dirstate: introduce a "tracked-key" feature
A new format variant is introduced. When used, a `tracked-key` file will be
generated. That file will be update when the set of tracked file might have
changed. This will be useful for external automation (e.g. build tool) to be
notified when the set of relevant files changes.
One of the motivation for this changes is to mitigate effect dirstate-v2 has on
such automation. Since the dirstate file is updated much more frequently on
dirstate-v2, monitoring update to that file is no longer a viable strategy.
See the associated documentation for details about the feature
To prevent older client to update the repository without updating that file, a
new requirements is introduced.
The `postfinalizegenerators` business is a bit weird, so I'll likely clean that
up soon.
Differential Revision: https://phab.mercurial-scm.org/D12124
--- a/mercurial/configitems.py Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/configitems.py Mon Jan 31 08:44:48 2022 +0100
@@ -1284,6 +1284,12 @@
)
coreconfigitem(
b'format',
+ b'exp-dirstate-tracked-key-version',
+ default=0,
+ experimental=True,
+)
+coreconfigitem(
+ b'format',
b'dotencode',
default=True,
)
--- a/mercurial/dirstate.py Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/dirstate.py Mon Jan 31 08:44:48 2022 +0100
@@ -12,6 +12,7 @@
import errno
import os
import stat
+import uuid
from .i18n import _
from .pycompat import delattr
@@ -23,6 +24,7 @@
encoding,
error,
match as matchmod,
+ node,
pathutil,
policy,
pycompat,
@@ -99,6 +101,7 @@
sparsematchfn,
nodeconstants,
use_dirstate_v2,
+ use_tracked_key=False,
):
"""Create a new dirstate object.
@@ -107,6 +110,7 @@
the dirstate.
"""
self._use_dirstate_v2 = use_dirstate_v2
+ self._use_tracked_key = use_tracked_key
self._nodeconstants = nodeconstants
self._opener = opener
self._validate = validate
@@ -115,11 +119,15 @@
# ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
# UNC path pointing to root share (issue4557)
self._rootdir = pathutil.normasprefix(root)
+ # True is any internal state may be different
self._dirty = False
+ # True if the set of tracked file may be different
+ self._dirty_tracked_set = False
self._ui = ui
self._filecache = {}
self._parentwriters = 0
self._filename = b'dirstate'
+ self._filename_tk = b'dirstate-tracked-key'
self._pendingfilename = b'%s.pending' % self._filename
self._plchangecallbacks = {}
self._origpl = None
@@ -409,6 +417,7 @@
if a in self.__dict__:
delattr(self, a)
self._dirty = False
+ self._dirty_tracked_set = False
self._parentwriters = 0
self._origpl = None
@@ -446,6 +455,8 @@
pre_tracked = self._map.set_tracked(filename)
if reset_copy:
self._map.copymap.pop(filename, None)
+ if pre_tracked:
+ self._dirty_tracked_set = True
return pre_tracked
@requires_no_parents_change
@@ -460,6 +471,7 @@
ret = self._map.set_untracked(filename)
if ret:
self._dirty = True
+ self._dirty_tracked_set = True
return ret
@requires_no_parents_change
@@ -544,6 +556,13 @@
# this. The test agrees
self._dirty = True
+ old_entry = self._map.get(filename)
+ if old_entry is None:
+ prev_tracked = False
+ else:
+ prev_tracked = old_entry.tracked
+ if prev_tracked != wc_tracked:
+ self._dirty_tracked_set = True
self._map.reset_state(
filename,
@@ -702,20 +721,44 @@
if not self._dirty:
return
- filename = self._filename
+ write_key = self._use_tracked_key and self._dirty_tracked_set
if tr:
# delay writing in-memory changes out
+ if write_key:
+ tr.addfilegenerator(
+ b'dirstate-0-key-pre',
+ (self._filename_tk,),
+ lambda f: self._write_tracked_key(tr, f),
+ location=b'plain',
+ )
tr.addfilegenerator(
b'dirstate-1-main',
(self._filename,),
lambda f: self._writedirstate(tr, f),
location=b'plain',
)
+ if write_key:
+ tr.addfilegenerator(
+ b'dirstate-2-key-post',
+ (self._filename_tk,),
+ lambda f: self._write_tracked_key(tr, f),
+ location=b'plain',
+ )
return
file = lambda f: self._opener(f, b"w", atomictemp=True, checkambig=True)
+ if write_key:
+ # we change the key-file before changing the dirstate to make sure
+ # reading invalidate there cache before we start writing
+ with file(self._filename_tk) as f:
+ self._write_tracked_key(tr, f)
with file(self._filename) as f:
self._writedirstate(tr, f)
+ if write_key:
+ # we update the key-file after writing to make sure reader have a
+ # key that match the newly written content
+ with file(self._filename_tk) as f:
+ self._write_tracked_key(tr, f)
def addparentchangecallback(self, category, callback):
"""add a callback to be called when the wd parents are changed
@@ -736,9 +779,13 @@
):
callback(self, self._origpl, self._pl)
self._origpl = None
-
self._map.write(tr, st)
self._dirty = False
+ self._dirty_tracked_set = False
+
+ def _write_tracked_key(self, tr, f):
+ key = node.hex(uuid.uuid4().bytes)
+ f.write(b"1\n%s\n" % key) # 1 is the format version
def _dirignore(self, f):
if self._ignore(f):
--- a/mercurial/helptext/config.txt Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/helptext/config.txt Mon Jan 31 08:44:48 2022 +0100
@@ -944,6 +944,42 @@
For a more comprehensive guide, see :hg:`help internals.dirstate-v2`.
