Reputation: 54
The defaults throughput are as follow (cassandra.yaml) :
compaction_throughput_mb_per_sec: 16
stream_throughput_outbound_megabits_per_sec: 200
inter_dc_stream_throughput_outbound_megabits_per_sec: 200
To speed up things like compaction, I have set those values :
$ nodetool getcompactionthroughput
Current compaction throughput: 10000 MB/s
$ nodetool getstreamthroughput
Current stream throughput: 10000 Mb/s
$ nodetool getinterdcstreamthroughput
Current inter-datacenter stream throughput: 10000 Mb/s
Cassandra data directories are backed by both SSD and HDD, depending of the keyspace.
Are there any impact (like read or write timeout) of applying such very high values ?
Thank you
Upvotes: 1
Views: 542
Reputation: 2310
Only impact I can see with high compaction throughput is that your traffic (read/writes) from the application may get impacted. As SSDs have finite IOPS capacity so giving most of it to compaction will impact your traffic at the time compaction is going on.
Upvotes: 1