretty sure they talk on "storage_port: 7000" from the yaml file. -Jeremiah From: Niteesh kumar [nitees...@directi.com] Sent: Tuesday, October 02, 2012 4:52 AM To: dev@cassandra.apache.org Subject: persistent connection among cluster nodes while looking at netstat table i observed that my cluster nodes not using persistent connection to talk among themselves on port 9160 to redirect request. I also observed that local write latency is around 30-40 microsecond, while its takes around .5 miliseconds if the chosen node is not the node responsible for the key for 50K QPS. I think this attributes to connection making time among servers as my servers are on same rack. does cassandra support this feature to maintain persistent connection among cluster nodes
