# HG changeset patch
# User Jun Wu <quark@fb.com>
# Date 1472826059 -3600
# Node ID 2f6d5c60f6fc5186e931cbd2deb407517c08fc74
# Parent  d3b2da20a9c58064e456b5bac3587858d4223d7e
annotate: pre-calculate the "needed" dictionary (issue5360)

The "needed" dict is used as a reference counter to free items in the giant
"hist" dict. However, currently it is not very accurate and can lead to
dropping "hist" items unnecessarily, for example, with the following DAG,

       -3-
      /   \
  0--1--2--4--

The current algorithm will visit and calculate rev 1 twice, undesired. And
it tries to be smart by clearing rev 1's parents: "pcache[1] = []" at the
time hist[1] being accessed (note: hist[1] needs to be used twice, by rev 2
and rev 3). It can result in incorrect results if p1 of rev 4 deletes chunks
belonging to rev 0.

However, simply removing "needed" is not okay, because it will consume 10x
memory:

  # without any change
  % HGRCPATH= lrun ./hg annotate mercurial/commands.py -r d130a38 3>&2 [1]
  MEMORY   49074176
  CPUTIME  9.213
  REALTIME 9.270

  # with "needed" removed
  MEMORY   637673472
  CPUTIME  8.164
  REALTIME 8.249

This patch moves "needed" (and "pcache") calculation to a separate DFS to
address the issue. It improves perf and fixes issue5360 by correctly reusing
hist, while maintaining low memory usage. Some additional attempt has been
made to further reduce memory usage, like changing "pcache[f] = []" to "del
pcache[f]". Therefore the result can be both faster and lower memory usage:

  # with this patch applied
  MEMORY   47575040
  CPUTIME  7.870
  REALTIME 7.926

[1]: lrun is a lightweight sandbox built on Linux cgroup and namespace. It's
     used to measure CPU and memory usage here. Source code is available at
     github.com/quark-zju/lrun.

diff -r d3b2da20a9c5 -r 2f6d5c60f6fc mercurial/context.py
--- a/mercurial/context.py	Thu Sep 01 14:01:43 2016 -0500
+++ b/mercurial/context.py	Fri Sep 02 15:20:59 2016 +0100
@@ -990,15 +990,29 @@
         # bit recursion-hostile. Instead we do an iterative
         # depth-first search.
 
+        # 1st DFS pre-calculates pcache and needed
         visit = [base]
-        hist = {}
         pcache = {}
         needed = {base: 1}
         while visit:
+            f = visit.pop()
+            if f in pcache:
+                continue
+            pl = parents(f)
+            pcache[f] = pl
+            for p in pl:
+                needed[p] = needed.get(p, 0) + 1
+                if p not in pcache:
+                    visit.append(p)
+
+        # 2nd DFS does the actual annotate
+        visit[:] = [base]
+        hist = {}
+        while visit:
             f = visit[-1]
-            pcached = f in pcache
-            if not pcached:
-                pcache[f] = parents(f)
+            if f in hist:
+                visit.pop()
+                continue
 
             ready = True
             pl = pcache[f]
@@ -1006,18 +1020,11 @@
                 if p not in hist:
                     ready = False
                     visit.append(p)
-                if not pcached:
-                    needed[p] = needed.get(p, 0) + 1
             if ready:
                 visit.pop()
-                reusable = f in hist
-                if reusable:
-                    curr = hist[f]
-                else:
-                    curr = decorate(f.data(), f)
+                curr = decorate(f.data(), f)
                 for p in pl:
-                    if not reusable:
-                        curr = pair(hist[p], curr)
+                    curr = pair(hist[p], curr)
                     if needed[p] == 1:
                         del hist[p]
                         del needed[p]
@@ -1025,7 +1032,7 @@
                         needed[p] -= 1
 
                 hist[f] = curr
-                pcache[f] = []
+                del pcache[f]
 
         return zip(hist[base][0], hist[base][1].splitlines(True))
 
diff -r d3b2da20a9c5 -r 2f6d5c60f6fc tests/test-annotate.t
--- a/tests/test-annotate.t	Thu Sep 01 14:01:43 2016 -0500
+++ b/tests/test-annotate.t	Fri Sep 02 15:20:59 2016 +0100
@@ -606,3 +606,35 @@
   3: B
 
   $ cd ..
+
+Issue5360: Deleted chunk in p1 of a merge changeset
+
+  $ hg init repo-5360
+  $ cd repo-5360
+  $ echo 1 > a
+  $ hg commit -A a -m 1
+  $ echo 2 >> a
+  $ hg commit -m 2
+  $ echo a > a
+  $ hg commit -m a
+  $ hg update '.^' -q
+  $ echo 3 >> a
+  $ hg commit -m 3 -q
+  $ hg merge 2 -q
+  $ cat > a << EOF
+  > b
+  > 1
+  > 2
+  > 3
+  > a
+  > EOF
+  $ hg resolve --mark -q
+  $ hg commit -m m
+  $ hg annotate a
+  4: b
+  0: 1
+  1: 2
+  3: 3
+  2: a
+
+  $ cd ..