2014-05-15 18:44:00 +00:00
|
|
|
{- Using ddar as a remote. Based on bup and rsync remotes.
|
|
|
|
-
|
2020-06-04 19:36:34 +00:00
|
|
|
- Copyright 2011-2020 Joey Hess <id@joeyh.name>
|
2014-05-15 18:44:00 +00:00
|
|
|
- Copyright 2014 Robie Basak <robie@justgohome.co.uk>
|
|
|
|
-
|
2019-07-28 18:27:33 +00:00
|
|
|
- Licensed under the GNU GPL version 3 or higher.
|
2014-05-15 18:44:00 +00:00
|
|
|
-}
|
|
|
|
|
2020-06-04 19:36:34 +00:00
|
|
|
{-# LANGUAGE BangPatterns #-}
|
incremental verify for byteRetriever special remotes
Several special remotes verify content while it is being retrieved,
avoiding a separate checksum pass. They are: S3, bup, ddar, and
gcrypt (with a local repository).
Not done when using chunking, yet.
Complicated by Retriever needing to change to be polymorphic. Which in turn
meant RankNTypes is needed, and also needed some code changes. The
change in Remote.External does not change behavior at all but avoids
the type checking failing because of a "rigid, skolem type" which
"would escape its scope". So I refactored slightly to make the type
checker's job easier there.
Unfortunately, directory uses fileRetriever (except when chunked),
so it is not amoung the improved ones. Fixing that would need a way for
FileRetriever to return a Verification. But, since the file retrieved
may be encrypted or chunked, it would be extra work to always
incrementally checksum the file while retrieving it. Hm.
Some other special remotes use fileRetriever, and so don't get incremental
verification, but could be converted to byteRetriever later. One is
GitLFS, which uses downloadConduit, which writes to the file, so could
verify as it goes. Other special remotes like web could too, but don't
use Remote.Helper.Special and so will need to be addressed separately.
Sponsored-by: Dartmouth College's DANDI project
2021-08-11 17:43:30 +00:00
|
|
|
{-# LANGUAGE RankNTypes #-}
|
2020-06-04 19:36:34 +00:00
|
|
|
|
2014-05-15 18:44:00 +00:00
|
|
|
module Remote.Ddar (remote) where
|
|
|
|
|
|
|
|
import qualified Data.Map as M
|
2014-08-03 05:12:24 +00:00
|
|
|
import qualified Data.ByteString.Lazy as L
|
2014-05-15 18:44:00 +00:00
|
|
|
import System.IO.Error
|
2023-03-01 19:55:58 +00:00
|
|
|
import System.PosixCompat.Files (isDirectory)
|
2014-05-15 18:44:00 +00:00
|
|
|
|
2016-01-20 20:36:33 +00:00
|
|
|
import Annex.Common
|
2014-05-15 18:44:00 +00:00
|
|
|
import Types.Remote
|
|
|
|
import Types.Creds
|
|
|
|
import qualified Git
|
|
|
|
import Config
|
|
|
|
import Config.Cost
|
2020-01-14 19:41:34 +00:00
|
|
|
import Annex.SpecialRemote.Config
|
2014-05-15 18:44:00 +00:00
|
|
|
import Remote.Helper.Special
|
2019-02-20 19:55:01 +00:00
|
|
|
import Remote.Helper.ExportImport
|
2023-08-16 19:48:09 +00:00
|
|
|
import Remote.Helper.Path
|
2014-05-15 18:44:00 +00:00
|
|
|
import Annex.Ssh
|
|
|
|
import Annex.UUID
|
2017-08-18 02:11:31 +00:00
|
|
|
import Utility.SshHost
|
2020-01-10 18:10:20 +00:00
|
|
|
import Types.ProposedAccepted
|
2023-03-01 19:55:58 +00:00
|
|
|
import qualified Utility.RawFilePath as R
|
2014-05-15 18:44:00 +00:00
|
|
|
|
2015-02-12 19:44:10 +00:00
|
|
|
data DdarRepo = DdarRepo
|
|
|
|
{ ddarRepoConfig :: RemoteGitConfig
|
|
|
|
, ddarRepoLocation :: String
|
|
|
|
}
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
remote :: RemoteType
|
2020-01-14 19:41:34 +00:00
|
|
|
remote = specialRemoteType $ RemoteType
|
2017-09-07 17:45:31 +00:00
|
|
|
{ typename = "ddar"
|
|
|
|
, enumerate = const (findSpecialRemotes "ddarrepo")
|
|
|
|
, generate = gen
|
2020-01-14 19:41:34 +00:00
|
|
|
, configParser = mkRemoteConfigParser
|
2020-01-20 19:20:04 +00:00
|
|
|
[ optionalStringParser ddarrepoField
|
|
|
|
(FieldDesc "(required) location of ddar archive to use")
|
|
|
|
]
|
2017-09-07 17:45:31 +00:00
|
|
|
, setup = ddarSetup
|
|
|
|
, exportSupported = exportUnsupported
|
2019-02-20 19:55:01 +00:00
|
|
|
, importSupported = importUnsupported
|
add thirdPartyPopulated interface
This is to support, eg a borg repo as a special remote, which is
populated not by running git-annex commands, but by using borg. Then
git-annex sync lists the content of the remote, learns which files are
annex objects, and treats those as present in the remote.
