I do bulk load of real data into cluster. In may case this do in 16 threads (8 process / per machine, on two machines), with avg insert speed 1000 per second per thread, so total is 16000 rows per second, with avg size of row 573 bytes
2011/3/7 Aaron Morton <email@example.com>
It's always possible to run out of memory. Can you provide...
- number cf's and their Memtable settings
1 CF with memtable 64MB, other settings as default
- any row or key cache settings
Its stay default e.g 200000, but i don't do any read, only writes
- any other buffer or memory settings you may have changed in Cassandra.yaml.
I change only binary_memtable_throughput_in_mb setting, and set it to 64MB
- what load you are putting on the cluster, e.g. Inserting x rows/columns per second with avg size y