+``exp-dirstate-tracked-key-version``
+ Enable or disable the writing of "tracked key" file alongside the dirstate.
+
+ That "tracked-key" can help external automations to detect changes to the
+ set of tracked files.
+
+ Two values are currently supported:
+ - 0: no file is written (the default),
+ - 1: a file in version "1" is written.
+
+ The tracked-key is written in a new `.hg/dirstate-tracked-key`. That file
+ contains two lines:
+ - the first line is the file version (currently: 1),
+ - the second line contains the "tracked-key".
+
+ The tracked-key changes whenever the set of file tracked in the dirstate
+ changes. The general guarantees are:
+ - if the tracked key is identical, the set of tracked file MUST not have changed,
+ - if the tracked key is different, the set of tracked file MIGHT differ.
+
+ They are two "ways" to use this feature:
+
+ 1) monitoring changes to the `.hg/dirstate-tracked-key`, if the file changes
+ the tracked set might have changed.
+
+ 2) storing the value and comparing it to a later value. Beware that it is
+ impossible to achieve atomic writing or reading of the two files involved
+ files (`.hg/dirstate` and `.hg/dirstate-tracked-key`). So it is needed to
+ read the `tracked-key` files twice: before and after reading the tracked
+ set. The `tracked-key` is only usable as a cache key if it had the same
+ value in both cases and must be discarded otherwise.
+
+ To enforce that the `tracked-key` value can be used race-free (with double
+ reading as explained in (2)), the `.hg/dirstate-tracked-key` is written
+ twice: before and after we change the associated `.hg/dirstate` file.
+
``use-persistent-nodemap``
Enable or disable the "persistent-nodemap" feature which improves
performance if the Rust extensions are available.
--- a/mercurial/localrepo.py Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/localrepo.py Mon Jan 31 08:44:48 2022 +0100
@@ -1278,6 +1278,7 @@
requirementsmod.BOOKMARKS_IN_STORE_REQUIREMENT,
requirementsmod.CHANGELOGV2_REQUIREMENT,
requirementsmod.COPIESSDC_REQUIREMENT,
+ requirementsmod.DIRSTATE_TRACKED_KEY_V1,
requirementsmod.DIRSTATE_V2_REQUIREMENT,
requirementsmod.DOTENCODE_REQUIREMENT,
requirementsmod.FNCACHE_REQUIREMENT,
@@ -1742,7 +1743,9 @@
"""Extension point for wrapping the dirstate per-repo."""
sparsematchfn = lambda: sparse.matcher(self)
v2_req = requirementsmod.DIRSTATE_V2_REQUIREMENT
+ tk = requirementsmod.DIRSTATE_TRACKED_KEY_V1
use_dirstate_v2 = v2_req in self.requirements
+ use_tracked_key = tk in self.requirements
return dirstate.dirstate(
self.vfs,
@@ -1752,6 +1755,7 @@
sparsematchfn,
self.nodeconstants,
use_dirstate_v2,
+ use_tracked_key=use_tracked_key,
)
def _dirstatevalidate(self, node):
@@ -3691,6 +3695,17 @@
else:
requirements.add(requirementsmod.SHARED_REQUIREMENT)
+ tracked_key = ui.configint(b'format', b'exp-dirstate-tracked-key-version')
+ if tracked_key:
+ if tracked_key != 1:
+ msg = _("ignoring unknown tracked key version: %d\n")
+ hint = _(
+ "see `hg help config.format.exp-dirstate-tracked-key-version"
+ )
+ ui.warn(msg % tracked_key, hint=hint)
+ else:
+ requirements.add(requirementsmod.DIRSTATE_TRACKED_KEY_V1)
+
return requirements
--- a/mercurial/requirements.py Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/requirements.py Mon Jan 31 08:44:48 2022 +0100
@@ -18,6 +18,7 @@
STORE_REQUIREMENT = b'store'
FNCACHE_REQUIREMENT = b'fncache'
+DIRSTATE_TRACKED_KEY_V1 = b'exp-dirstate-tracked-key-v1'
DIRSTATE_V2_REQUIREMENT = b'dirstate-v2'