So, most of the import machinery is reused, to a new purpose. While
normally importtree maintains a remote tracking branch, this does not,
because the files stored in the remote are annex object files, not
user-visible filenames. But, internally, a git tree is still generated,
of the files on the remote that are annex objects. This tree is used
by retrieveExportWithContentIdentifier, etc. As with other import/export
remotes, that the tree is recorded in the export log, and gets grafted
into the git-annex branch.
importKey changed to be able to return Nothing, to indicate when an
ImportLocation is not an annex object and so should be skipped from
being included in the tree.
It did not seem to make sense to have git-annex import do this, since
from the user's perspective, it's not like other imports. So only
git-annex sync does it.
Note that, git-annex sync does not yet download objects from such
remotes that are preferred content. importKeys is run with
content downloading disabled, to avoid getting the content of all
objects. Perhaps what's needed is for seekSyncContent to be run with these
remotes, but I don't know if it will just work (in particular, it needs
to avoid trying to transfer objects to them), so I skipped that for now.
(Untested and unused as of yet.)
This commit was sponsored by Jochen Bartl on Patreon.
2020-12-18 18:52:57 +00:00
|
|
|
, thirdPartyPopulated = False
|
2017-09-07 17:45:31 +00:00
|
|
|
}
|
2014-05-15 18:44:00 +00:00
|
|
|
|
2020-01-14 19:41:34 +00:00
|
|
|
ddarrepoField :: RemoteConfigField
|
|
|
|
ddarrepoField = Accepted "ddarrepo"
|
|
|
|
|
fix encryption of content to gcrypt and git-lfs
Fix serious regression in gcrypt and encrypted git-lfs remotes.
Since version 7.20200202.7, git-annex incorrectly stored content
on those remotes without encrypting it.
Problem was, Remote.Git enumerates all git remotes, including git-lfs
and gcrypt. It then dispatches to those. So, Remote.List used the
RemoteConfigParser from Remote.Git, instead of from git-lfs or gcrypt,
and that parser does not know about encryption fields, so did not
include them in the ParsedRemoteConfig. (Also didn't include other
fields specific to those remotes, perhaps chunking etc also didn't
get through.)
To fix, had to move RemoteConfig parsing down into the generate methods
of each remote, rather than doing it in Remote.List.
And a consequence of that was that ParsedRemoteConfig had to change to
include the RemoteConfig that got parsed, so that testremote can
generate a new remote based on an existing remote.
(I would have rather fixed this just inside Remote.Git, but that was not
practical, at least not w/o re-doing work that Remote.List already did.
Big ugly mostly mechanical patch seemed preferable to making git-annex
slower.)
2020-02-26 21:20:56 +00:00
|
|
|
gen :: Git.Repo -> UUID -> RemoteConfig -> RemoteGitConfig -> RemoteStateHandle -> Annex (Maybe Remote)
|
|
|
|
gen r u rc gc rs = do
|
|
|
|
c <- parsedRemoteConfig remote rc
|
2023-01-12 17:42:28 +00:00
|
|
|
cst <- remoteCost gc c $
|
2014-05-15 18:44:00 +00:00
|
|
|
if ddarLocal ddarrepo
|
|
|
|
then nearlyCheapRemoteCost
|
|
|
|
else expensiveRemoteCost
|
fix encryption of content to gcrypt and git-lfs
Fix serious regression in gcrypt and encrypted git-lfs remotes.
Since version 7.20200202.7, git-annex incorrectly stored content
on those remotes without encrypting it.
