High CPU after read timeout

Hi, Cassandra 3.9, I found after some ALLOW FILTERING request running on huge partition fails with Cassandra timeout during read query at consistency ONE (1 responses were required but only 0 replica responded) nodes continue to consume CPU in ReadStage-N threads, as if they still performing

Re: High CPU after read timeout

There is no mechanism for reads to timeout once they have started. The messaging service will drop the request when its received on the ReadStage or RequestResponseStage. This is how its always operated so not unique to 3.9. If a client disconnects from a coordinator there is also no way for the

possible race in copy from csv, cassandra 3.9

I use "copy from" to import a bunch of csv files, each with 100 rows (exported by "copy to" from another table) There is a chance that the copy from just hangs, after importing 9995000 lines, doing nothing, waiting forever. Could this be a race in the copy code? I use NUMPROCESSES=6, in bash

Re: possible race in copy from csv, cassandra 3.9

Looks similar to what was fixed by CASSANDRA-12740 , released in 3.10. On Thu, Jul 13, 2017 at 5:43 PM, Micha wrote: > I use "copy from" to import a bunch of csv files, each with 100 rows > (exported by "copy to"