cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Martin Hentschel <hemar...@inf.ethz.ch>
Subject Throughput performance problem
Date Thu, 23 Sep 2010 09:14:48 GMT
When inserting rows to Cassandra, we have noticed an odd performance behavior.  When we insert
rows with increasing row keys (0,1,2,...) we get a throughput that is 10% higher than when
we insert rows with random row keys (in the range of 0 to 1'000'000).

This is strange because we use the RandomPartitioner.

Do you have any ideas?

Thanks,

Martin



Mime
View raw message