Problem was, Remote.Git enumerates all git remotes, including git-lfs
and gcrypt. It then dispatches to those. So, Remote.List used the
RemoteConfigParser from Remote.Git, instead of from git-lfs or gcrypt,
and that parser does not know about encryption fields, so did not
include them in the ParsedRemoteConfig. (Also didn't include other
fields specific to those remotes, perhaps chunking etc also didn't
get through.)
To fix, had to move RemoteConfig parsing down into the generate methods
of each remote, rather than doing it in Remote.List.
And a consequence of that was that ParsedRemoteConfig had to change to
include the RemoteConfig that got parsed, so that testremote can
generate a new remote based on an existing remote.
(I would have rather fixed this just inside Remote.Git, but that was not
practical, at least not w/o re-doing work that Remote.List already did.
Big ugly mostly mechanical patch seemed preferable to making git-annex
slower.)
2020-02-26 21:20:56 +00:00
|
|
|
let specialcfg = (specialRemoteCfg c)
|
|
|
|
-- chunking would not improve ddar
|
|
|
|
{ chunkConfig = NoChunks
|
|
|
|
}
|
2014-08-03 19:35:23 +00:00
|
|
|
return $ Just $ specialRemote' specialcfg c
|
2020-05-13 15:50:31 +00:00
|
|
|
(store ddarrepo)
|
|
|
|
(retrieve ddarrepo)
|
|
|
|
(remove ddarrepo)
|
|
|
|
(checkKey ddarrepo)
|
fix encryption of content to gcrypt and git-lfs
Fix serious regression in gcrypt and encrypted git-lfs remotes.
Since version 7.20200202.7, git-annex incorrectly stored content
on those remotes without encrypting it.
Problem was, Remote.Git enumerates all git remotes, including git-lfs
and gcrypt. It then dispatches to those. So, Remote.List used the
RemoteConfigParser from Remote.Git, instead of from git-lfs or gcrypt,
and that parser does not know about encryption fields, so did not
include them in the ParsedRemoteConfig. (Also didn't include other
fields specific to those remotes, perhaps chunking etc also didn't
get through.)
To fix, had to move RemoteConfig parsing down into the generate methods
of each remote, rather than doing it in Remote.List.
And a consequence of that was that ParsedRemoteConfig had to change to
include the RemoteConfig that got parsed, so that testremote can
generate a new remote based on an existing remote.
(I would have rather fixed this just inside Remote.Git, but that was not
practical, at least not w/o re-doing work that Remote.List already did.
Big ugly mostly mechanical patch seemed preferable to making git-annex
slower.)
2020-02-26 21:20:56 +00:00
|
|
|
(this c cst)
|
2014-08-02 22:58:38 +00:00
|
|
|
where
|
fix encryption of content to gcrypt and git-lfs
Fix serious regression in gcrypt and encrypted git-lfs remotes.
Since version 7.20200202.7, git-annex incorrectly stored content
on those remotes without encrypting it.
Problem was, Remote.Git enumerates all git remotes, including git-lfs
and gcrypt. It then dispatches to those. So, Remote.List used the
RemoteConfigParser from Remote.Git, instead of from git-lfs or gcrypt,
and that parser does not know about encryption fields, so did not
include them in the ParsedRemoteConfig. (Also didn't include other
fields specific to those remotes, perhaps chunking etc also didn't
get through.)
To fix, had to move RemoteConfig parsing down into the generate methods
of each remote, rather than doing it in Remote.List.
And a consequence of that was that ParsedRemoteConfig had to change to
include the RemoteConfig that got parsed, so that testremote can
generate a new remote based on an existing remote.
(I would have rather fixed this just inside Remote.Git, but that was not
practical, at least not w/o re-doing work that Remote.List already did.
Big ugly mostly mechanical patch seemed preferable to making git-annex
slower.)
2020-02-26 21:20:56 +00:00
|
|
|
this c cst = Remote
|
2014-05-15 18:44:00 +00:00
|
|
|
{ uuid = u
|
|
|
|
, cost = cst
|
|
|
|
, name = Git.repoDescribe r
|
2014-08-02 22:58:38 +00:00
|
|
|
, storeKey = storeKeyDummy
|
2020-05-13 21:05:56 +00:00
|
|
|
, retrieveKeyFile = retrieveKeyFileDummy
|
|
|
|
, retrieveKeyFileCheap = Nothing
|
2018-06-21 20:38:47 +00:00
|
|
|
-- ddar communicates over ssh, not subject to http redirect
|
|
|
|
-- type attacks
|
|
|
|
, retrievalSecurityPolicy = RetrievalAllKeysSecure
|
run Preparer to get Remover and CheckPresent actions
This will allow special remotes to eg, open a http connection and reuse it,
while checking if chunks are present, or removing chunks.