# When narrowing is finalized and no longer subject to format changes,
@@ -96,6 +97,7 @@
SHARED_REQUIREMENT,
RELATIVE_SHARED_REQUIREMENT,
SHARESAFE_REQUIREMENT,
+ DIRSTATE_TRACKED_KEY_V1,
DIRSTATE_V2_REQUIREMENT,
}
--- a/mercurial/transaction.py Mon Jan 31 14:26:35 2022 +0100
+++ b/mercurial/transaction.py Mon Jan 31 08:44:48 2022 +0100
@@ -30,7 +30,9 @@
# the changelog having been written).
postfinalizegenerators = {
b'bookmarks',
+ b'dirstate-0-key-pre',
b'dirstate-1-main',
+ b'dirstate-2-key-post',
}
GEN_GROUP_ALL = b'all'
--- a/tests/test-help.t Mon Jan 31 14:26:35 2022 +0100
+++ b/tests/test-help.t Mon Jan 31 08:44:48 2022 +0100
@@ -1599,6 +1599,8 @@
"use-dirstate-v2"
+ "exp-dirstate-tracked-key-version"
+
"use-persistent-nodemap"
"use-share-safe"
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tests/test-status-tracked-key.t Mon Jan 31 08:44:48 2022 +0100
@@ -0,0 +1,163 @@
+==============================
+Test the "tracked key" feature
+==============================
+
+The tracked key feature provide a file that get updated when the set of tracked
+files get updated.
+
+basic setup
+
+ $ cat << EOF >> $HGRCPATH
+ > [format]
+ > exp-dirstate-tracked-key-version=1
+ > EOF
+
+ $ hg init tracked-key-test
+ $ cd tracked-key-test
+ $ hg debugbuilddag '.+10' -n
+ $ hg log -G -T '{rev} {desc} {files}\n'
+ o 10 r10 nf10
+ |
+ o 9 r9 nf9
+ |
+ o 8 r8 nf8
+ |
+ o 7 r7 nf7
+ |
+ o 6 r6 nf6
+ |
+ o 5 r5 nf5
+ |
+ o 4 r4 nf4
+ |
+ o 3 r3 nf3
+ |
+ o 2 r2 nf2
+ |
+ o 1 r1 nf1
+ |
+ o 0 r0 nf0
+
+ $ hg up tip
+ 11 files updated, 0 files merged, 0 files removed, 0 files unresolved
+ $ hg files
+ nf0
+ nf1
+ nf10
+ nf2
+ nf3
+ nf4
+ nf5
+ nf6
+ nf7
+ nf8
+ nf9
+
+key-file exists
+-----------
+
+The tracked key file should exist
+
+ $ ls -1 .hg/dirstate*
+ .hg/dirstate
+ .hg/dirstate-tracked-key
+
+key-file stay the same if the tracked set is unchanged
+------------------------------------------------------
+
+(copy its content for later comparison)
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ echo foo >> nf0
+ $ sleep 1
+ $ hg status
+ M nf0
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ $ hg revert -C nf0
+ $ sleep 1
+ $ hg status
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+
+key-file change if the tracked set is changed manually
+------------------------------------------------------
+
+adding a file to tracking
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ echo x > x
+ $ hg add x
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+remove a file from tracking
+(forget)
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg forget x
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+(remove)
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg remove nf1
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+key-file changes on revert (when applicable)
+--------------------------------------------
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg status
+ R nf1
+ ? x
+ $ hg revert --all
+ undeleting nf1
+ $ hg status
+ ? x
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+
+`hg update` does affect the key-file (when needed)
+--------------------------------------------------
+
+update changing the tracked set
+
+(removing)
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg status --rev . --rev '.#generations[-1]'
+ R nf10
+ $ hg up '.#generations[-1]'
+ 0 files updated, 0 files merged, 1 files removed, 0 files unresolved
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+(adding)
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg status --rev . --rev '.#generations[1]'
+ A nf10
+ $ hg up '.#generations[1]'
+ 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck
+ Files .hg/dirstate-tracked-key and ../key-bck differ
+ [1]
+
+update not affecting the tracked set
+
+ $ echo foo >> nf0
+ $ hg commit -m foo
+
+ $ cp .hg/dirstate-tracked-key ../key-bck
+ $ hg status --rev . --rev '.#generations[-1]'
+ M nf0
+ $ hg up '.#generations[-1]'
+ 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+ $ diff --brief .hg/dirstate-tracked-key ../key-bck