Github user keith-turner commented on a diff in the pull request:

    https://github.com/apache/accumulo/pull/275#discussion_r127782947
  
    --- Diff: 
core/src/main/java/org/apache/accumulo/core/iterators/system/LocalityGroupIterator.java
 ---
    @@ -97,75 +134,122 @@ public static final int seek(HeapIterator hiter, 
LocalityGroup[] groups, Set<Byt
         else
           cfSet = Collections.emptySet();
     
    -    for (LocalityGroup lgr : groups) {
    -      // when include is set to true it means this locality groups contains
    -      // wanted column families
    -      boolean include = false;
    +    // determine the set of groups to use
    +    Collection<LocalityGroup> groupsToUse = Collections.EMPTY_LIST;
     
    -      if (cfSet.size() == 0) {
    -        include = !inclusive;
    -      } else if (lgr.isDefaultLocalityGroup && lgr.columnFamilies == null) 
{
    -        // do not know what column families are in the default locality 
group,
    -        // only know what column families are not in it
    +    // if no column families specified, then include all groups unless 
!inclusive
    +    if (cfSet.size() == 0) {
    +      if (!inclusive) {
    +        groupsToUse = groups.groups;
    +      }
    +    } else {
    +      groupsToUse = new HashSet<LocalityGroup>();
     
    +      // do not know what column families are in the default locality 
group,
    +      // only know what column families are not in it
    +      if (groups.defaultGroup != null) {
             if (inclusive) {
    -          if (!nonDefaultColumnFamilies.containsAll(cfSet)) {
    +          if (!groups.groupByCf.keySet().containsAll(cfSet)) {
                 // default LG may contain wanted and unwanted column families
    -            include = true;
    +            groupsToUse.add(groups.defaultGroup);
               }// else - everything wanted is in other locality groups, so 
nothing to do
             } else {
    -          // must include, if all excluded column families are in other 
locality groups
    -          // then there are not unwanted column families in default LG
    -          include = true;
    +          // must include the default group as it may include cfs not in 
our cfSet
    +          groupsToUse.add(groups.defaultGroup);
    +        }
    +      }
    +
    +      /*
    +       * Need to consider the following cases for inclusive and exclusive 
(lgcf:locality group column family set, cf:column family set) lgcf and cf are 
disjoint
    +       * lgcf and cf are the same cf contains lgcf lgcf contains cf lgccf 
and cf intersect but neither is a subset of the other
    +       */
    +      if (!inclusive) {
    +        for (Entry<ByteSequence,LocalityGroup> entry : 
groups.groupByCf.entrySet()) {
    +          if (!cfSet.contains(entry.getKey())) {
    +            groupsToUse.add(entry.getValue());
    +          }
    +        }
    +      } else if (groups.groupByCf.size() <= cfSet.size()) {
    +        for (Entry<ByteSequence,LocalityGroup> entry : 
groups.groupByCf.entrySet()) {
    +          if (cfSet.contains(entry.getKey())) {
    +            groupsToUse.add(entry.getValue());
    +          }
             }
           } else {
    -        /*
    -         * Need to consider the following cases for inclusive and 
exclusive (lgcf:locality group column family set, cf:column family set) lgcf 
and cf are
    -         * disjoint lgcf and cf are the same cf contains lgcf lgcf 
contains cf lgccf and cf intersect but neither is a subset of the other
    -         */
    -
    -        for (Entry<ByteSequence,MutableLong> entry : 
lgr.columnFamilies.entrySet())
    -          if (entry.getValue().longValue() > 0)
    -            if (cfSet.contains(entry.getKey())) {
    -              if (inclusive)
    -                include = true;
    -            } else if (!inclusive) {
    -              include = true;
    -            }
    +        for (ByteSequence cf : cfSet) {
    +          LocalityGroup group = groups.groupByCf.get(cf);
    +          if (group != null) {
    +            groupsToUse.add(group);
    +          }
    +        }
           }
    +    }
     
    -      if (include) {
    -        lgr.getIterator().seek(range, EMPTY_CF_SET, false);
    -        hiter.addSource(lgr.getIterator());
    -        numLGSeeked++;
    -      }// every column family is excluded, zero count, or not present
    +    for (LocalityGroup lgr : groupsToUse) {
    +      lgr.getIterator().seek(range, EMPTY_CF_SET, false);
    +      hiter.addSource(lgr.getIterator());
    +      numLGSeeked++;
    +    }
    +
    +    if (used != null) {
    +      used.addAll(groupsToUse);
         }
     
         return numLGSeeked;
       }
     
       @Override
       public void seek(Range range, Collection<ByteSequence> columnFamilies, 
boolean inclusive) throws IOException {
    -    seek(this, groups, nonDefaultColumnFamilies, range, columnFamilies, 
inclusive);
    +
    +    // determine if the arguments have changed since the last time
    +    boolean sameArgs = false;
    +    ImmutableSet<ByteSequence> cfSet = null;
    +    if (lastUsed != null && inclusive == lastInclusive) {
    --- End diff --
    
    @ivakegg  my memory is a bit fuzzy on this.  Its good that InMemoryMapTest 
covers these changes.  However, I think some of these optimizations you made 
will benefit iterators seeking the in mem map, but not iterators seeking 
RFiles.  I think I was not surprised at lack of coverage, but at the lack of 
use of your optimizations by RFile.  Personally I would like to see RFile 
refactored to use your optimizations.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

Reply via email to