S3 and WebDAV both need this to support chunks with reasonable speed.
Note that a special remote might want to cache a http connection across
multiple requests. A simple case of this is that CheckPresent is typically
called before Store or Remove. A remote using this interface can certianly
use a Preparer that eg, uses a MVar to cache a http connection.
However, it's up to the remote to then deal with things like stale or
stalled http connections when eg, doing a series of downloads from a remote
and other places. There could be long delays between calls to a remote,
which could lead to eg, http connection stalls; the machine might even
move to a new network, etc.
It might be nice to improve this interface later to allow
the simple case without needing to handle the full complex case.
One way to do it would be to have a `Transaction SpecialRemote cache`,
where SpecialRemote contains methods for Storer, Retriever, Remover, and
CheckPresent, that all expect to be passed a `cache`.
2014-08-06 18:28:36 +00:00
|
|
|
, removeKey = removeKeyDummy
|
2015-10-08 19:01:38 +00:00
|
|
|
, lockContent = Nothing
|
run Preparer to get Remover and CheckPresent actions
This will allow special remotes to eg, open a http connection and reuse it,
while checking if chunks are present, or removing chunks.
S3 and WebDAV both need this to support chunks with reasonable speed.
Note that a special remote might want to cache a http connection across
multiple requests. A simple case of this is that CheckPresent is typically
called before Store or Remove. A remote using this interface can certianly
use a Preparer that eg, uses a MVar to cache a http connection.
However, it's up to the remote to then deal with things like stale or
stalled http connections when eg, doing a series of downloads from a remote
and other places. There could be long delays between calls to a remote,
which could lead to eg, http connection stalls; the machine might even
move to a new network, etc.
It might be nice to improve this interface later to allow
the simple case without needing to handle the full complex case.
One way to do it would be to have a `Transaction SpecialRemote cache`,
where SpecialRemote contains methods for Storer, Retriever, Remover, and
CheckPresent, that all expect to be passed a `cache`.
2014-08-06 18:28:36 +00:00
|
|
|
, checkPresent = checkPresentDummy
|
2014-08-06 17:45:19 +00:00
|
|
|
, checkPresentCheap = ddarLocal ddarrepo
|
2017-09-01 17:02:07 +00:00
|
|
|
, exportActions = exportUnsupported
|
2019-02-20 19:55:01 +00:00
|
|
|
, importActions = importUnsupported
|
2014-05-15 18:44:00 +00:00
|
|
|
, whereisKey = Nothing
|
|
|
|
, remoteFsck = Nothing
|
|
|
|
, repairRepo = Nothing
|
|
|
|
, config = c
|
2018-06-04 18:31:55 +00:00
|
|
|
, getRepo = return r
|
2014-05-15 18:44:00 +00:00
|
|
|
, gitconfig = gc
|
2015-02-12 19:44:10 +00:00
|
|
|
, localpath = if ddarLocal ddarrepo && not (null $ ddarRepoLocation ddarrepo)
|
|
|
|
then Just $ ddarRepoLocation ddarrepo
|
2014-05-15 18:44:00 +00:00
|
|
|
else Nothing
|
|
|
|
, remotetype = remote
|
2023-08-16 19:48:09 +00:00
|
|
|
, availability = checkPathAvailability
|
|
|
|
(ddarLocal ddarrepo && not (null $ ddarRepoLocation ddarrepo))
|
|
|
|
(ddarRepoLocation ddarrepo)
|
2014-05-15 18:44:00 +00:00
|
|
|
, readonly = False
|
2018-08-30 15:12:18 +00:00
|
|
|
, appendonly = False
|
2020-12-28 19:08:53 +00:00
|
|
|
, untrustworthy = False
|
2014-08-10 18:52:58 +00:00
|
|
|
, mkUnavailable = return Nothing
|
2015-02-12 19:44:10 +00:00
|
|
|
, getInfo = return [("repo", ddarRepoLocation ddarrepo)]
|
2014-12-08 17:40:15 +00:00
|
|
|
, claimUrl = Nothing
|
2014-12-11 19:32:42 +00:00
|
|
|
, checkUrl = Nothing
|
add RemoteStateHandle
This solves the problem of sameas remotes trampling over per-remote
state. Used for:
* per-remote state, of course
* per-remote metadata, also of course
* per-remote content identifiers, because two remote implementations
could in theory generate the same content identifier for two different
peices of content
While chunk logs are per-remote data, they don't use this, because the
number and size of chunks stored is a common property across sameas
remotes.
