From patchwork Fri Dec 28 18:12:53 2018
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [7,of,8,V3] delta: have a native implementation of _findsnapshot
From: Boris Feld <boris.feld@octobus.net>
X-Patchwork-Id: 37384
Message-Id: <d5912247e9a798f3a329.1546020773@pc62.home>
To: mercurial-devel@mercurial-scm.org
Date: Fri, 28 Dec 2018 19:12:53 +0100

# HG changeset patch
# User Boris Feld <boris.feld@octobus.net>
# Date 1545297320 -3600
#      Thu Dec 20 10:15:20 2018 +0100
# Node ID d5912247e9a798f3a329794f64ce0627af0ba107
# Parent  f4307f117d823efa9497a8ffa46bf13f68a16c2d
# EXP-Topic sparse-revlog
# Available At https://bitbucket.org/octobus/mercurial-devel/
#              hg pull https://bitbucket.org/octobus/mercurial-devel/ -r d5912247e9a7
delta: have a native implementation of _findsnapshot

The function might traverse a lot of revision, a native implementation get
significantly faster.

example affected manifest write
before: 0.114989
after:  0.067141 (-42%)

diff --git a/mercurial/cext/revlog.c b/mercurial/cext/revlog.c
--- a/mercurial/cext/revlog.c
+++ b/mercurial/cext/revlog.c
@@ -1049,6 +1049,80 @@ static PyObject *index_issnapshot(indexO
 	return PyBool_FromLong((long)issnap);
 }
 
+static PyObject *index_findsnapshots(indexObject *self, PyObject *args)
+{
+
+	Py_ssize_t start_rev;
+	PyObject *cache;
+	Py_ssize_t base;
+	Py_ssize_t rev;
+	int issnap;
+	PyObject *key;
+	bool newallvalues;
+	PyObject *allvalues;
+	PyObject *value;
+	const Py_ssize_t length = index_length(self);
+	if (!PyArg_ParseTuple(args, "On", &cache, &start_rev)) {
+		return NULL;
+	}
+	if (!PyDict_Check(cache)) {
+		PyErr_SetString(PyExc_TypeError,
+		                "cache argument must be a dict");
+		return NULL;
+	}
+	for (rev = start_rev; rev < length; rev++) {
+		issnap = index_issnapshotrev(self, rev);
+		if (issnap < 0) {
+			goto bail;
+		}
+		if (issnap == 0) {
+			continue;
+		}
+		base = (Py_ssize_t)index_baserev(self, rev);
+		if (base == rev) {
+			base = -1;
+		}
+		if (base == -2) {
+			assert(PyErr_Occurred());
+			goto bail;
+		}
+		key = PyInt_FromSsize_t(base);
+		newallvalues = false;
+		allvalues = PyDict_GetItem(cache, key);
+		if (allvalues == NULL && PyErr_Occurred()) {
+			goto bail;
+		}
+		if (allvalues == NULL) {
+			allvalues = PyList_New(0);
+			newallvalues = true;
+			if (PyDict_SetItem(cache, key, allvalues) < 0) {
+				goto bail;
+			}
+		}
+		value = PyInt_FromSsize_t(rev);
+		if (PyList_Append(allvalues, value)) {
+			goto bail;
+		}
+		Py_XDECREF(key);
+		if (newallvalues) {
+			Py_XDECREF(allvalues);
+		}
+		Py_XDECREF(value);
+		key = NULL;
+		allvalues = NULL;
+		value = NULL;
+	}
+	Py_INCREF(Py_None);
+	return Py_None;
+bail:
+	Py_XDECREF(key);
+	if (newallvalues) {
+		Py_XDECREF(allvalues);
+	}
+	Py_XDECREF(value);
+	return NULL;
+}
+
 static PyObject *index_deltachain(indexObject *self, PyObject *args)
 {
 	int rev, generaldelta;
@@ -2663,6 +2737,8 @@ static PyMethodDef index_methods[] = {
      "get filtered head revisions"}, /* Can always do filtering */
     {"issnapshot", (PyCFunction)index_issnapshot, METH_O,
      "True if the object is a snapshot"},
+    {"findsnapshots", (PyCFunction)index_findsnapshots, METH_VARARGS,
+     "Gather snapshot data in a cache dict"},
     {"deltachain", (PyCFunction)index_deltachain, METH_VARARGS,
      "determine revisions with deltas to reconstruct fulltext"},
     {"slicechunktodensity", (PyCFunction)index_slicechunktodensity,
diff --git a/mercurial/revlogutils/deltas.py b/mercurial/revlogutils/deltas.py
--- a/mercurial/revlogutils/deltas.py
+++ b/mercurial/revlogutils/deltas.py
@@ -30,6 +30,7 @@ from ..thirdparty import (
 from .. import (
     error,
     mdiff,
+    util,
 )
 
 # maximum <delta-chain-data>/<revision-text-length> ratio
@@ -688,11 +689,14 @@ def _candidategroups(revlog, textlen, p1
 
 def _findsnapshots(revlog, cache, start_rev):
     """find snapshot from start_rev to tip"""
-    deltaparent = revlog.deltaparent
-    issnapshot = revlog.issnapshot
-    for rev in revlog.revs(start_rev):
-        if issnapshot(rev):
-            cache[deltaparent(rev)].append(rev)
+    if util.safehasattr(revlog.index, 'findsnapshots'):
+        revlog.index.findsnapshots(cache, start_rev)
+    else:
+        deltaparent = revlog.deltaparent
+        issnapshot = revlog.issnapshot
+        for rev in revlog.revs(start_rev):
+            if issnapshot(rev):
+                cache[deltaparent(rev)].append(rev)
 
 def _refinedgroups(revlog, p1, p2, cachedelta):
     good = None