Dear Wiki user, You have subscribed to a wiki page or wiki category on "Cassandra Wiki" for change notification.
The "MemtableSSTable" page has been changed by Paul Prescod. http://wiki.apache.org/cassandra/MemtableSSTable?action=diff&rev1=5&rev2=6 -------------------------------------------------- Once flushed, SSTable files are immutable; no further writes may be done. So, on the read path, the server must (potentially, although it uses tricks like bloom filters to avoid doing so unnecessarily) combine row fragments from all the SSTables on disk, as well as any unflushed Memtables, to produce the requested data. - To bound the number of SSTable files that must be consulted on reads, and to reclaim [[DistributedDeletes|space taken by unused data]], Cassandra performs compactions: merging multiple old SSTable files into a single new one. Compactions are triggered when at least 4 SStables has been flushed to disk. Since the input SSTables are all sorted by key, merging can be done efficiently, still requiring no random i/o. Once compaction is finished, the old SSTable files may be deleted: note that in the worst case (a workload consisting of no overwrites or deletes) this will temporarily require 2x your existing on-disk space used. In today's world of multi-TB disks this is usually not a problem but it is good to keep in mind when you are setting alert thresholds. + To bound the number of SSTable files that must be consulted on reads, and to reclaim [[DistributedDeletes|space taken by unused data]], Cassandra performs compactions: merging multiple old SSTable files into a single new one. Compactions are triggered when at least 4 SStables have been flushed to disk. Four similar-sized SSTables are merged into a single one. They start out being the same size as your memtable flush size, and then form a hierarchy with each one doubling in size. So you'll have up to 4 of the same size as your memtable, then up to 4 double that size, then up to 4 double that size, etc. + + Since the input SSTables are all sorted by key, merging can be done efficiently, still requiring no random i/o. Once compaction is finished, the old SSTable files may be deleted: note that in the worst case (a workload consisting of no overwrites or deletes) this will temporarily require 2x your existing on-disk space used. In today's world of multi-TB disks this is usually not a problem but it is good to keep in mind when you are setting alert thresholds. (The high-level memtable/sstable design as well as the "Memtable" and "SSTable" names come from Cassandra's sections 5.3 and 5.4 of [[http://labs.google.com/papers/bigtable.html|Google's Bigtable paper]], although some of the terminology around compaction differs.)