External special remote had a complication, where it was theoretically
possible for a remote to send SETSTATE or GETSTATE during INITREMOTE or
EXPORTSUPPORTED. Since the uuid of the remote is typically generate in
Remote.setup, it would only be possible to pass a Maybe
RemoteStateHandle into it, and it would otherwise have to construct its
own. Rather than go that route, I decided to send an ERROR in this case.
It seems unlikely that any existing external special remote will be
affected. They would have to make up a git-annex key, and set state for
some reason during INITREMOTE. I can imagine such a hack, but it doesn't
seem worth complicating the code in such an ugly way to support it.
Unfortunately, both TestRemote and Annex.Import needed the Remote
to have a new field added that holds its RemoteStateHandle.
2019-10-14 16:33:27 +00:00
|
|
|
, remoteStateHandle = rs
|
2014-05-15 18:44:00 +00:00
|
|
|
}
|
2016-11-16 01:29:54 +00:00
|
|
|
ddarrepo = maybe (giveup "missing ddarrepo") (DdarRepo gc) (remoteAnnexDdarRepo gc)
|
2014-05-15 18:44:00 +00:00
|
|
|
|
2017-02-07 18:35:58 +00:00
|
|
|
ddarSetup :: SetupStage -> Maybe UUID -> Maybe CredPair -> RemoteConfig -> RemoteGitConfig -> Annex (RemoteConfig, UUID)
|
|
|
|
ddarSetup _ mu _ c gc = do
|
2014-05-15 18:44:00 +00:00
|
|
|
u <- maybe (liftIO genUUID) return mu
|
|
|
|
|
|
|
|
-- verify configuration is sane
|
2020-01-10 18:10:20 +00:00
|
|
|
let ddarrepo = maybe (giveup "Specify ddarrepo=") fromProposedAccepted $
|
2020-01-14 19:41:34 +00:00
|
|
|
M.lookup ddarrepoField c
|
2016-05-23 21:27:15 +00:00
|
|
|
(c', _encsetup) <- encryptionSetup c gc
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
-- The ddarrepo is stored in git config, as well as this repo's
|
2023-03-14 02:39:16 +00:00
|
|
|
-- persistent state, so it can vary between hosts.
|
2018-03-27 16:41:57 +00:00
|
|
|
gitConfigSpecialRemote u c' [("ddarrepo", ddarrepo)]
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
return (c', u)
|
|
|
|
|
2014-08-02 22:58:38 +00:00
|
|
|
store :: DdarRepo -> Storer
|
|
|
|
store ddarrepo = fileStorer $ \k src _p -> do
|
2014-05-15 18:44:00 +00:00
|
|
|
let params =
|
|
|
|
[ Param "c"
|
|
|
|
, Param "-N"
|
2019-01-14 17:03:35 +00:00
|
|
|
, Param $ serializeKey k
|
2015-02-12 19:44:10 +00:00
|
|
|
, Param $ ddarRepoLocation ddarrepo
|
2014-05-15 18:44:00 +00:00
|
|
|
, File src
|
|
|
|
]
|
2020-05-13 18:03:00 +00:00
|
|
|
unlessM (liftIO $ boolSystem "ddar" params) $
|
|
|
|
giveup "ddar failed"
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
{- Convert remote DdarRepo to host and path on remote end -}
|
2017-08-18 02:11:31 +00:00
|
|
|
splitRemoteDdarRepo :: DdarRepo -> (SshHost, String)
|
2023-04-10 17:38:14 +00:00
|
|
|
splitRemoteDdarRepo ddarrepo = (either giveup id $ mkSshHost host, ddarrepo')
|
2014-05-15 18:44:00 +00:00
|
|
|
where
|
2015-02-12 19:44:10 +00:00
|
|
|
(host, remainder) = span (/= ':') (ddarRepoLocation ddarrepo)
|
2014-05-15 18:44:00 +00:00
|
|
|
ddarrepo' = drop 1 remainder
|
|
|
|
|
|
|
|
{- Return the command and parameters to use for a ddar call that may need to be
|
|
|
|
- made on a remote repository. This will call ssh if needed. -}
|
2017-02-15 19:08:46 +00:00
|
|
|
ddarRemoteCall :: ConsumeStdin -> DdarRepo -> Char -> [CommandParam] -> Annex (String, [CommandParam])
|
|
|
|
ddarRemoteCall cs ddarrepo cmd params
|
2014-05-15 18:44:00 +00:00
|
|
|
| ddarLocal ddarrepo = return ("ddar", localParams)
|
2017-03-17 20:02:47 +00:00
|
|
|
| otherwise = sshCommand cs (host, Nothing) (ddarRepoConfig ddarrepo) remoteCommand
|
2014-05-15 18:44:00 +00:00
|
|
|
where
|
|
|
|
(host, ddarrepo') = splitRemoteDdarRepo ddarrepo
|
