D2686: xdiff: add a preprocessing step that trims files
quark (Jun Wu)
phabricator at mercurial-scm.org
Mon Mar 5 00:50:28 UTC 2018
quark created this revision.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.
REVISION SUMMARY
xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable
lines. That is in theory good, but happens too late - after splitting,
hashing, and adjusting the hash values so they are unique. Those splitting,
hashing and adjusting hash values steps could have noticeable overhead.
For not uncommon cases like diffing two large files with minor differences,
the raw performance of those preparation steps seriously matter. Even
allocating an O(N) array and storing line offsets to it is expensive.
Therefore my previous attempts [1] [2] cannot be good enough since they do
not remove the O(N) array assignment.
This patch adds a preprocessing step - `xdl_trim_files` that runs before
other preprocessing steps. It counts common prefix and suffix and lines in
them (needed for displaying line number), without doing anything else.
Testing with an emulated large (57MB) file, minor change case:
open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(10000000)))
open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(10000000) if i != 6000000))
This patch improves the perf by more than 5x:
# before this patch
xdiff a b 0.65s user 0.37s system 98% cpu 1.033 total
# after this patch, gcc -O2
xdiff a b 0.10s user 0.08s system 97% cpu 0.179 total
# after this patch, gcc -O3 -mavx2
xdiff a b 0.06s user 0.08s system 98% cpu 0.142 total
# gnu diffutils
diff a b 0.04s user 0.05s system 98% cpu 0.088 total
# (best of 20 runs)
It's still slow than GNU diffutils in this case. But it's much closer.
Testing with real repo data:
For the whole repo, this patch makes xdiff 25% faster:
# hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff]
# xdiff, after
! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100)
# xdiff, before
! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91)
# bdiff
! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67)
For files that are long (ex. commands.py), the speedup is more than 3x, very
significant:
# hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff]
# xdiff, after
! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12)
# xdiff, before
! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4)
# bdiff
! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4)
[1]: https://phab.mercurial-scm.org/D2631
[1]: https://phab.mercurial-scm.org/D2634
REPOSITORY
rHG Mercurial
REVISION DETAIL
https://phab.mercurial-scm.org/D2686
AFFECTED FILES
mercurial/thirdparty/xdiff/xdiffi.c
mercurial/thirdparty/xdiff/xemit.c
mercurial/thirdparty/xdiff/xprepare.c
mercurial/thirdparty/xdiff/xprepare.h
mercurial/thirdparty/xdiff/xtypes.h
CHANGE DETAILS
diff --git a/mercurial/thirdparty/xdiff/xtypes.h b/mercurial/thirdparty/xdiff/xtypes.h
--- a/mercurial/thirdparty/xdiff/xtypes.h
+++ b/mercurial/thirdparty/xdiff/xtypes.h
@@ -94,6 +94,7 @@
typedef struct s_xdfenv {
xdfile_t xdf1, xdf2;
+ long prefix_lines, suffix_lines;
} xdfenv_t;
diff --git a/mercurial/thirdparty/xdiff/xprepare.h b/mercurial/thirdparty/xdiff/xprepare.h
--- a/mercurial/thirdparty/xdiff/xprepare.h
+++ b/mercurial/thirdparty/xdiff/xprepare.h
@@ -26,7 +26,7 @@
int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
- xdfenv_t *xe);
+ xdfenv_t *xe, xdemitconf_t const *xecfg);
void xdl_free_env(xdfenv_t *xe);
diff --git a/mercurial/thirdparty/xdiff/xprepare.c b/mercurial/thirdparty/xdiff/xprepare.c
--- a/mercurial/thirdparty/xdiff/xprepare.c
+++ b/mercurial/thirdparty/xdiff/xprepare.c
@@ -61,6 +61,8 @@
static void xdl_free_ctx(xdfile_t *xdf);
static int xdl_clean_mmatch(char const *dis, long i, long s, long e);
static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
+static void xdl_trim_files(mmfile_t *mf1, mmfile_t *mf2, long reserved,
+ xdfenv_t* xe, mmfile_t *out_mf1, mmfile_t *out_mf2);
static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2);
static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2);
@@ -156,6 +158,105 @@
}
+/*
+ * Trim common prefix from files.
