diff mercurial/revset.py @ 34065:c6c8a52e28c9

revset: optimize "draft() & ::x" pattern

The `draft() & ::x` type query could be common for selecting one or more
draft feature branches being worked on.

Before this patch, `::x` may travel through the changelog DAG for a long
distance until it gets a smaller revision number than `min(draft())`. It
could be very slow on long changelog with distant (in terms of revision
numbers) drafts.

This patch adds a fast path for this situation, and will stop traveling the
changelog DAG once `::x` hits a non-draft revision.

The fast path also works for `secret()` and `not public()`.

To measure the performance difference, I used drawdag to create a repo that
emulates distant drafts:

          DRAFT4
           |
          DRAFT3 # draft
          /
  PUBLIC9999 # public
      |
  PUBLIC9998
      |
      .   DRAFT2
      .    |
      .   DRAFT1 # draft
      |   /
  PUBLIC0001 # public

And measured the performance using the repo:

  (BEFORE)
  $ hg perfrevset 'draft() & ::(DRAFT2+DRAFT4)'
  ! wall 0.017132 comb 0.010000 user 0.010000 sys 0.000000 (best of 156)
  $ hg perfrevset 'draft() & ::(all())'
  ! wall 0.024221 comb 0.030000 user 0.030000 sys 0.000000 (best of 113)
  (AFTER)
  $ hg perfrevset 'draft() & ::(DRAFT2+DRAFT4)'
  ! wall 0.000243 comb 0.000000 user 0.000000 sys 0.000000 (best of 9303)
  $ hg perfrevset 'draft() & ::(all())'
  ! wall 0.004319 comb 0.000000 user 0.000000 sys 0.000000 (best of 655)

Differential Revision: https://phab.mercurial-scm.org/D441

--- a/mercurial/revset.py	Fri Sep 01 12:13:17 2017 -0700
+++ b/mercurial/revset.py	Mon Aug 28 14:49:00 2017 -0700
@@ -1577,6 +1577,37 @@
     getargs(x, 0, 0, "_notpublic takes no arguments")
     return _phase(repo, subset, phases.draft, phases.secret)
 
+# for internal use
+@predicate('_phaseandancestors(phasename, set)', safe=True)
+def _phaseandancestors(repo, subset, x):
+    # equivalent to (phasename() & ancestors(set)) but more efficient
+    # phasename could be one of 'draft', 'secret', or '_notpublic'
+    args = getargs(x, 2, 2, "_phaseandancestors requires two arguments")
+    phasename = getsymbol(args[0])
+    s = getset(repo, fullreposet(repo), args[1])
+
+    draft = phases.draft
+    secret = phases.secret
+    phasenamemap = {
+        '_notpublic': draft,
+        'draft': draft, # follow secret's ancestors
+        'secret': secret,
+    }
+    if phasename not in phasenamemap:
+        raise error.ParseError('%r is not a valid phasename' % phasename)
+
+    minimalphase = phasenamemap[phasename]
+    getphase = repo._phasecache.phase
+
+    def cutfunc(rev):
+        return getphase(repo, rev) < minimalphase
+
+    revs = dagop.revancestors(repo, s, cutfunc=cutfunc)
+
+    if phasename == 'draft': # need to remove secret changesets
+        revs = revs.filter(lambda r: getphase(repo, r) == draft)
+    return subset & revs
+
 @predicate('public()', safe=True)
 def public(repo, subset, x):
     """Changeset in public phase."""