2011-11-26 12:39:47 +00:00
|
|
|
{-# LANGUAGE BangPatterns #-}
|
|
|
|
|
2010-10-09 23:22:40 +00:00
|
|
|
{- git-annex location log
|
|
|
|
-
|
2011-04-02 19:50:51 +00:00
|
|
|
- git-annex keeps track of which repositories have the contents of annexed
|
|
|
|
- files.
|
2010-10-09 23:22:40 +00:00
|
|
|
-
|
2010-10-12 22:06:34 +00:00
|
|
|
- Repositories record their UUID and the date when they --get or --drop
|
2010-10-13 00:04:36 +00:00
|
|
|
- a value.
|
2010-10-10 16:31:14 +00:00
|
|
|
-
|
2018-04-26 18:21:27 +00:00
|
|
|
- Copyright 2010-2018 Joey Hess <id@joeyh.name>
|
2010-10-27 20:53:54 +00:00
|
|
|
-
|
2019-03-13 19:48:14 +00:00
|
|
|
- Licensed under the GNU AGPL version 3 or higher.
|
2010-10-09 23:22:40 +00:00
|
|
|
-}
|
|
|
|
|
2011-10-15 20:21:08 +00:00
|
|
|
module Logs.Location (
|
2010-10-12 22:25:41 +00:00
|
|
|
LogStatus(..),
|
2012-12-12 23:20:38 +00:00
|
|
|
logStatus,
|
2020-12-11 15:33:10 +00:00
|
|
|
logStatusAfter,
|
2010-10-13 19:55:18 +00:00
|
|
|
logChange,
|
2012-01-10 17:11:16 +00:00
|
|
|
loggedLocations,
|
2014-02-06 16:43:56 +00:00
|
|
|
loggedLocationsHistorical,
|
2016-07-17 19:15:08 +00:00
|
|
|
loggedLocationsRef,
|
2016-04-22 17:49:32 +00:00
|
|
|
isKnownKey,
|
2015-06-09 18:08:57 +00:00
|
|
|
checkDead,
|
|
|
|
setDead,
|
2018-04-26 18:21:27 +00:00
|
|
|
Unchecked,
|
|
|
|
finishCheck,
|
2011-07-01 21:23:01 +00:00
|
|
|
loggedKeys,
|
2011-10-29 21:49:37 +00:00
|
|
|
loggedKeysFor,
|
2018-04-26 20:13:05 +00:00
|
|
|
loggedKeysFor',
|
2010-10-11 21:52:46 +00:00
|
|
|
) where
|
2010-10-09 23:22:40 +00:00
|
|
|
|
2016-01-20 20:36:33 +00:00
|
|
|
import Annex.Common
|
2011-10-04 04:40:47 +00:00
|
|
|
import qualified Annex.Branch
|
2013-08-29 22:51:22 +00:00
|
|
|
import Logs
|
2011-10-15 20:21:08 +00:00
|
|
|
import Logs.Presence
|
2012-12-12 23:20:38 +00:00
|
|
|
import Annex.UUID
|
2016-07-17 19:15:08 +00:00
|
|
|
import Annex.CatFile
|
2017-08-14 17:55:38 +00:00
|
|
|
import Annex.VectorClock
|
2016-07-17 19:15:08 +00:00
|
|
|
import Git.Types (RefDate, Ref)
|
2015-01-28 21:17:26 +00:00
|
|
|
import qualified Annex
|
2012-12-12 23:20:38 +00:00
|
|
|
|
2015-06-09 18:52:05 +00:00
|
|
|
import Data.Time.Clock
|
|
|
|
|
2012-12-12 23:20:38 +00:00
|
|
|
{- Log a change in the presence of a key's value in current repository. -}
|
|
|
|
logStatus :: Key -> LogStatus -> Annex ()
|
2013-09-05 01:37:13 +00:00
|
|
|
logStatus key s = do
|
2012-12-12 23:20:38 +00:00
|
|
|
u <- getUUID
|
2013-09-05 01:37:13 +00:00
|
|
|
logChange key u s
|
2010-10-09 23:22:40 +00:00
|
|
|
|
2020-12-11 15:33:10 +00:00
|
|
|
{- Run an action that gets the content of a key, and update the log
|
|
|
|
- when it succeeds. -}
|
|
|
|
logStatusAfter :: Key -> Annex Bool -> Annex Bool
|
|
|
|
logStatusAfter key a = ifM a
|
|
|
|
( do
|
|
|
|
logStatus key InfoPresent
|
|
|
|
return True
|
|
|
|
, return False
|
|
|
|
)
|
|
|
|
|
2011-06-22 20:01:32 +00:00
|
|
|
{- Log a change in the presence of a key's value in a repository. -}
|
2011-11-09 05:15:51 +00:00
|
|
|
logChange :: Key -> UUID -> LogStatus -> Annex ()
|
2015-04-01 21:53:16 +00:00
|
|
|
logChange = logChange' logNow
|
|
|
|
|
2019-01-03 17:21:48 +00:00
|
|
|
logChange' :: (LogStatus -> LogInfo -> Annex LogLine) -> Key -> UUID -> LogStatus -> Annex ()
|
2019-01-01 17:49:19 +00:00
|
|
|
logChange' mklog key u@(UUID _) s = do
|
2015-01-28 21:17:26 +00:00
|
|
|
config <- Annex.getGitConfig
|
start implementing hidden git-annex repositories
This adds a separate journal, which does not currently get committed to
an index, but is planned to be committed to .git/annex/index-private.