2015-02-12 19:44:10 +00:00
|
|
|
localParams = Param [cmd] : Param (ddarRepoLocation ddarrepo) : params
|
2017-03-17 20:02:47 +00:00
|
|
|
remoteCommand = unwords $ map shellEscape $ toCommand $
|
|
|
|
[Param "ddar", Param [cmd], Param ddarrepo'] ++ params
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
{- Specialized ddarRemoteCall that includes extraction command and flags -}
|
2017-02-15 19:08:46 +00:00
|
|
|
ddarExtractRemoteCall :: ConsumeStdin -> DdarRepo -> Key -> Annex (String, [CommandParam])
|
|
|
|
ddarExtractRemoteCall cs ddarrepo k =
|
2019-01-14 17:03:35 +00:00
|
|
|
ddarRemoteCall cs ddarrepo 'x' [Param "--force-stdout", Param $ serializeKey k]
|
2014-05-15 18:44:00 +00:00
|
|
|
|
2014-08-02 22:58:38 +00:00
|
|
|
retrieve :: DdarRepo -> Retriever
|
2014-08-03 05:12:24 +00:00
|
|
|
retrieve ddarrepo = byteRetriever $ \k sink -> do
|
2017-02-15 19:08:46 +00:00
|
|
|
(cmd, params) <- ddarExtractRemoteCall NoConsumeStdin ddarrepo k
|
2020-06-04 16:13:26 +00:00
|
|
|
let p = (proc cmd $ toCommand params)
|
|
|
|
{ std_out = CreatePipe }
|
|
|
|
bracketIO (createProcess p) cleanupProcess (go sink p)
|
|
|
|
where
|
|
|
|
go sink p (_, Just h, _, pid) = do
|
incremental verify for byteRetriever special remotes
Several special remotes verify content while it is being retrieved,
avoiding a separate checksum pass. They are: S3, bup, ddar, and
gcrypt (with a local repository).
Not done when using chunking, yet.
Complicated by Retriever needing to change to be polymorphic. Which in turn
meant RankNTypes is needed, and also needed some code changes. The
change in Remote.External does not change behavior at all but avoids
the type checking failing because of a "rigid, skolem type" which
"would escape its scope". So I refactored slightly to make the type
checker's job easier there.
Unfortunately, directory uses fileRetriever (except when chunked),
so it is not amoung the improved ones. Fixing that would need a way for
FileRetriever to return a Verification. But, since the file retrieved
may be encrypted or chunked, it would be extra work to always
incrementally checksum the file while retrieving it. Hm.
Some other special remotes use fileRetriever, and so don't get incremental
verification, but could be converted to byteRetriever later. One is
GitLFS, which uses downloadConduit, which writes to the file, so could
verify as it goes. Other special remotes like web could too, but don't
use Remote.Helper.Special and so will need to be addressed separately.
Sponsored-by: Dartmouth College's DANDI project
2021-08-11 17:43:30 +00:00
|
|
|
r <- sink =<< liftIO (L.hGetContents h)
|
2020-06-04 16:13:26 +00:00
|
|
|
liftIO $ do
|
|
|
|
hClose h
|
|
|
|
forceSuccessProcess p pid
|
incremental verify for byteRetriever special remotes
Several special remotes verify content while it is being retrieved,
avoiding a separate checksum pass. They are: S3, bup, ddar, and
gcrypt (with a local repository).
Not done when using chunking, yet.
Complicated by Retriever needing to change to be polymorphic. Which in turn
meant RankNTypes is needed, and also needed some code changes. The
change in Remote.External does not change behavior at all but avoids
the type checking failing because of a "rigid, skolem type" which
"would escape its scope". So I refactored slightly to make the type
checker's job easier there.
Unfortunately, directory uses fileRetriever (except when chunked),
so it is not amoung the improved ones. Fixing that would need a way for
FileRetriever to return a Verification. But, since the file retrieved
may be encrypted or chunked, it would be extra work to always
incrementally checksum the file while retrieving it. Hm.
