# HG changeset patch
# User Rodrigo Damazio Bovendorp <rdamazio@google.com>
# Date 2020-07-10 03:46:52
# Node ID 263cf0f60b70aa62cf81a45c6012afe531dd8c62
# Parent  f204ba74004bbcd7d7ba7ab6586d16a95ddd4733

fix: prefetch file contents

This prevents the worker subprocesses from contacting the server individually,
which is either inefficient, or leads to problems if the connection is shared
among them.

Differential Revision: https://phab.mercurial-scm.org/D8723

diff --git a/hgext/fix.py b/hgext/fix.py
--- a/hgext/fix.py
+++ b/hgext/fix.py
@@ -271,6 +271,11 @@ def fix(ui, repo, *pats, **opts):
         basepaths = getbasepaths(repo, opts, workqueue, basectxs)
         fixers = getfixers(ui)
 
+        # Rather than letting each worker independently fetch the files
+        # (which also would add complications for shared/keepalive
+        # connections), prefetch them all first.
+        _prefetchfiles(repo, workqueue, basepaths)
+
         # There are no data dependencies between the workers fixing each file
         # revision, so we can use all available parallelism.
         def getfixes(items):
@@ -630,6 +635,24 @@ def getbasectxs(repo, opts, revstofix):
                 basectxs[rev].add(pctx)
     return basectxs
 
+def _prefetchfiles(repo, workqueue, basepaths):
+    toprefetch = set()
+
+    # Prefetch the files that will be fixed.
+    for rev, path in workqueue:
+        if rev == wdirrev:
+            continue
+        toprefetch.add((rev, path))
+
+    # Prefetch the base contents for lineranges().
+    for (baserev, fixrev, path), basepath in basepaths.items():
+        toprefetch.add((baserev, basepath))
+
+    if toprefetch:
+        scmutil.prefetchfiles(repo, [
+            (rev, scmutil.matchfiles(repo, [path])) for rev, path in toprefetch
+        ])
+
 
 def fixfile(ui, repo, opts, fixers, fixctx, path, basepaths, basectxs):
     """Run any configured fixers that should affect the file in this context