We're on a read and update heavy access pattern. E.g. each request to Cassandra goes like
1. read all columns of row 2. do something with row 3. write all columns of row the columns we use are always the same, e.g. always (c1,c2,c3). c2 and c3 have a TTL. Since we always read c1,c2,c3 and after that overwrite c1,c2,c3, I found out, with https://issues.apache.org/jira/browse/CASSANDRA-2498, specifying which columns I want to read prevents Cassandra from looking into all "historic" SSTables. However, there is also the possibility to switch to leveled compactions for read/update intense workloads, right? How would you compare both solutions? Should we settle with the access pattern change, switch to leveled compactions, or do both? Thanks! -- Marcel