Some other special remotes use fileRetriever, and so don't get incremental
verification, but could be converted to byteRetriever later. One is
GitLFS, which uses downloadConduit, which writes to the file, so could
verify as it goes. Other special remotes like web could too, but don't
use Remote.Helper.Special and so will need to be addressed separately.
Sponsored-by: Dartmouth College's DANDI project
2021-08-11 17:43:30 +00:00
|
|
|
return r
|
2020-06-04 16:13:26 +00:00
|
|
|
go _ _ _ = error "internal"
|
2014-05-15 18:44:00 +00:00
|
|
|
|
run Preparer to get Remover and CheckPresent actions
This will allow special remotes to eg, open a http connection and reuse it,
while checking if chunks are present, or removing chunks.
S3 and WebDAV both need this to support chunks with reasonable speed.
Note that a special remote might want to cache a http connection across
multiple requests. A simple case of this is that CheckPresent is typically
called before Store or Remove. A remote using this interface can certianly
use a Preparer that eg, uses a MVar to cache a http connection.
However, it's up to the remote to then deal with things like stale or
stalled http connections when eg, doing a series of downloads from a remote
and other places. There could be long delays between calls to a remote,
which could lead to eg, http connection stalls; the machine might even
move to a new network, etc.
It might be nice to improve this interface later to allow
the simple case without needing to handle the full complex case.
One way to do it would be to have a `Transaction SpecialRemote cache`,
where SpecialRemote contains methods for Storer, Retriever, Remover, and
CheckPresent, that all expect to be passed a `cache`.
2014-08-06 18:28:36 +00:00
|
|
|
remove :: DdarRepo -> Remover
|
toward SafeDropProof expiry checking
Added Maybe POSIXTime to SafeDropProof, which gets set when the proof is
based on a LockedCopy. If there are several LockedCopies, it uses the
closest expiry time. That is not optimal, it may be that the proof
expires based on one LockedCopy but another one has not expired. But
that seems unlikely to really happen, and anyway the user can just
re-run a drop if it fails due to expiry.
Pass the SafeDropProof to removeKey, which is responsible for checking
it for expiry in situations where that could be a problem. Which really
only means in Remote.Git.
Made Remote.Git check expiry when dropping from a local remote.
Checking expiry when dropping from a P2P remote is not yet implemented.
P2P.Protocol.remove has SafeDropProof plumbed through to it for that
purpose.
Fixing the remaining 2 build warnings should complete this work.
Note that the use of a POSIXTime here means that if the clock gets set
forward while git-annex is in the middle of a drop, it may say that
dropping took too long. That seems ok. Less ok is that if the clock gets
turned back a sufficient amount (eg 5 minutes), proof expiry won't be
noticed. It might be better to use the Monotonic clock, but that doesn't
advance when a laptop is suspended, and while there is the linux
Boottime clock, that is not available on other systems. Perhaps a
combination of POSIXTime and the Monotonic clock could detect laptop
suspension and also detect clock being turned back?
There is a potential future flag day where
p2pDefaultLockContentRetentionDuration is not assumed, but is probed
using the P2P protocol, and peers that don't support it can no longer
produce a LockedCopy. Until that happens, when git-annex is
communicating with older peers there is a risk of data loss when
a ssh connection closes during LOCKCONTENT.
