diff histogram: intern strings

phillipwood · gitster · commit 663c5ad0356f · 2021-11-18T22:23:31.000-08:00
Histogram is the only diff algorithm not to call
xdl_classify_record(). xdl_classify_record() ensures that the hash
values of two strings that are not equal differ which means that it is
not necessary to use xdl_recmatch() when comparing lines, all that is
necessary is to compare the hash values. This gives a 7% reduction in
the runtime of "git log --patch" when using the histogram diff
algorithm.

Test                                  HEAD^             HEAD
-----------------------------------------------------------------------------
4000.1: log -3000 (baseline)          0.18(0.14+0.04)   0.19(0.17+0.02) +5.6%
4000.2: log --raw -3000 (tree-only)   0.99(0.77+0.21)   0.98(0.78+0.20) -1.0%
4000.3: log -p -3000 (Myers)          4.84(4.31+0.51)   4.81(4.15+0.64) -0.6%
4000.4: log -p -3000 --histogram      6.34(5.86+0.46)   5.87(5.19+0.66) -7.4%
4000.5: log -p -3000 --patience       5.39(4.60+0.76)   5.35(4.60+0.73) -0.7%

Signed-off-by: Phillip Wood &lt;phillip.wood@dunelm.org.uk&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c
@@ -91,9 +91,8 @@ struct region {
 static int cmp_recs(xpparam_t const *xpp,
 	xrecord_t *r1, xrecord_t *r2)
 {
-	return r1->ha == r2->ha &&
-		xdl_recmatch(r1->ptr, r1->size, r2->ptr, r2->size,
-			    xpp->flags);
+	return r1->ha == r2->ha;
+
 }
 
 #define CMP_ENV(xpp, env, s1, l1, s2, l2) \
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
@@ -181,15 +181,11 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 	if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *))))
 		goto abort;
 
-	if (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF)
-		hbits = hsize = 0;
-	else {
-		hbits = xdl_hashbits((unsigned int) narec);
-		hsize = 1 << hbits;
-		if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
-			goto abort;
-		memset(rhash, 0, hsize * sizeof(xrecord_t *));
-	}
+	hbits = xdl_hashbits((unsigned int) narec);
+	hsize = 1 << hbits;
+	if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
+		goto abort;
+	memset(rhash, 0, hsize * sizeof(xrecord_t *));
 
 	nrec = 0;
 	if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) {
@@ -208,9 +204,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 			crec->size = (long) (cur - prev);
 			crec->ha = hav;
 			recs[nrec++] = crec;
-
-			if ((XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) &&
-			    xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
+			if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
 				goto abort;
 		}
 	}
@@ -279,8 +273,7 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	enl1 = xdl_guess_lines(mf1, sample) + 1;
 	enl2 = xdl_guess_lines(mf2, sample) + 1;
 
-	if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF &&
-	    xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
+	if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
 		return -1;
 
 	if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
@@ -305,8 +298,7 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		return -1;
 	}
 
-	if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)
-		xdl_free_classifier(&cf);
+	xdl_free_classifier(&cf);
 
 	return 0;
 }

Original file line number	Diff line number	Diff line change
`@@ -91,9 +91,8 @@ struct region {`
`91`	`91`	`static int cmp_recs(xpparam_t const *xpp,`
`92`	`92`	`xrecord_t r1, xrecord_t r2)`
`93`	`93`	`{`
`94`		`- return r1->ha == r2->ha &&`
`95`		`- xdl_recmatch(r1->ptr, r1->size, r2->ptr, r2->size,`
`96`		`- xpp->flags);`
	`94`	`+ return r1->ha == r2->ha;`
	`95`	`+`
`97`	`96`	`}`
`98`	`97`
`99`	`98`	`#define CMP_ENV(xpp, env, s1, l1, s2, l2) \`