git-annex/Logs/Location.hs
Joey Hess 1acdd18ea8
deal better with clock skew situations, using vector clocks
* Deal with clock skew, both forwards and backwards, when logging
  information to the git-annex branch.
* GIT_ANNEX_VECTOR_CLOCK can now be set to a fixed value (eg 1)
  rather than needing to be advanced each time a new change is made.
* Misuse of GIT_ANNEX_VECTOR_CLOCK will no longer confuse git-annex.

When changing a file in the git-annex branch, the vector clock to use is now
determined by first looking at the current time (or GIT_ANNEX_VECTOR_CLOCK
when set), and comparing it to the newest vector clock already in use in
that file. If a newer time stamp was already in use, advance it forward by
a second instead.

When the clock is set to a time in the past, this avoids logging with
an old timestamp, which would risk that log line later being ignored in favor
of "newer" line that is really not newer.

When a log entry has been made with a clock that was set far ahead in the
future, this avoids newer information being logged with an older timestamp
and so being ignored in favor of that future-timestamped information.
Once all clocks get fixed, this will result in the vector clocks being
incremented, until finally enough time has passed that time gets back ahead
of the vector clock value, and then it will return to usual operation.

(This latter situation is not ideal, but it seems the best that can be done.
The issue with it is, since all writers will be incrementing the last
vector clock they saw, there's no way to tell when one writer made a write
significantly later in time than another, so the earlier write might
arbitrarily be picked when merging. This problem is why git-annex uses
timestamps in the first place, rather than pure vector clocks.)

Advancing forward by 1 second is somewhat arbitrary. setDead
advances a timestamp by just 1 picosecond, and the vector clock could
too. But then it would interfere with setDead, which wants to be
overrulled by any change. So it could use 2 picoseconds or something,
but that seems weird. It could just as well advance it forward by a
minute or whatever, but then it would be harder for real time to catch
up with the vector clock when forward clock slew had happened.

A complication is that many log files contain several different peices of
information, and it may be best to only use vector clocks for the same peice
of information. For example, a key's location log file contains
InfoPresent/InfoMissing for each UUID, and it only looks at the vector
clocks for the UUID that is being changed, and not other UUIDs.

Although exactly where the dividing line is can be hard to determine.
Consider metadata logs, where a field "tag" can have multiple values set
at different times. Should it advance forward past the last tag?
Probably. What about when a different field is set, should it look at
the clocks of other fields? Perhaps not, but currently it does, and
this does not seems like it will cause any problems.

Another one I'm not entirely sure about is the export log, which is
keyed by (fromuuid, touuid). So if multiple repos are exporting to the
same remote, different vector clocks can be used for that remote.
It looks like that's probably ok, because it does not try to determine
what order things occurred when there was an export conflict.

