/// <summary>Does the actual (time-consuming) work of the merge,
/// but without holding synchronized lock on IndexWriter
/// instance
/// </summary>
private int MergeMiddle(MergePolicy.OneMerge merge)
{
merge.CheckAborted(directory);
System.String mergedName = merge.info.name;
SegmentMerger merger = null;
int mergedDocCount = 0;
SegmentInfos sourceSegments = merge.segments;
int numSegments = sourceSegments.Count;
if (infoStream != null)
Message("merging " + merge.SegString(directory));
merger = new SegmentMerger(this, mergedName, merge);
merge.readers = new SegmentReader[numSegments];
merge.readersClone = new SegmentReader[numSegments];
bool mergeDocStores = false;
System.Collections.Hashtable dss = new System.Collections.Hashtable();
String currentDocStoreSegment;
lock(this) {
currentDocStoreSegment = docWriter.GetDocStoreSegment();
}
bool currentDSSMerged = false;
// This is try/finally to make sure merger's readers are
// closed:
bool success = false;
try
{
int totDocCount = 0;
for (int i = 0; i < numSegments; i++)
{
SegmentInfo info = sourceSegments.Info(i);
// Hold onto the "live" reader; we will use this to
// commit merged deletes
SegmentReader reader = merge.readers[i] = readerPool.Get(info, merge.mergeDocStores, MERGE_READ_BUFFER_SIZE, -1);
// We clone the segment readers because other
// deletes may come in while we're merging so we
// need readers that will not change
SegmentReader clone = merge.readersClone[i] = (SegmentReader)reader.Clone(true);
merger.Add(clone);
if (clone.HasDeletions())
{
mergeDocStores = true;
}
if (info.GetDocStoreOffset() != -1 && currentDocStoreSegment != null)
{
currentDSSMerged |= currentDocStoreSegment.Equals(info.GetDocStoreSegment());
}
totDocCount += clone.NumDocs();
}
if (infoStream != null)
{
Message("merge: total " + totDocCount + " docs");
}
merge.CheckAborted(directory);
// If deletions have arrived and it has now become
// necessary to merge doc stores, go and open them:
if (mergeDocStores && !merge.mergeDocStores)
{
merge.mergeDocStores = true;
lock (this)
{
if (currentDSSMerged)
{
if (infoStream != null)
{
Message("now flush at mergeMiddle");
}
DoFlush(true, false);
}
}
for (int i = 0; i < numSegments; i++)
{
merge.readersClone[i].OpenDocStores();
}
// Clear DSS
merge.info.SetDocStore(-1, null, false);
}
// This is where all the work happens:
mergedDocCount = merge.info.docCount = merger.Merge(merge.mergeDocStores);
System.Diagnostics.Debug.Assert(mergedDocCount == totDocCount);
if (merge.useCompoundFile)
{
success = false;
string compoundFileName = IndexFileNames.SegmentFileName(mergedName, IndexFileNames.COMPOUND_FILE_EXTENSION);
try
{
if (infoStream != null)
{
Message("create compound file " + compoundFileName);
}
merger.CreateCompoundFile(compoundFileName);
success = true;
}
catch (System.IO.IOException ioe)
{
lock (this)
{
if (merge.IsAborted())
{
// This can happen if rollback or close(false)
// is called -- fall through to logic below to
// remove the partially created CFS:
}
else
{
HandleMergeException(ioe, merge);
}
}
}
catch (Exception t)
{
HandleMergeException(t, merge);
}
finally
{
if (!success)
{
if (infoStream != null)
{
Message("hit exception creating compound file during merge");
}
lock (this)
{
deleter.DeleteFile(compoundFileName);
deleter.DeleteNewFiles(merger.GetMergedFiles());
}
}
}
success = false;
lock (this)
{
// delete new non cfs files directly: they were never
// registered with IFD
deleter.DeleteNewFiles(merger.GetMergedFiles());
if (merge.IsAborted())
{
if (infoStream != null)
{
Message("abort merge after building CFS");
}
deleter.DeleteFile(compoundFileName);
return 0;
}
}
merge.info.SetUseCompoundFile(true);
}
int termsIndexDivisor;
bool loadDocStores;
// if the merged segment warmer was not installed when
// this merge was started, causing us to not force
// the docStores to close, we can't warm it now
bool canWarm = merge.info.GetDocStoreSegment() == null || currentDocStoreSegment == null || !merge.info.GetDocStoreSegment().Equals(currentDocStoreSegment);
if (poolReaders && mergedSegmentWarmer != null && canWarm)
{
// Load terms index & doc stores so the segment
// warmer can run searches, load documents/term
// vectors
termsIndexDivisor = readerTermsIndexDivisor;
loadDocStores = true;
}
else
{
termsIndexDivisor = -1;
loadDocStores = false;
}
// TODO: in the non-realtime case, we may want to only
// keep deletes (it's costly to open entire reader
// when we just need deletes)
SegmentReader mergedReader = readerPool.Get(merge.info, loadDocStores, BufferedIndexInput.BUFFER_SIZE, termsIndexDivisor);
try
{
if (poolReaders && mergedSegmentWarmer != null)
{
mergedSegmentWarmer.Warm(mergedReader);
}
if (!CommitMerge(merge, merger, mergedDocCount, mergedReader))
{
// commitMerge will return false if this merge was aborted
return 0;
}
}
finally
{
lock (this)
{
readerPool.Release(mergedReader);
}
}
success = true;
}
finally
{
// Readers are already closed in commitMerge if we didn't hit
// an exc:
if (!success)
{
CloseMergeReaders(merge, true);
}
}
merge.mergeDone = true;
lock (mergeScheduler)
{
System.Threading.Monitor.PulseAll(mergeScheduler);
}
// Force a sync after commiting the merge. Once this
// sync completes then all index files referenced by the
// current segmentInfos are on stable storage so if the
// OS/machine crashes, or power cord is yanked, the
// index will be intact. Note that this is just one
// (somewhat arbitrary) policy; we could try other
// policies like only sync if it's been > X minutes or
// more than Y bytes have been written, etc.
