[PATCH v2 8/8] xdiff/xprepare: use a smaller sample size for histogram diff

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



For histogram diff, we can afford a smaller sample size and thus a
poorer estimate of the number of lines, as the hash table (rhash) won't
be filled up/grown. This is safe as the final count of lines (xdf.nrecs)
will be updated correctly anyway by xdl_prepare_ctx().

This gives us a small boost in performance.

Signed-off-by: Tay Ray Chuan <rctay89@xxxxxxxxx>
---
 xdiff/xprepare.c |   17 ++++++++++++++---
 xdiff/xutils.c   |    8 ++------
 xdiff/xutils.h   |    2 +-
 3 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index c139ba8..b4d8402 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -26,6 +26,8 @@
 #define XDL_KPDIS_RUN 4
 #define XDL_MAX_EQLIMIT 1024
 #define XDL_SIMSCAN_WINDOW 100
+#define XDL_GUESS_NLINES1 256
+#define XDL_GUESS_NLINES2 20
 
 
 typedef struct s_xdlclass {
@@ -234,11 +236,20 @@ static void xdl_free_ctx(xdfile_t *xdf) {
 
 int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		    xdfenv_t *xe) {
-	long enl1, enl2;
+	long enl1, enl2, sample;
 	xdlclassifier_t cf;
 
-	enl1 = xdl_guess_lines(mf1) + 1;
-	enl2 = xdl_guess_lines(mf2) + 1;
+	/*
+	 * For histogram diff, we can afford a smaller sample size and
+	 * thus a poorer estimate of the number of lines, as the hash
+	 * table (rhash) won't be filled up/grown. The number of lines
+	 * (nrecs) will be updated correctly anyway by
+	 * xdl_prepare_ctx().
+	 */
+	sample = xpp->flags & XDF_HISTOGRAM_DIFF ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1;
+
+	enl1 = xdl_guess_lines(mf1, sample) + 1;
+	enl2 = xdl_guess_lines(mf2, sample) + 1;
 
 	if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
 		xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 890cc4f..0de084e 100644
--- a/xdiff/xutils.c
+++ b/xdiff/xutils.c
@@ -24,10 +24,6 @@
 
 
 
-#define XDL_GUESS_NLINES 256
-
-
-
 
 long xdl_bogosqrt(long n) {
 	long i;
@@ -153,12 +149,12 @@ void *xdl_cha_next(chastore_t *cha) {
 }
 
 
-long xdl_guess_lines(mmfile_t *mf) {
+long xdl_guess_lines(mmfile_t *mf, long sample) {
 	long nl = 0, size, tsize = 0;
 	char const *data, *cur, *top;
 
 	if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) {
-		for (top = data + size; nl < XDL_GUESS_NLINES && cur < top; ) {
+		for (top = data + size; nl < sample && cur < top; ) {
 			nl++;
 			if (!(cur = memchr(cur, '\n', top - cur)))
 				cur = top;
diff --git a/xdiff/xutils.h b/xdiff/xutils.h
index 674a657..714719a 100644
--- a/xdiff/xutils.h
+++ b/xdiff/xutils.h
@@ -33,7 +33,7 @@ void xdl_cha_free(chastore_t *cha);
 void *xdl_cha_alloc(chastore_t *cha);
 void *xdl_cha_first(chastore_t *cha);
 void *xdl_cha_next(chastore_t *cha);
-long xdl_guess_lines(mmfile_t *mf);
+long xdl_guess_lines(mmfile_t *mf, long sample);
 int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
 unsigned long xdl_hash_record(char const **data, char const *top, long flags);
 unsigned int xdl_hashbits(unsigned int size);
-- 
1.7.3.4.730.g67af1.dirty

--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]