From 9b28d55401a529ff08c709f42f66e765c93b0a20 Mon Sep 17 00:00:00 2001
From: Davide Libenzi <davidel@xmailserver.org>
Date: Fri, 7 Nov 2008 21:24:33 -0800
Subject: [PATCH] xdiff: give up scanning similar lines early
In a corner case of large files whose lines do not match uniquely, the
loop to eliminate a line that matches multiple locations adjacent to a run
of lines that do not uniquely match wasted too much cycles. Fix this by
giving up early after scanning 100 lines in both direction.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
xdiff/xprepare.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index e87ab57c652..a43aa72cd08 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -23,10 +23,9 @@
#include "xinclude.h"
-
#define XDL_KPDIS_RUN 4
#define XDL_MAX_EQLIMIT 1024
-
+#define XDL_SIMSCAN_WINDOW 100
typedef struct s_xdlclass {
@@ -312,6 +311,18 @@ void xdl_free_env(xdfenv_t *xe) {
static int xdl_clean_mmatch(char const *dis, long i, long s, long e) {
long r, rdis0, rpdis0, rdis1, rpdis1;
+ /*
+ * Limits the window the is examined during the similar-lines
+ * scan. The loops below stops when dis[i - r] == 1 (line that
+ * has no match), but there are corner cases where the loop
+ * proceed all the way to the extremities by causing huge
+ * performance penalties in case of big files.
+ */
+ if (i - s > XDL_SIMSCAN_WINDOW)
+ s = i - XDL_SIMSCAN_WINDOW;
+ if (e - i > XDL_SIMSCAN_WINDOW)
+ e = i + XDL_SIMSCAN_WINDOW;
+
/*
* Scans the lines before 'i' to find a run of lines that either
* have no match (dis[j] == 0) or have multiple matches (dis[j] > 1).