Changes that are regarding a UUID that is private will get written to
this journal, and so will not be published into the git-annex branch.
All log writing should have been made to indicate the UUID it's
regarding, though I've not verified this yet.
Currently, no UUIDs are treated as private yet, a way to configure that
is needed.
The implementation is careful to not add any additional IO work when
privateUUIDsKnown is False. It will skip looking at the private journal
at all. So this should be free, or nearly so, unless the feature is
used. When it is used, all branch reads will be about twice as expensive.
It is very lucky -- or very prudent design -- that Annex.Branch.change
and maybeChange are the only ways to change a file on the branch,
and Annex.Branch.set is only internal use. That let Annex.Branch.get
always yield any private information that has been recorded, without
the risk that Annex.Branch.set might be called, with a non-private UUID,
and end up leaking the private information into the git-annex branch.
And, this relies on the way git-annex union merges the git-annex branch.
When reading a file, there can be a public and a private version, and
they are just concacenated together. That will be handled the same as if
there were two diverged git-annex branches that got union merged.
2021-04-20 18:32:41 +00:00
|
|
|
maybeAddLog (Annex.Branch.RegardingUUID [u]) (locationLogFile config key)
|
|
|
|
=<< mklog s (LogInfo (fromUUID u))
|
2015-04-01 21:53:16 +00:00
|
|
|
logChange' _ _ NoUUID _ = noop
|
2010-10-12 22:25:41 +00:00
|
|
|
|
|
|
|
{- Returns a list of repository UUIDs that, according to the log, have
|
2014-02-06 16:43:56 +00:00
|
|
|
- the value of a key. -}
|
2012-01-10 17:11:16 +00:00
|
|
|
loggedLocations :: Key -> Annex [UUID]
|
2015-04-01 21:53:16 +00:00
|
|
|
loggedLocations = getLoggedLocations currentLogInfo
|
2014-02-06 16:43:56 +00:00
|
|
|
|
|
|
|
{- Gets the location log on a particular date. -}
|
|
|
|
loggedLocationsHistorical :: RefDate -> Key -> Annex [UUID]
|
2015-04-01 21:53:16 +00:00
|
|
|
loggedLocationsHistorical = getLoggedLocations . historicalLogInfo
|
2014-02-06 16:43:56 +00:00
|
|
|
|
2016-07-17 19:15:08 +00:00
|
|
|
{- Gets the locations contained in a git ref. -}
|
|
|
|
loggedLocationsRef :: Ref -> Annex [UUID]
|
2019-01-03 17:21:48 +00:00
|
|
|
loggedLocationsRef ref = map (toUUID . fromLogInfo) . getLog <$> catObject ref
|
2016-07-17 19:15:08 +00:00
|
|
|
|
2019-11-26 19:27:22 +00:00
|
|
|
getLoggedLocations :: (RawFilePath -> Annex [LogInfo]) -> Key -> Annex [UUID]
|
2015-01-28 21:17:26 +00:00
|
|
|
getLoggedLocations getter key = do
|
|
|
|
config <- Annex.getGitConfig
|
2019-01-03 17:21:48 +00:00
|
|
|
map (toUUID . fromLogInfo) <$> getter (locationLogFile config key)
|
2015-04-01 21:53:16 +00:00
|
|
|
|
2016-04-22 17:49:32 +00:00
|
|
|
{- Is there a location log for the key? True even for keys with no
|
|
|
|
- remaining locations. -}
|
|
|
|
isKnownKey :: Key -> Annex Bool
|
|
|
|
isKnownKey key = do
|
|
|
|
config <- Annex.getGitConfig
|
|
|
|
not . null <$> readLog (locationLogFile config key)
|
|
|
|
|
2015-06-09 18:08:57 +00:00
|
|
|
{- For a key to be dead, all locations that have location status for the key
|
|
|
|
- must have InfoDead set. -}
|
|
|
|
checkDead :: Key -> Annex Bool
|
|
|
|
checkDead key = do
|
2015-04-01 21:53:16 +00:00
|
|
|
config <- Annex.getGitConfig
|
2015-06-09 18:08:57 +00:00
|
|
|
ls <- compactLog <$> readLog (locationLogFile config key)
|
Keys marked as dead are now skipped by --all.
fsck already special-cased dead keys to make --all not report errors with
them, and it makes sense to also expand that to whereis. I think it makes
sense for dead keys to be skipped by all uses of --all, so mistakes can be
completely forgotten about and not come back to haunt us.