Sponsored-by: Jochen Bartl on Patreon
2021-08-04 12:33:46 -04:00

173 lines
4.8 KiB
Haskell

{-# LANGUAGE BangPatterns #-}
{- git-annex location log
-
- git-annex keeps track of which repositories have the contents of annexed
- files.
-
- Repositories record their UUID and the date when they --get or --drop
- a value.
-
- Copyright 2010-2021 Joey Hess <id@joeyh.name>
-
- Licensed under the GNU AGPL version 3 or higher.
-}
module Logs.Location (
LogStatus(..),
logStatus,
logStatusAfter,
logChange,
loggedLocations,
loggedLocationsHistorical,
loggedLocationsRef,
isKnownKey,
checkDead,
setDead,
Unchecked,
finishCheck,
loggedKeys,
loggedKeysFor,
loggedKeysFor',
) where
import Annex.Common
import qualified Annex.Branch
import Logs
import Logs.Presence
import Annex.UUID
import Annex.CatFile
import Annex.VectorClock
import Git.Types (RefDate, Ref)
import qualified Annex
import Data.Time.Clock
{- Log a change in the presence of a key's value in current repository. -}
logStatus :: Key -> LogStatus -> Annex ()
logStatus key s = do
u <- getUUID
logChange key u s
{- 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
)
{- Log a change in the presence of a key's value in a repository. -}
logChange :: Key -> UUID -> LogStatus -> Annex ()
logChange key u@(UUID _) s = do
config <- Annex.getGitConfig
maybeAddLog
(Annex.Branch.RegardingUUID [u])
(locationLogFile config key)
s
(LogInfo (fromUUID u))
logChange _ NoUUID _ = noop
{- Returns a list of repository UUIDs that, according to the log, have
- the value of a key. -}
loggedLocations :: Key -> Annex [UUID]
loggedLocations = getLoggedLocations currentLogInfo
{- Gets the location log on a particular date. -}
loggedLocationsHistorical :: RefDate -> Key -> Annex [UUID]
loggedLocationsHistorical = getLoggedLocations . historicalLogInfo
{- Gets the locations contained in a git ref. -}
loggedLocationsRef :: Ref -> Annex [UUID]
loggedLocationsRef ref = map (toUUID . fromLogInfo) . getLog <$> catObject ref
getLoggedLocations :: (RawFilePath -> Annex [LogInfo]) -> Key -> Annex [UUID]
getLoggedLocations getter key = do
config <- Annex.getGitConfig
map (toUUID . fromLogInfo) <$> getter (locationLogFile config key)
{- 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 <$> readLog (locationLogFile config key)
{- For a key to be dead, all locations that have location status for the key
- must have InfoDead set. -}
checkDead :: Key -> Annex Bool
checkDead key = do
config <- Annex.getGitConfig
ls <- compactLog <$> readLog (locationLogFile config key)
return $! all (\l -> status l == InfoDead) ls
{- Updates the log to say that a key is dead.
-
- Changes all logged lines for the key, in any location, that are
- currently InfoMissing, to be InfoDead.
-
- The vector clock in the log is updated minimally, so that any
- other location log changes are guaranteed to overrule this.
-}
setDead :: Key -> Annex ()
setDead key = do
config <- Annex.getGitConfig
let logfile = locationLogFile config key
ls <- compactLog <$> readLog logfile
mapM_ (go logfile) (filter (\l -> status l == InfoMissing) ls)
where
go logfile l =
let u = toUUID (fromLogInfo (info l))
c = case date l of
VectorClock v -> CandidateVectorClock $
v + realToFrac (picosecondsToDiffTime 1)
Unknown -> CandidateVectorClock 0
in addLog' (Annex.Branch.RegardingUUID [u]) logfile InfoDead
(info l) c
data Unchecked a = Unchecked (Annex (Maybe a))
finishCheck :: Unchecked a -> Annex (Maybe a)
finishCheck (Unchecked a) = a
{- Finds all keys that have location log information.
- (There may be duplicate keys in the list.)
-
- Keys that have been marked as dead are not included.
-}
loggedKeys :: Annex ([Unchecked Key], IO Bool)
loggedKeys = loggedKeys' (not <$$> checkDead)
loggedKeys' :: (Key -> Annex Bool) -> Annex ([Unchecked Key], IO Bool)
loggedKeys' check = do
config <- Annex.getGitConfig
(bfs, cleanup) <- Annex.Branch.files
let l = mapMaybe (defercheck <$$> locationLogFileKey config) bfs
return (l, cleanup)
where
defercheck k = Unchecked $ ifM (check k)
( return (Just k)
, return Nothing
)
{- Finds all keys that have location log information indicating
- they are present in the specified repository.
-
- This does not stream well; use loggedKeysFor' for lazy streaming.
-}
loggedKeysFor :: UUID -> Annex [Key]
loggedKeysFor u = do
(l, cleanup) <- loggedKeysFor' u
l' <- catMaybes <$> mapM finishCheck l
liftIO $ void cleanup
return l'
loggedKeysFor' :: UUID -> Annex ([Unchecked Key], IO Bool)
loggedKeysFor' u = loggedKeys' isthere
where
isthere k = do
us <- loggedLocations k
let !there = u `elem` us
return there