+ * Note: need to preserve some lines for shifting to work. For example,
+ *
+ * a.py | common | b.py | common | diff
+ * | p | s | | p | s |
+ * -------------------------------------------
+ * try: | Y | try: | Y |
+ * 1 | Y | 1 | Y |
+ * except: | Y y | except: | Y |
+ * pass | Y y | pass | Y |
+ * try: | Y y | try: | Y | +
+ * 3 | Y | 2 | | +
+ * except: | Y | except: | y | +
+ * pass | Y | pass | y | +
+ * | | try: | y |
+ * | | 3 | Y |
+ * | | except: | Y |
+ * | | pass | Y |
+ *
+ * To make shifting work, common suffix is handled so it cannot overlap with
+ * common prefix (in the above case, lines marked with "y" will not count as
+ * common suffix). Then subtract some O(1) lines leaving room for shifting.
+ *
+ * Find common prefix first, since the diff algorithm moves hunks towards the
+ * end. For example,
+ *
+ * #!python
+ * open('a','w').write('x\n'* 1000)
+ * open('b','w').write('x\n'* 1001)
+ *
+ * Diffing the two files in either direction, will print a hunk at the end.
+ */
+static void xdl_trim_files(mmfile_t *mf1, mmfile_t *mf2, long reserved,
+ xdfenv_t *xe, mmfile_t *out_mf1, mmfile_t *out_mf2) {
+ mmfile_t msmall, mlarge;
+ long plines = 0, pbytes = 0, slines = 0, sbytes = 0, i;
+ const char *pp1, *pp2, *ps1, *ps2;
+
+ /* reserved must >= 0 for the line boundary adjustment to work */
+ if (reserved < 0)
+ reserved = 0;
+
+ if (mf1->size < mf2->size) {
+ memcpy(&msmall, mf1, sizeof(mmfile_t));
+ memcpy(&mlarge, mf2, sizeof(mmfile_t));
+ } else {
+ memcpy(&msmall, mf2, sizeof(mmfile_t));
+ memcpy(&mlarge, mf1, sizeof(mmfile_t));
+ }
+
+ pp1 = msmall.ptr, pp2 = mlarge.ptr;
+ for (i = 0; i < msmall.size && *pp1 == *pp2; ++i) {
+ plines += (*pp1 == '\n');
+ pp1++, pp2++;
+ }
+
+ ps1 = msmall.ptr + msmall.size - 1, ps2 = mlarge.ptr + mlarge.size - 1;
+ for (; ps1 > pp1 && *ps1 == *ps2; ++i) {
+ slines += (*ps1 == '\n');
+ ps1--, ps2--;
+ }
+
+ /* Retract common prefix and suffix boundaries for reserved lines */
+ if (plines <= reserved + 1) {
+ plines = 0;
+ } else {
+ for (i = 0; i <= reserved;) {
+ pp1--;
+ i += (*pp1 == '\n');
+ }
+ /* The new mmfile starts at the next char just after '\n' */
+ pbytes = pp1 - msmall.ptr + 1;
+ plines -= reserved;
+ }
+
+ if (slines <= reserved + 1) {
+ slines = 0;
+ } else {
+ for (i = 0; i <= reserved;) {
+ ps1++;
+ i += (*ps1 == '\n');
+ }
+ /* The new mmfile includes this '\n' */
+ sbytes = msmall.ptr + msmall.size - ps1 - 1;
+ slines -= reserved;
+ if (msmall.ptr[msmall.size - 1] == '\n')
+ slines -= 1;
+ }
+
+ xe->prefix_lines = plines;
+ xe->suffix_lines = slines;
+ out_mf1->ptr = mf1->ptr + pbytes;
+ out_mf1->size = mf1->size - pbytes - sbytes;
+ out_mf2->ptr = mf2->ptr + pbytes;
+ out_mf2->size = mf2->size - pbytes - sbytes;
+}
+
+
static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf) {
unsigned int hbits;
@@ -254,10 +355,14 @@
xdl_cha_free(&xdf->rcha);
}
+/* Minimal reserved lines during file trimming. This is to leave room for
+ * shifting */
+#define MIN_RESERVED_LINES 100
int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
- xdfenv_t *xe) {
- long enl1, enl2, sample;
+ xdfenv_t *xe, xdemitconf_t const *xecfg) {
+ mmfile_t tmf1, tmf2;
+ long enl1, enl2, sample, reserved_lines = MIN_RESERVED_LINES;
xdlclassifier_t cf;
memset(&cf, 0, sizeof(cf));
@@ -270,12 +375,16 @@
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) {
+ if (xecfg)
+ reserved_lines += xecfg->ctxlen;