if (autoCommit)
{
long size;
lock (this)
{
size = merge.info.SizeInBytes();
}
Commit(size);
}
return mergedDocCount;
}
/// <summary> Merges the indicated segments, replacing them in the stack with a
/// single segment.
/// </summary>
internal void Merge(MergePolicy.OneMerge merge)
{
bool success = false;
try
{
try
{
try
{
MergeInit(merge);
if (infoStream != null)
{
Message("now merge\n merge=" + merge.SegString(directory) + "\n merge=" + merge + "\n index=" + SegString());
}
MergeMiddle(merge);
MergeSuccess(merge);
success = true;
}
catch (System.Exception t)
{
HandleMergeException(t, merge);
}
}
finally
{
lock (this)
{
MergeFinish(merge);
if (!success)
{
if (infoStream != null)
Message("hit exception during merge");
if (merge.info != null && !segmentInfos.Contains(merge.info))
deleter.Refresh(merge.info.name);
}
// This merge (and, generally, any change to the
// segments) may now enable new merges, so we call
// merge policy & update pending merges.
if (success && !merge.IsAborted() && !closed && !closing)
UpdatePendingMerges(merge.maxNumSegmentsOptimize, merge.optimize);
}
}
}
catch (System.OutOfMemoryException oom)
{
HandleOOM(oom, "merge");
}
}
private void _MergeInit(MergePolicy.OneMerge merge)
{
lock (this)
{
System.Diagnostics.Debug.Assert(TestPoint("startMergeInit"));
System.Diagnostics.Debug.Assert(merge.registerDone);
System.Diagnostics.Debug.Assert(!merge.optimize || merge.maxNumSegmentsOptimize > 0);
if (hitOOM)
{
throw new System.SystemException("this writer hit an OutOfMemoryError; cannot merge");
}
if (merge.info != null)
// mergeInit already done
return ;
if (merge.IsAborted())
return ;
bool changed = ApplyDeletes();
// If autoCommit == true then all deletes should have
// been flushed when we flushed the last segment
System.Diagnostics.Debug.Assert(!changed || !autoCommit);
SegmentInfos sourceSegments = merge.segments;
int end = sourceSegments.Count;
// Check whether this merge will allow us to skip
// merging the doc stores (stored field & vectors).
// This is a very substantial optimization (saves tons
// of IO) that can only be applied with
// autoCommit=false.
