incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Kent Tong <freemant2...@yahoo.com>
Subject Re: random keys and overlapping key ranges in SSTables
Date Sat, 31 Dec 2011 13:42:57 GMT
> bloom filters can guess right sstables to be read with high 
> probability < 0.1%. In reality even if you are using size based 
> compaction and have about 300 sstables, reading is fast unless
> there is row fragmentation and you are reading entire row.

Right, that's it. Thanks!


Mime
View raw message