+ xdl_trim_files(mf1, mf2, reserved_lines, xe, &tmf1, &tmf2);
+
+ if (xdl_prepare_ctx(1, &tmf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
xdl_free_classifier(&cf);
return -1;
}
- if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
+ if (xdl_prepare_ctx(2, &tmf2, enl2, xpp, &cf, &xe->xdf2) < 0) {
xdl_free_ctx(&xe->xdf1);
xdl_free_classifier(&cf);
diff --git a/mercurial/thirdparty/xdiff/xemit.c b/mercurial/thirdparty/xdiff/xemit.c
--- a/mercurial/thirdparty/xdiff/xemit.c
+++ b/mercurial/thirdparty/xdiff/xemit.c
@@ -169,6 +169,7 @@
long s1, s2, e1, e2, lctx;
xdchange_t *xch, *xche;
long funclineprev = -1;
+ long p = xe->prefix_lines;
struct func_line func_line = { 0 };
for (xch = xscr; xch; xch = xche->next) {
@@ -261,7 +262,7 @@
s1 - 1, funclineprev);
funclineprev = s1 - 1;
}
- if (xdl_emit_hunk_hdr(s1 + 1, e1 - s1, s2 + 1, e2 - s2,
+ if (xdl_emit_hunk_hdr(s1 + 1 + p, e1 - s1, s2 + 1 + p, e2 - s2,
func_line.buf, func_line.len, ecb) < 0)
return -1;
diff --git a/mercurial/thirdparty/xdiff/xdiffi.c b/mercurial/thirdparty/xdiff/xdiffi.c
--- a/mercurial/thirdparty/xdiff/xdiffi.c
+++ b/mercurial/thirdparty/xdiff/xdiffi.c
@@ -321,14 +321,14 @@
}
-int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
- xdfenv_t *xe) {
+int xdl_do_diff2(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
+ xdfenv_t *xe, xdemitconf_t const *xecfg) {
long ndiags;
long *kvd, *kvdf, *kvdb;
xdalgoenv_t xenv;
diffdata_t dd1, dd2;
- if (xdl_prepare_env(mf1, mf2, xpp, xe) < 0) {
+ if (xdl_prepare_env(mf1, mf2, xpp, xe, xecfg) < 0) {
return -1;
}
@@ -377,6 +377,12 @@
}
+int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
+ xdfenv_t *xe) {
+ return xdl_do_diff2(mf1, mf2, xpp, xe, NULL);
+}
+
+
static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2) {
xdchange_t *xch;
@@ -1006,30 +1012,38 @@
static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
xdemitconf_t const *xecfg)
{
+ long p = xe->prefix_lines, s = xe->suffix_lines;
xdchange_t *xch, *xche;
if ((xecfg->flags & XDL_EMIT_BDIFFHUNK) != 0) {
long i1 = 0, i2 = 0, n1 = xe->xdf1.nrec, n2 = xe->xdf2.nrec;
for (xch = xscr; xch; xch = xche->next) {
xche = xdl_get_hunk(&xch, xecfg);
if (!xch)
break;
+ if (xch != xche)
+ xdl_bug("xch != xche");
+ xch->i1 += p;
+ xch->i2 += p;
if (xch->i1 > i1 || xch->i2 > i2) {
- if (xecfg->hunk_func(i1, xch->i1, i2, xch->i2, ecb->priv) < 0)
+ if (xecfg->hunk_func(i1, xch->i1, i2, xch->i2,
+ ecb->priv) < 0)
return -1;
}
- i1 = xche->i1 + xche->chg1;
- i2 = xche->i2 + xche->chg2;
+ i1 = xch->i1 + xch->chg1;
+ i2 = xch->i2 + xch->chg2;
}
- if (xecfg->hunk_func(i1, n1, i2, n2, ecb->priv) < 0)
+ if (xecfg->hunk_func(i1, n1 + p + s, i2, n2 + p + s,
+ ecb->priv) < 0)
return -1;
} else {
for (xch = xscr; xch; xch = xche->next) {
xche = xdl_get_hunk(&xch, xecfg);
if (!xch)
break;
- if (xecfg->hunk_func(
- xch->i1, xche->i1 + xche->chg1 - xch->i1,
- xch->i2, xche->i2 + xche->chg2 - xch->i2,
+ if (xecfg->hunk_func(xch->i1 + p,
+ xche->i1 + xche->chg1 - xch->i1 + p,
+ xch->i2 + p,
+ xche->i2 + xche->chg2 - xch->i2 + p,
ecb->priv) < 0)
return -1;
}
@@ -1043,7 +1057,7 @@
xdfenv_t xe;
emit_func_t ef = xecfg->hunk_func ? xdl_call_hunk_func : xdl_emit_diff;
- if (xdl_do_diff(mf1, mf2, xpp, &xe) < 0) {
+ if (xdl_do_diff2(mf1, mf2, xpp, &xe, xecfg) < 0) {
return -1;
}
To: quark, #hg-reviewers
Cc: mercurial-devel
More information about the Mercurial-devel
mailing list