# HG changeset patch
# User Kyle Lippincott <spectral@google.com>
# Date 2020-09-16 19:13:46
# Node ID 89f0d9f87701cb953dfa48b8deb456fa7a97e1a8
# Parent  93a0f3ba36bbf97d2fbcd8d3d002c2c992421896

branchmap: add a cache validation cache, avoid expensive re-hash on every use

In a pathological `hg log` case, we end up executing the branchmap validity
checking twice per commit displayed. Or maybe we always do, and I just noticed
because it's really slow in this repo for some reason.

Before:
```
  Time (mean ± σ):      9.816 s ±  0.071 s    [User: 9.435 s, System: 0.392 s]

  Range (min … max):    9.709 s …  9.920 s
```

After:
```
  Time (mean ± σ):      8.671 s ±  0.078 s    [User: 8.309 s, System: 0.392 s]

  Range (min … max):    8.594 s …  8.816 s
```

Differential Revision: https://phab.mercurial-scm.org/D9023

diff --git a/mercurial/changelog.py b/mercurial/changelog.py
--- a/mercurial/changelog.py
+++ b/mercurial/changelog.py
@@ -403,9 +403,21 @@ class changelog(revlog.revlog):
         self._delayed = False
         self._delaybuf = None
         self._divert = False
-        self.filteredrevs = frozenset()
+        self._filteredrevs = frozenset()
+        self._filteredrevs_hashcache = {}
         self._copiesstorage = opener.options.get(b'copies-storage')
 
+    @property
+    def filteredrevs(self):
+        return self._filteredrevs
+
+    @filteredrevs.setter
+    def filteredrevs(self, val):
+        # Ensure all updates go through this function
+        assert isinstance(val, frozenset)
+        self._filteredrevs = val
+        self._filteredrevs_hashcache = {}
+
     def delayupdate(self, tr):
         """delay visibility of index updates to other readers"""
 
diff --git a/mercurial/scmutil.py b/mercurial/scmutil.py
--- a/mercurial/scmutil.py
+++ b/mercurial/scmutil.py
@@ -364,13 +364,15 @@ def filteredhash(repo, maxrev):
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
-    key = None
-    revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
-    if revs:
-        s = hashutil.sha1()
-        for rev in revs:
-            s.update(b'%d;' % rev)
-        key = s.digest()
+    key = cl._filteredrevs_hashcache.get(maxrev)
+    if not key:
+        revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
+        if revs:
+            s = hashutil.sha1()
+            for rev in revs:
+                s.update(b'%d;' % rev)
+            key = s.digest()
+            cl._filteredrevs_hashcache[maxrev] = key
     return key