Directory lastDir = directory;
System.String lastDocStoreSegment = null;
int next = - 1;
bool mergeDocStores = false;
bool doFlushDocStore = false;
System.String currentDocStoreSegment = docWriter.GetDocStoreSegment();
// Test each segment to be merged: check if we need to
// flush/merge doc stores
for (int i = 0; i < end; i++)
{
SegmentInfo si = sourceSegments.Info(i);
// If it has deletions we must merge the doc stores
if (si.HasDeletions())
mergeDocStores = true;
// If it has its own (private) doc stores we must
// merge the doc stores
if (- 1 == si.GetDocStoreOffset())
mergeDocStores = true;
// If it has a different doc store segment than
// previous segments, we must merge the doc stores
System.String docStoreSegment = si.GetDocStoreSegment();
if (docStoreSegment == null)
mergeDocStores = true;
else if (lastDocStoreSegment == null)
lastDocStoreSegment = docStoreSegment;
else if (!lastDocStoreSegment.Equals(docStoreSegment))
mergeDocStores = true;
// Segments' docScoreOffsets must be in-order,
// contiguous. For the default merge policy now
// this will always be the case but for an arbitrary
// merge policy this may not be the case
if (- 1 == next)
next = si.GetDocStoreOffset() + si.docCount;
else if (next != si.GetDocStoreOffset())
mergeDocStores = true;
else
next = si.GetDocStoreOffset() + si.docCount;
// If the segment comes from a different directory
// we must merge
if (lastDir != si.dir)
mergeDocStores = true;
// If the segment is referencing the current "live"
// doc store outputs then we must merge
if (si.GetDocStoreOffset() != - 1 && currentDocStoreSegment != null && si.GetDocStoreSegment().Equals(currentDocStoreSegment))
{
doFlushDocStore = true;
}
}
// if a mergedSegmentWarmer is installed, we must merge
// the doc stores because we will open a full
// SegmentReader on the merged segment:
if (!mergeDocStores && mergedSegmentWarmer != null && currentDocStoreSegment != null && lastDocStoreSegment != null && lastDocStoreSegment.Equals(currentDocStoreSegment))
{
mergeDocStores = true;
}
int docStoreOffset;
System.String docStoreSegment2;
bool docStoreIsCompoundFile;
if (mergeDocStores)
{
docStoreOffset = - 1;
docStoreSegment2 = null;
docStoreIsCompoundFile = false;
}
else
{
SegmentInfo si = sourceSegments.Info(0);
docStoreOffset = si.GetDocStoreOffset();
docStoreSegment2 = si.GetDocStoreSegment();
docStoreIsCompoundFile = si.GetDocStoreIsCompoundFile();
}
if (mergeDocStores && doFlushDocStore)
{
// SegmentMerger intends to merge the doc stores
// (stored fields, vectors), and at least one of the
// segments to be merged refers to the currently
// live doc stores.
// TODO: if we know we are about to merge away these
// newly flushed doc store files then we should not
// make compound file out of them...
if (infoStream != null)
Message("now flush at merge");
DoFlush(true, false);
}
merge.mergeDocStores = mergeDocStores;
// Bind a new segment name here so even with
// ConcurrentMergePolicy we keep deterministic segment
// names.
merge.info = new SegmentInfo(NewSegmentName(), 0, directory, false, true, docStoreOffset, docStoreSegment2, docStoreIsCompoundFile, false);
System.Collections.Generic.IDictionary<string, string> details = new System.Collections.Generic.Dictionary<string, string>();
details["optimize"] = merge.optimize + "";
details["mergeFactor"] = end + "";
details["mergeDocStores"] = mergeDocStores + "";
SetDiagnostics(merge.info, "merge", details);
// Also enroll the merged segment into mergingSegments;
// this prevents it from getting selected for a merge
// after our merge is done but while we are building the
// CFS:
mergingSegments[merge.info] = merge.info;
}
}
/* FIXME if we want to support non-contiguous segment merges */
private bool CommitMerge(MergePolicy.OneMerge merge, SegmentMerger merger, int mergedDocCount, SegmentReader mergedReader)
{
lock (this)
{
System.Diagnostics.Debug.Assert(TestPoint("startCommitMerge"));
if (hitOOM)
{
throw new System.SystemException("this writer hit an OutOfMemoryError; cannot complete merge");
}
if (infoStream != null)
Message("commitMerge: " + merge.SegString(directory) + " index=" + SegString());
System.Diagnostics.Debug.Assert(merge.registerDone);
// If merge was explicitly aborted, or, if rollback() or
// rollbackTransaction() had been called since our merge
// started (which results in an unqualified
// deleter.refresh() call that will remove any index
// file that current segments does not reference), we
// abort this merge
if (merge.IsAborted())
{
if (infoStream != null)
Message("commitMerge: skipping merge " + merge.SegString(directory) + ": it was aborted");
return false;
}
int start = EnsureContiguousMerge(merge);
CommitMergedDeletes(merge, mergedReader);
docWriter.RemapDeletes(segmentInfos, merger.GetDocMaps(), merger.GetDelCounts(), merge, mergedDocCount);
// If the doc store we are using has been closed and
// is in now compound format (but wasn't when we
// started), then we will switch to the compound
// format as well:
SetMergeDocStoreIsCompoundFile(merge);
merge.info.SetHasProx(merger.HasProx());
((System.Collections.IList) ((System.Collections.ArrayList) segmentInfos).GetRange(start, start + merge.segments.Count - start)).Clear();
System.Diagnostics.Debug.Assert(!segmentInfos.Contains(merge.info));
segmentInfos.Insert(start, merge.info);
CloseMergeReaders(merge, false);
// Must note the change to segmentInfos so any commits
// in-flight don't lose it:
Checkpoint();
// If the merged segments had pending changes, clear
// them so that they don't bother writing them to
// disk, updating SegmentInfo, etc.:
readerPool.Clear(merge.segments);
if (merge.optimize)
{
// cascade the optimize:
segmentsToOptimize[merge.info] = merge.info;
}
return true;
}
}
