# HG changeset patch
# User Pierre-Yves David <pierre-yves.david@octobus.net>
# Date 2022-11-19 00:35:01
# Node ID dcb2581e33bef108fa21d6245eb3313a643c3135
# Parent  55c6ebd11cb9670d5535fa700fdb877d270d1a40

memory-usage: fix `hg log --follow --rev R F` space complexity

When running `hg log --follow --rev REVS FILES`, the log code will walk the
history of all FILES starting from the file revisions that exists in each REVS.

Before doing so, it looks if the files actually exists in the target revisions.
To do so, it opens the manifest of each revision in REVS to look up if we find
the associated items in FILES.

Before this changeset this was done in a way that created a changectx for
each target revision, keeping them in memory while we look into each file.

If the set of REVS is large, this means keeping the manifest for each entry in
REVS in memory. That can be large… if REV is in the form `::X`, this can quickly
become huge and saturate the memory. We have seen usage allocating 2GB per
second until memory runs out.

So this changeset invert the two loop so that only one revision is kept in
memory during the operation. This solve the memory explosion issue.

diff --git a/mercurial/logcmdutil.py b/mercurial/logcmdutil.py
--- a/mercurial/logcmdutil.py
+++ b/mercurial/logcmdutil.py
@@ -817,17 +817,26 @@ def _makematcher(repo, revs, wopts):
             # There may be the case that a path doesn't exist in some (but
             # not all) of the specified start revisions, but let's consider
             # the path is valid. Missing files will be warned by the matcher.
-            startctxs = [repo[r] for r in revs]
-            for f in match.files():
-                found = False
-                for c in startctxs:
-                    if f in c:
-                        found = True
-                    elif c.hasdir(f):
+            all_files = list(match.files())
+            missing_files = set(all_files)
+            files = all_files
+            for r in revs:
+                if not files:
+                    # We don't have any file to check anymore.
+                    break
+                ctx = repo[r]
+                for f in files:
+                    if f in ctx:
+                        missing_files.discard(f)
+                    elif ctx.hasdir(f):
                         # If a directory exists in any of the start revisions,
                         # take the slow path.
-                        found = slowpath = True
-                if not found:
+                        missing_files.discard(f)
+                        slowpath = True
+                        # we found on slow path, no need to search for more.
+                        files = missing_files
+            for f in all_files:
+                if f in missing_files:
                     raise error.StateError(
                         _(
                             b'cannot follow file not in any of the specified '