2024-07-04 16:23:46 +00:00
|
|
|
remove ddarrepo _proof key = do
|
2017-02-15 19:08:46 +00:00
|
|
|
(cmd, params) <- ddarRemoteCall NoConsumeStdin ddarrepo 'd'
|
2019-01-14 17:03:35 +00:00
|
|
|
[Param $ serializeKey key]
|
2020-05-14 18:08:09 +00:00
|
|
|
unlessM (liftIO $ boolSystem cmd params) $
|
|
|
|
giveup "ddar failed to remove"
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
ddarDirectoryExists :: DdarRepo -> Annex (Either String Bool)
|
|
|
|
ddarDirectoryExists ddarrepo
|
|
|
|
| ddarLocal ddarrepo = do
|
2022-09-05 17:44:03 +00:00
|
|
|
maybeStatus <- liftIO $ tryJust (guard . isDoesNotExistError) $
|
2023-03-01 19:55:58 +00:00
|
|
|
R.getSymbolicLinkStatus $ toRawFilePath $ ddarRepoLocation ddarrepo
|
2014-05-15 18:44:00 +00:00
|
|
|
return $ case maybeStatus of
|
|
|
|
Left _ -> Right False
|
|
|
|
Right status -> Right $ isDirectory status
|
|
|
|
| otherwise = do
|
2017-03-17 20:02:47 +00:00
|
|
|
let remotecmd = unwords $ map shellEscape
|
|
|
|
[ "test", "-d", ddarrepo' ]
|
|
|
|
(sshcmd, sshps) <- sshCommand NoConsumeStdin (host, Nothing)
|
|
|
|
(ddarRepoConfig ddarrepo) remotecmd
|
|
|
|
exitCode <- liftIO $ safeSystem sshcmd sshps
|
2014-05-15 18:44:00 +00:00
|
|
|
case exitCode of
|
|
|
|
ExitSuccess -> return $ Right True
|
|
|
|
ExitFailure 1 -> return $ Right False
|
2017-03-17 20:02:47 +00:00
|
|
|
ExitFailure code -> return $ Left $ "ssh " ++
|
|
|
|
show (unwords $ toCommand sshps) ++
|
2014-05-15 18:44:00 +00:00
|
|
|
" failed with status " ++ show code
|
|
|
|
where
|
|
|
|
(host, ddarrepo') = splitRemoteDdarRepo ddarrepo
|
|
|
|
|
|
|
|
{- Use "ddar t" to determine if a given key is present in a ddar archive -}
|
|
|
|
inDdarManifest :: DdarRepo -> Key -> Annex (Either String Bool)
|
|
|
|
inDdarManifest ddarrepo k = do
|
2017-02-15 19:08:46 +00:00
|
|
|
(cmd, params) <- ddarRemoteCall NoConsumeStdin ddarrepo 't' []
|
2020-06-04 19:36:34 +00:00
|
|
|
let p = (proc cmd $ toCommand params)
|
|
|
|
{ std_out = CreatePipe }
|
|
|
|
liftIO $ catchMsgIO $ withCreateProcess p (go p)
|
2014-05-15 18:44:00 +00:00
|
|
|
where
|
2019-01-14 17:03:35 +00:00
|
|
|
k' = serializeKey k
|
2020-06-04 19:36:34 +00:00
|
|
|
|
|
|
|
go p _ (Just hout) _ pid = do
|
|
|
|
contents <- hGetContents hout
|
|
|
|
let !r = elem k' (lines contents)
|
|
|
|
forceSuccessProcess p pid
|
|
|
|
return r
|
|
|
|
go _ _ _ _ _ = error "internal"
|
2014-05-15 18:44:00 +00:00
|
|
|
|
run Preparer to get Remover and CheckPresent actions
This will allow special remotes to eg, open a http connection and reuse it,
while checking if chunks are present, or removing chunks.
S3 and WebDAV both need this to support chunks with reasonable speed.
Note that a special remote might want to cache a http connection across
multiple requests. A simple case of this is that CheckPresent is typically
called before Store or Remove. A remote using this interface can certianly
use a Preparer that eg, uses a MVar to cache a http connection.
However, it's up to the remote to then deal with things like stale or
stalled http connections when eg, doing a series of downloads from a remote
and other places. There could be long delays between calls to a remote,
which could lead to eg, http connection stalls; the machine might even
move to a new network, etc.
It might be nice to improve this interface later to allow
the simple case without needing to handle the full complex case.
One way to do it would be to have a `Transaction SpecialRemote cache`,
where SpecialRemote contains methods for Storer, Retriever, Remover, and
CheckPresent, that all expect to be passed a `cache`.
2014-08-06 18:28:36 +00:00
|
|
|
checkKey :: DdarRepo -> CheckPresent
|
2014-08-06 17:45:19 +00:00
|
|
|
checkKey ddarrepo key = do
|
2014-05-15 18:44:00 +00:00
|
|
|
directoryExists <- ddarDirectoryExists ddarrepo
|
|
|
|
case directoryExists of
|
2014-08-06 17:45:19 +00:00
|
|
|
Left e -> error e
|
2023-04-10 17:38:14 +00:00
|
|
|
Right True -> either giveup return
|
2014-08-06 17:45:19 +00:00
|
|
|
=<< inDdarManifest ddarrepo key
|
|
|
|
Right False -> return False
|
2014-05-15 18:44:00 +00:00
|
|
|
|
|
|
|
ddarLocal :: DdarRepo -> Bool
|
2015-02-12 19:44:10 +00:00
|
|
|
ddarLocal = notElem ':' . ddarRepoLocation
|