[ https://issues.apache.org/jira/browse/CASSANDRA-6696?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13986688#comment-13986688 ]
Marcus Eriksson commented on CASSANDRA-6696: -------------------------------------------- Pushed a semi-working sstable-per vnode version here: https://github.com/krummas/cassandra/commits/marcuse/6696-3 (by no means review-ready) * flushes to vnode-separate sstables, spread out over the disks available * keeps the sstables separate during compaction, for STCS by grouping the compactionbuckets by overlapping sstables, and with LCS by keeping a separate manifest for every vnode. Still quite broken, but i think good enough to evaluate if we want to go this way, drawback is mainly that it takes a looong time to flush to 768 sstables instead of one (768 = num_tokens=256 and rf = 3). Doing 768 parallel compactions is also quite heavy. Unless anyone has a brilliant idea how to make flushing and compaction less heavy, I think we need some sort of balance here, maybe grouping the vnodes (8 or 16 vnodes per sstable perhaps?) so that we flush a more reasonable amout of sstables, or even just going with the per-disk approach? > Drive replacement in JBOD can cause data to reappear. > ------------------------------------------------------ > > Key: CASSANDRA-6696 > URL: https://issues.apache.org/jira/browse/CASSANDRA-6696 > Project: Cassandra > Issue Type: Improvement > Components: Core > Reporter: sankalp kohli > Assignee: Marcus Eriksson > Fix For: 3.0 > > > In JBOD, when someone gets a bad drive, the bad drive is replaced with a new > empty one and repair is run. > This can cause deleted data to come back in some cases. Also this is true for > corrupt stables in which we delete the corrupt stable and run repair. > Here is an example: > Say we have 3 nodes A,B and C and RF=3 and GC grace=10days. > row=sankalp col=sankalp is written 20 days back and successfully went to all > three nodes. > Then a delete/tombstone was written successfully for the same row column 15 > days back. > Since this tombstone is more than gc grace, it got compacted in Nodes A and B > since it got compacted with the actual data. So there is no trace of this row > column in node A and B. > Now in node C, say the original data is in drive1 and tombstone is in drive2. > Compaction has not yet reclaimed the data and tombstone. > Drive2 becomes corrupt and was replaced with new empty drive. > Due to the replacement, the tombstone in now gone and row=sankalp col=sankalp > has come back to life. > Now after replacing the drive we run repair. This data will be propagated to > all nodes. > Note: This is still a problem even if we run repair every gc grace. > -- This message was sent by Atlassian JIRA (v6.2#6252)