SimilarityRenameDetector: Only attempt to index large files once

If a file fails to index the first time the loop encounters it, the
file is likely to fail to index again on the next row.  Rather than
wasting a huge amount of CPU to index it again and fail, remember
which destination files failed to index and skip over them on each
subsequent row.

Because this condition is very unlikely, avoid allocating the BitSet
until its actually needed.  This keeps the memory usage unaffected
for the common case.

Change-Id: I93509b28b61a9bba8f681a7b4df4c6127bca2a09
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>

diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/diff/SimilarityRenameDetector.java b/org.eclipse.jgit/src/org/eclipse/jgit/diff/SimilarityRenameDetector.java
index 89e71e666121b1cebfa8d1ac7f8db42a7055e62c..bf1bbda63bcd7e1c373c80449d17440b3f0ca3b8 100644 (file)
--- a/org.eclipse.jgit/src/org/eclipse/jgit/diff/SimilarityRenameDetector.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/diff/SimilarityRenameDetector.java
@@ -49,6 +49,7 @@ import static org.eclipse.jgit.diff.DiffEntry.Side.OLD;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Arrays;
+import java.util.BitSet;
 import java.util.List;
 
 import org.eclipse.jgit.JGitText;
@@ -216,6 +217,7 @@ class SimilarityRenameDetector {
 
                long[] srcSizes = new long[srcs.size()];
                long[] dstSizes = new long[dsts.size()];
+               BitSet dstTooLarge = null;
 
                // Init the size arrays to some value that indicates that we haven't
                // calculated the size yet. Since sizes cannot be negative, -1 will work
@@ -255,6 +257,11 @@ class SimilarityRenameDetector {
                                        continue;
                                }
 
+                               if (dstTooLarge != null && dstTooLarge.get(dstIdx)) {
+                                       pm.update(1);
+                                       continue;
+                               }
+
                                long srcSize = srcSizes[srcIdx];
                                if (srcSize < 0) {
                                        srcSize = size(OLD, srcEnt);
@@ -279,6 +286,9 @@ class SimilarityRenameDetector {
                                try {
                                        d = hash(NEW, dstEnt);
                                } catch (TableFullException tableFull) {
+                                       if (dstTooLarge == null)
+                                               dstTooLarge = new BitSet(dsts.size());
+                                       dstTooLarge.set(dstIdx);
                                        tableOverflow = true;
                                        pm.update(1);
                                        continue;