svn commit: r1043451 - /couchdb/trunk/src/couchdb/couch_db_updater.erl

[ko...@apache.org]

Author: kocolosk
Date: Wed Dec  8 15:28:06 2010
New Revision: 1043451

URL: http://svn.apache.org/viewvc?rev=1043451&view=rev
Log:
Usort the infos during compaction to remove dupes, COUCHDB-968

This is not a bulletproof solution; it only removes dupes when the
they appear in the same batch of 1000 updates.  However, for dupes
that show up in _all_docs the probability of that happening is quite
high.  If the dupes are only in _changes a user may need to compact
twice, once to get the dupes ordered together and a second time to
remove them.

A more complete solution would be to trigger the compaction in "retry"
mode, but this is siginificantly slower.

Modified:
    couchdb/trunk/src/couchdb/couch_db_updater.erl

Modified: couchdb/trunk/src/couchdb/couch_db_updater.erl
URL: http://svn.apache.org/viewvc/couchdb/trunk/src/couchdb/couch_db_updater.erl?rev=1043451&r1=1043450&r2=1043451&view=diff
==============================================================================
--- couchdb/trunk/src/couchdb/couch_db_updater.erl (original)
+++ couchdb/trunk/src/couchdb/couch_db_updater.erl Wed Dec  8 15:28:06 2010
@@ -754,7 +754,10 @@ copy_rev_tree_attachments(SrcDb, DestFd,
         end, Tree).
             
 
-copy_docs(Db, #db{updater_fd = DestFd} = NewDb, InfoBySeq, Retry) ->
+copy_docs(Db, #db{updater_fd = DestFd} = NewDb, InfoBySeq0, Retry) ->
+    % COUCHDB-968, make sure we prune duplicates during compaction
+    InfoBySeq = lists:usort(fun(#doc_info{id=A}, #doc_info{id=B}) -> A =< B end,
+        InfoBySeq0),
     Ids = [Id || #doc_info{id=Id} <- InfoBySeq],
     LookupResults = couch_btree:lookup(Db#db.fulldocinfo_by_id_btree, Ids),