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>
This commit is contained in:
Shawn O. Pearce 2010-11-11 14:25:01 -08:00
parent 0e307a6afd
commit 918e6e20f0
1 changed files with 10 additions and 0 deletions

View File

@ -49,6 +49,7 @@
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 @@ private int buildMatrix(ProgressMonitor pm) throws IOException {
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 @@ private int buildMatrix(ProgressMonitor pm) throws IOException {
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 @@ private int buildMatrix(ProgressMonitor pm) throws IOException {
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;