The speed impact of testing if the key is dead is negligible for fsck and
whereis, since they use the location log anyway and it gets cached.
This does slow down a few commands that support --all, in particular
metadata --all runs around 2x as slow. I don't think metadata
--all is often used though. It might slow down copy/move/mirror
--all and get --all.
log --all is not affected (does not use the normal --all machinery).
Dead keys will still be processed by --incomplete, --branch,
--failed, and --key. Although it would be unlikely for a dead key to
ave in incomplete or failed transfer. It seems to make perfect sense for
--branch to process keys on the branch, even if dead.
(fsck's special-casing of dead keys was left in, so if one of these options
causes a dead key to be fscked, there will be a nice message.)
This commit was supported by the NSF-funded DataLad project.
2017-05-09 16:55:21 +00:00
|
|
|
return $! all (\l -> status l == InfoDead) ls
|
2015-06-09 18:08:57 +00:00
|
|
|
|
2015-06-09 18:52:05 +00:00
|
|
|
{- Updates the log to say that a key is dead.
|
|
|
|
-
|
|
|
|
- Changes all logged lines for the key, in any location, that are
|
|
|
|
- currently InfoMissing, to be InfoDead.
|
|
|
|
-}
|
2015-06-09 18:08:57 +00:00
|
|
|
setDead :: Key -> Annex ()
|
2015-06-09 18:52:05 +00:00
|
|
|
setDead key = do
|
|
|
|
config <- Annex.getGitConfig
|
|
|
|
let logfile = locationLogFile config key
|
|
|
|
ls <- compactLog <$> readLog logfile
|
|
|
|
mapM_ (go logfile) (filter (\l -> status l == InfoMissing) ls)
|
|
|
|
where
|
start implementing hidden git-annex repositories
This adds a separate journal, which does not currently get committed to
an index, but is planned to be committed to .git/annex/index-private.
Changes that are regarding a UUID that is private will get written to
this journal, and so will not be published into the git-annex branch.
All log writing should have been made to indicate the UUID it's
regarding, though I've not verified this yet.
Currently, no UUIDs are treated as private yet, a way to configure that
is needed.
The implementation is careful to not add any additional IO work when
privateUUIDsKnown is False. It will skip looking at the private journal
at all. So this should be free, or nearly so, unless the feature is
used. When it is used, all branch reads will be about twice as expensive.
It is very lucky -- or very prudent design -- that Annex.Branch.change
and maybeChange are the only ways to change a file on the branch,
and Annex.Branch.set is only internal use. That let Annex.Branch.get
always yield any private information that has been recorded, without
the risk that Annex.Branch.set might be called, with a non-private UUID,
and end up leaking the private information into the git-annex branch.
And, this relies on the way git-annex union merges the git-annex branch.
When reading a file, there can be a public and a private version, and
they are just concacenated together. That will be handled the same as if
there were two diverged git-annex branches that got union merged.
2021-04-20 18:32:41 +00:00
|
|
|
go logfile l =
|
|
|
|
let u = toUUID (fromLogInfo (info l))
|
|
|
|
in addLog (Annex.Branch.RegardingUUID [u]) logfile (setDead' l)
|
2015-06-09 18:52:05 +00:00
|
|
|
|
|
|
|
{- Note that the timestamp in the log is updated minimally, so that this
|
|
|
|
- can be overruled by other location log changes. -}
|
|
|
|
setDead' :: LogLine -> LogLine
|
|
|
|
setDead' l = l
|
|
|
|
{ status = InfoDead
|
2017-08-14 17:55:38 +00:00
|
|
|
, date = case date l of
|
|
|
|
VectorClock c -> VectorClock $
|
|
|
|
c + realToFrac (picosecondsToDiffTime 1)
|
|
|
|
Unknown -> Unknown
|
2015-06-09 18:52:05 +00:00
|
|
|
}
|
2011-04-02 19:50:51 +00:00
|
|
|
|
2018-04-26 18:21:27 +00:00
|
|
|
data Unchecked a = Unchecked (Annex (Maybe a))
|
|
|
|
|
|
|
|
finishCheck :: Unchecked a -> Annex (Maybe a)
|
|
|
|
finishCheck (Unchecked a) = a
|
|
|
|
|
2011-04-03 00:36:01 +00:00
|
|
|
{- Finds all keys that have location log information.
|
Keys marked as dead are now skipped by --all.
fsck already special-cased dead keys to make --all not report errors with
them, and it makes sense to also expand that to whereis. I think it makes
sense for dead keys to be skipped by all uses of --all, so mistakes can be
completely forgotten about and not come back to haunt us.
