ancestor: caching the parent list to improve performance

When computing the DAG depth, we walk through all ancestors: this commit adds
memoization during that first step. Then, the memorized parents are fetched
from a dict instead of calling parents() on each vertex.

This tweak, according to Kcachegrind, improves ancestor() performance by 16%
when cloning a big repository.

mercurial/ancestor.py

@@ -1,83 +1,85 b''
 # ancestor.py - generic DAG ancestor algorithm for mercurial
 #
 # Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import heapq
 
 def ancestor(a, b, pfunc):
     """
     return the least common ancestor of nodes a and b or None if there
     is no such ancestor.
 
     pfunc must return a list of parent vertices
     """
 
     if a == b:
         return a
 
     # find depth from root of all ancestors
+    parentcache = {}
     visit = [a, b]
     depth = {}
     while visit:
         vertex = visit[-1]
         pl = pfunc(vertex)
+        parentcache[vertex] = pl
         if not pl:
             depth[vertex] = 0
             visit.pop()
         else:
             for p in pl:
                 if p == a or p == b: # did we find a or b as a parent?
                     return p # we're done
                 if p not in depth:
                     visit.append(p)
             if visit[-1] == vertex:
                 depth[vertex] = min([depth[p] for p in pl]) - 1
                 visit.pop()
 
     # traverse ancestors in order of decreasing distance from root
     def ancestors(vertex):
         h = [(depth[vertex], vertex)]
         seen = {}
         while h:
             d, n = heapq.heappop(h)
             if n not in seen:
                 seen[n] = 1
                 yield (d, n)
-                for p in pfunc(n):
+                for p in parentcache[n]:
                     heapq.heappush(h, (depth[p], p))
 
     def generations(vertex):
         sg, s = None, {}
         for g, v in ancestors(vertex):
             if g != sg:
                 if sg:
                     yield sg, s
                 sg, s = g, {v:1}
             else:
                 s[v] = 1
         yield sg, s
 
     x = generations(a)
     y = generations(b)
     gx = x.next()
     gy = y.next()
 
     # increment each ancestor list until it is closer to root than
     # the other, or they match
     try:
         while 1:
             if gx[0] == gy[0]:
                 for v in gx[1]:
                     if v in gy[1]:
                         return v
                 gy = y.next()
                 gx = x.next()
             elif gx[0] > gy[0]:
                 gy = y.next()
             else:
                 gx = x.next()
     except StopIteration:
         return None