From 2d7e46ea983a8b8870032e7ff9fe3b83d81143f6 Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Mon, 18 Apr 2016 14:04:20 -0400
Subject: [PATCH] fix drop hang reported by musicmatze
Fix hang when dropping content needs to lock the content on a ssh remote,
which occurred when the remote has git-annex version 5.20151019 or newer.
Analysis: `race` runs 2 threads at once, and the hGetLine finishes first.
So, it tries to cancel the waitForProcess, but unfortunately that is making
a foreign call and so cannot be canceled. The remote git-annex-shell
is waiting for a line on stdin before it will exit. Deadlock.
This only occurred sometimes; I reproduced it going from darkstar to
elephant, but not from darkstar to darkstar. Not sure how that fits into
the above analysis -- perhaps a race condition is also involved?
Fixed by not using `race`; now the hGetLine will fail with an exception
if the remote git-annex-shell exits without any output.
---
Remote/Git.hs | 21 +++++++++------------
debian/changelog | 4 ++++
2 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/Remote/Git.hs b/Remote/Git.hs
index 256428137f..284d6a49c8 100644
--- a/Remote/Git.hs
+++ b/Remote/Git.hs
@@ -57,7 +57,6 @@ import Types.NumCopies
import Control.Concurrent
import Control.Concurrent.MSampleVar
-import Control.Concurrent.Async
import qualified Data.Map as M
import Network.URI
@@ -387,17 +386,14 @@ lockKey r key callback
, std_out = CreatePipe
, std_err = UseHandle nullh
}
- -- Wait for either the process to exit, or for it to
- -- indicate the content is locked.
- v <- liftIO $ race
- (waitForProcess p)
- (hGetLine hout)
- let signaldone = void $ tryNonAsync $ liftIO $ do
- hPutStrLn hout ""
- hFlush hout
- hClose hin
- hClose hout
- void $ waitForProcess p
+ v <- liftIO $ tryIO $ hGetLine hout
+ let signaldone = void $ tryNonAsync $ liftIO $ mapM_ tryNonAsync
+ [ hPutStrLn hout ""
+ , hFlush hout
+ , hClose hin
+ , hClose hout
+ , void $ waitForProcess p
+ ]
let checkexited = not . isJust <$> getProcessExitCode p
case v of
Left _exited -> do
@@ -405,6 +401,7 @@ lockKey r key callback
liftIO $ do
hClose hin
hClose hout
+ void $ waitForProcess p
failedlock
Right l
| l == Ssh.contentLockedMarker -> bracket_
diff --git a/debian/changelog b/debian/changelog
index 588c34542d..9c008669d7 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -17,6 +17,10 @@ git-annex (6.20160413) UNRELEASED; urgency=medium
* fsck: Warn when core.sharedRepository is set and an annex object file's
write bit is not set and cannot be set due to the file being owned
by a different user.
+ * Fix hang when dropping content needs to lock the content on a
+ ssh remote, which occurred when the remote has git-annex version
+ 5.20151019 or newer. (The bug was in the client side; the remote
+ git-annex-shell does not need to be upgraded.)
-- Joey Hess <id@joeyh.name> Wed, 13 Apr 2016 13:30:32 -0400