Patchwork D11265: debugrebuildfncache: add a cheaper option to rebuild the fncache

login
register
mail settings
Submitter phabricator
Date Aug. 6, 2021, 8:45 p.m.
Message ID <differential-rev-PHID-DREV-w6noji44ru3hnn6t35ql-req@mercurial-scm.org>
Download mbox | patch
Permalink /patch/49579/
State Superseded
Headers show

Comments

phabricator - Aug. 6, 2021, 8:45 p.m.
valentin.gatienbaron created this revision.
Herald added a reviewer: hg-reviewers.
Herald added a subscriber: mercurial-patches.

REVISION SUMMARY
  On my repository, debugrebuildfncache takes 5-10min with the lock.
  
  With the flag added in this commit, it takes 10s. The tradeoff is that
  it only recovers from certain kinds of corruptions. It is intended to
  to recover faster from fncaches broken by a revlog split during a
  transaction that ends up being rolled back.

REPOSITORY
  rHG Mercurial

BRANCH
  default

REVISION DETAIL
  https://phab.mercurial-scm.org/D11265

AFFECTED FILES
  mercurial/debugcommands.py
  mercurial/repair.py
  tests/test-completion.t
  tests/test-transaction-rollback-on-revlog-split.t

CHANGE DETAILS




To: valentin.gatienbaron, #hg-reviewers
Cc: mercurial-patches, mercurial-devel

Patch

diff --git a/tests/test-transaction-rollback-on-revlog-split.t b/tests/test-transaction-rollback-on-revlog-split.t
--- a/tests/test-transaction-rollback-on-revlog-split.t
+++ b/tests/test-transaction-rollback-on-revlog-split.t
@@ -86,6 +86,10 @@ 
    warning: revlog 'data/file.d' not in fncache!
   1 warnings encountered!
   hint: run "hg debugrebuildfncache" to recover from corrupt fncache
+  $ hg debugrebuildfncache --only-data
+  adding data/file.d
+  1 items added, 0 removed from fncache
+  $ hg verify -q
   $ cd ..
 
 
diff --git a/tests/test-completion.t b/tests/test-completion.t
--- a/tests/test-completion.t
+++ b/tests/test-completion.t
@@ -314,7 +314,7 @@ 
   debugpushkey: 
   debugpvec: 
   debugrebuilddirstate: rev, minimal
-  debugrebuildfncache: 
+  debugrebuildfncache: only-data
   debugrename: rev
   debugrequires: 
   debugrevlog: changelog, manifest, dir, dump
diff --git a/mercurial/repair.py b/mercurial/repair.py
--- a/mercurial/repair.py
+++ b/mercurial/repair.py
@@ -441,7 +441,7 @@ 
                 yield repo.manifestlog.getstorage(dir)
 
 
-def rebuildfncache(ui, repo):
+def rebuildfncache(ui, repo, only_data=False):
     """Rebuilds the fncache file from repo history.
 
     Missing entries will be added. Extra entries will be removed.
@@ -465,28 +465,40 @@ 
         newentries = set()
         seenfiles = set()
 
-        progress = ui.makeprogress(
-            _(b'rebuilding'), unit=_(b'changesets'), total=len(repo)
-        )
-        for rev in repo:
-            progress.update(rev)
+        if only_data:
+            # Trust the listing of .i from the fncache, but not the .d. This is
+            # much faster, because we only need to stat every possible .d files,
+            # instead of reading the full changelog
+            for f in fnc:
+                if f[:5] == b'data/' and f[-2:] == b'.i':
+                    seenfiles.add(f[5:-2])
+                    newentries.add(f)
+                    dataf = f[:-2] + b'.d'
+                    if repo.store._exists(dataf):
+                        newentries.add(dataf)
+        else:
+            progress = ui.makeprogress(
+                _(b'rebuilding'), unit=_(b'changesets'), total=len(repo)
+            )
+            for rev in repo:
+                progress.update(rev)
 
-            ctx = repo[rev]
-            for f in ctx.files():
-                # This is to minimize I/O.
-                if f in seenfiles:
-                    continue
-                seenfiles.add(f)
+                ctx = repo[rev]
+                for f in ctx.files():
+                    # This is to minimize I/O.
+                    if f in seenfiles:
+                        continue
+                    seenfiles.add(f)
 
-                i = b'data/%s.i' % f
-                d = b'data/%s.d' % f
+                    i = b'data/%s.i' % f
+                    d = b'data/%s.d' % f
 
-                if repo.store._exists(i):
-                    newentries.add(i)
-                if repo.store._exists(d):
-                    newentries.add(d)
+                    if repo.store._exists(i):
+                        newentries.add(i)
+                    if repo.store._exists(d):
+                        newentries.add(d)
 
-        progress.complete()
+            progress.complete()
 
         if requirements.TREEMANIFEST_REQUIREMENT in repo.requirements:
             # This logic is safe if treemanifest isn't enabled, but also
diff --git a/mercurial/debugcommands.py b/mercurial/debugcommands.py
--- a/mercurial/debugcommands.py
+++ b/mercurial/debugcommands.py
@@ -2911,10 +2911,22 @@ 
         dirstate.rebuild(ctx.node(), ctx.manifest(), changedfiles)
 
 
-@command(b'debugrebuildfncache', [], b'')
-def debugrebuildfncache(ui, repo):
+@command(
+    b'debugrebuildfncache',
+    [
+        (
+            b'',
+            b'only-data',
+            False,
+            _(b'only look for wrong .d files (much faster)'),
+        )
+    ],
+    b'',
+)
+def debugrebuildfncache(ui, repo, **opts):
     """rebuild the fncache file"""
-    repair.rebuildfncache(ui, repo)
+    opts = pycompat.byteskwargs(opts)
+    repair.rebuildfncache(ui, repo, opts.get(b"only_data"))
 
 
 @command(