Improve performance of persisting an index by magnitudes

When updating smudged entries use a pathfilter to iterate only over
working tree files which have an associated smudged index entry.

Commit dac66672df0535f61a13273524d46e1e0012ca69 introduced that we
check and update smudged entries while persisting a dircache. Before
that commit adding a file to git caused  file i/o for the index file,
the object database (to store new content) and all files we wanted to
add (to read new content). After that commit we have additionally file
i/o for every file in the working tree (even ignored files).
Especially on windows iterating over the working tree can be very
time consuming. This decreased the performance of persisting a dircache
dramatically (I measured factors 4 to 10 while adding a file to linux
kernel repo). One could easily see this effect when dragging&dropping
modified files in a linux kernel repo in the egit staging view.

Change-Id: I568dec77635013cf6bb46f652d3f2b89de041c82
Signed-off-by: Kevin Sawicki <kevin@github.com>

diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/dircache/DirCache.java b/org.eclipse.jgit/src/org/eclipse/jgit/dircache/DirCache.java
index 9108d9235d806e9650076b9b284afcc96d0f639f..f24c9b2a5b7bf46516eb99a8cf4363135df04f1b 100644 (file)
--- a/org.eclipse.jgit/src/org/eclipse/jgit/dircache/DirCache.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/dircache/DirCache.java
@@ -57,8 +57,10 @@ import java.io.UnsupportedEncodingException;
 import java.security.DigestOutputStream;
 import java.security.MessageDigest;
 import java.text.MessageFormat;
+import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Comparator;
+import java.util.List;
 
 import org.eclipse.jgit.errors.CorruptObjectException;
 import org.eclipse.jgit.errors.LockFailedException;
@@ -74,6 +76,7 @@ import org.eclipse.jgit.storage.file.FileSnapshot;
 import org.eclipse.jgit.storage.file.LockFile;
 import org.eclipse.jgit.treewalk.FileTreeIterator;
 import org.eclipse.jgit.treewalk.TreeWalk;
+import org.eclipse.jgit.treewalk.filter.PathFilterGroup;
 import org.eclipse.jgit.util.FS;
 import org.eclipse.jgit.util.IO;
 import org.eclipse.jgit.util.MutableInteger;
@@ -941,7 +944,15 @@ public class DirCache {
         */
        private void updateSmudgedEntries() throws IOException {
                TreeWalk walk = new TreeWalk(repository);
+               List<String> paths = new ArrayList<String>(128);
                try {
+                       for (int i = 0; i < entryCnt; i++)
+                               if (sortedEntries[i].isSmudged())
+                                       paths.add(sortedEntries[i].getPathString());
+                       if (paths.isEmpty())
+                               return;
+                       walk.setFilter(PathFilterGroup.createFromStrings(paths));
+
                        DirCacheIterator iIter = new DirCacheIterator(this);
                        FileTreeIterator fIter = new FileTreeIterator(repository);
                        walk.addTree(iIter);