The speed impact of testing if the key is dead is negligible for fsck and
whereis, since they use the location log anyway and it gets cached.
This does slow down a few commands that support --all, in particular
metadata --all runs around 2x as slow. I don't think metadata
--all is often used though. It might slow down copy/move/mirror
--all and get --all.
log --all is not affected (does not use the normal --all machinery).
Dead keys will still be processed by --incomplete, --branch,
--failed, and --key. Although it would be unlikely for a dead key to
ave in incomplete or failed transfer. It seems to make perfect sense for
--branch to process keys on the branch, even if dead.
(fsck's special-casing of dead keys was left in, so if one of these options
causes a dead key to be fscked, there will be a nice message.)
This commit was supported by the NSF-funded DataLad project.
2017-05-09 16:55:21 +00:00
|
|
|
- (There may be duplicate keys in the list.)
|
|
|
|
-
|
|
|
|
- Keys that have been marked as dead are not included.
|
|
|
|
-}
|
2020-09-25 14:58:30 +00:00
|
|
|
loggedKeys :: Annex ([Unchecked Key], IO Bool)
|
Keys marked as dead are now skipped by --all.
fsck already special-cased dead keys to make --all not report errors with
them, and it makes sense to also expand that to whereis. I think it makes
sense for dead keys to be skipped by all uses of --all, so mistakes can be
completely forgotten about and not come back to haunt us.
The speed impact of testing if the key is dead is negligible for fsck and
whereis, since they use the location log anyway and it gets cached.
This does slow down a few commands that support --all, in particular
metadata --all runs around 2x as slow. I don't think metadata
--all is often used though. It might slow down copy/move/mirror
--all and get --all.
log --all is not affected (does not use the normal --all machinery).
Dead keys will still be processed by --incomplete, --branch,
--failed, and --key. Although it would be unlikely for a dead key to
ave in incomplete or failed transfer. It seems to make perfect sense for
--branch to process keys on the branch, even if dead.
(fsck's special-casing of dead keys was left in, so if one of these options
causes a dead key to be fscked, there will be a nice message.)
This commit was supported by the NSF-funded DataLad project.
2017-05-09 16:55:21 +00:00
|
|
|
loggedKeys = loggedKeys' (not <$$> checkDead)
|
|
|
|
|
2020-09-25 14:58:30 +00:00
|
|
|
loggedKeys' :: (Key -> Annex Bool) -> Annex ([Unchecked Key], IO Bool)
|
2020-02-14 19:22:48 +00:00
|
|
|
loggedKeys' check = do
|
|
|
|
config <- Annex.getGitConfig
|
2020-09-25 14:58:30 +00:00
|
|
|
(bfs, cleanup) <- Annex.Branch.files
|
|
|
|
let l = mapMaybe (defercheck <$$> locationLogFileKey config) bfs
|
|
|
|
return (l, cleanup)
|
2018-04-26 18:21:27 +00:00
|
|
|
where
|
|
|
|
defercheck k = Unchecked $ ifM (check k)
|
|
|
|
( return (Just k)
|
|
|
|
, return Nothing
|
|
|
|
)
|
2011-07-01 21:23:01 +00:00
|
|
|
|
2011-10-29 21:49:37 +00:00
|
|
|
{- Finds all keys that have location log information indicating
|
2018-04-26 20:13:05 +00:00
|
|
|
- they are present in the specified repository.
|
|
|
|
-
|
|
|
|
- This does not stream well; use loggedKeysFor' for lazy streaming.
|
2018-04-26 18:21:27 +00:00
|
|
|
-}
|
2011-10-29 21:49:37 +00:00
|
|
|
loggedKeysFor :: UUID -> Annex [Key]
|
2020-09-25 14:58:30 +00:00
|
|
|
loggedKeysFor u = do
|
|
|
|
(l, cleanup) <- loggedKeysFor' u
|
|
|
|
l' <- catMaybes <$> mapM finishCheck l
|
|
|
|
liftIO $ void cleanup
|
|
|
|
return l'
|
2018-04-26 20:13:05 +00:00
|
|
|
|
2020-09-25 14:58:30 +00:00
|
|
|
loggedKeysFor' :: UUID -> Annex ([Unchecked Key], IO Bool)
|
2018-04-26 20:13:05 +00:00
|
|
|
loggedKeysFor' u = loggedKeys' isthere
|
2012-11-11 04:51:07 +00:00
|
|
|
where
|
|
|
|
isthere k = do
|
|
|
|
us <- loggedLocations k
|
|
|
|
let !there = u `elem` us
|
|
|
|
return there
|