diff options
author | Pranith Kumar K <pkarampu@redhat.com> | 2014-06-23 21:35:29 +0530 |
---|---|---|
committer | Niels de Vos <ndevos@redhat.com> | 2014-06-24 09:26:13 -0700 |
commit | 5d2603c75bfd78c8b33903a20e844430276e7539 (patch) | |
tree | 3ca00f09ca0835de64167674351c386190e0a25d /xlators/cluster/afr | |
parent | b8f6798c173301f9fe0b12b53c67366fb8eaed59 (diff) |
cluster/afr: Fix resolution issues with afr
Problem with afr:
Lets say there is a directory hierarchy a/b/c/d on the mount and the
user is cd'ed into the directory. Bring down one of the bricks of replica and
remove all directories/files to simulate disk replacement on that brick. Now
this brick is brought back up. Creates on the cd'ed directory fail with ESTALE.
Basically before sending a create of 'f' inside 'd', fuse sends a lookup to
make sure the file is not present. On one of the bricks 'd' is present and
'f' is not so it sends ENOENT as response. On the new brick 'd' itself is not
present. So it sends ESTALE. In afr ESTALE is considered to be special errno on
witnessing which lookup has to fail. And ESTALE is given more priority than
ENOENT. Due to these reasons lookup fails with ESTALE rather than ENOENT. Since
lookup didn't fail with ENOENT, 'create' can't be issued so the command is
failed with ESTALE.
Solution:
Afr needs to consider ESTALE errno normally and ENOENT needs to
be given more priority so that operations like create can proceed even when
only one of the brick is up and running. Whenever client xlator identifies
that gfid-changed, it sets that information in lookup xdata. Afr uses this
information to fail the lookup with ESTALE so that top xlator can send
fresh lookup.
Change-Id: Ie8e0e327542fd644409eb5dadf451679afa1c0e5
BUG: 1112348
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/8154
Tested-by: Justin Clift <justin@gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-by: Niels de Vos <ndevos@redhat.com>
Diffstat (limited to 'xlators/cluster/afr')
-rw-r--r-- | xlators/cluster/afr/src/afr-common.c | 28 | ||||
-rw-r--r-- | xlators/cluster/afr/src/afr.h | 1 |
2 files changed, 19 insertions, 10 deletions
diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c index c4e57625220..2f9913152d4 100644 --- a/xlators/cluster/afr/src/afr-common.c +++ b/xlators/cluster/afr/src/afr-common.c @@ -2321,18 +2321,18 @@ afr_lookup_done (call_frame_t *frame, xlator_t *this) * others in that they must be given higher priority while * returning to the user. * - * The hierarchy is ESTALE > EIO > ENOENT > others + * The hierarchy is EIO > ENOENT > ESTALE > others */ int32_t afr_most_important_error(int32_t old_errno, int32_t new_errno, gf_boolean_t eio) { - if (old_errno == ESTALE || new_errno == ESTALE) - return ESTALE; if (eio && (old_errno == EIO || new_errno == EIO)) return EIO; if (old_errno == ENOENT || new_errno == ENOENT) return ENOENT; + if (old_errno == ESTALE || new_errno == ESTALE) + return ESTALE; return new_errno; } @@ -2361,8 +2361,19 @@ afr_resultant_errno_get (int32_t *children, } static void -afr_lookup_handle_error (afr_local_t *local, int32_t op_ret, int32_t op_errno) +afr_lookup_handle_error (afr_local_t *local, int32_t op_ret, int32_t op_errno, + dict_t *xattr) { + if (local->cont.lookup.needs_fresh_lookup) + return; + + if (xattr && dict_get (xattr, "gfid-changed")) { + local->op_ret = -1; + local->op_errno = ESTALE; + local->cont.lookup.needs_fresh_lookup = _gf_true; + return; + } + if ((local->loc.name == NULL) && (op_errno == ESTALE)) op_errno = ENOENT; @@ -2371,10 +2382,6 @@ afr_lookup_handle_error (afr_local_t *local, int32_t op_ret, int32_t op_errno) local->op_errno = afr_most_important_error(local->op_errno, op_errno, _gf_false); - - if (local->op_errno == ESTALE) { - local->op_ret = -1; - } } static void @@ -2491,7 +2498,7 @@ afr_lookup_handle_success (afr_local_t *local, xlator_t *this, int32_t child_ind afr_private_t *priv = this->private; if (local->success_count == 0) { - if (local->op_errno != ESTALE) { + if (!local->cont.lookup.needs_fresh_lookup) { local->op_ret = op_ret; local->op_errno = 0; } @@ -2528,7 +2535,8 @@ afr_lookup_cbk (call_frame_t *frame, void *cookie, local = frame->local; if (op_ret == -1) { - afr_lookup_handle_error (local, op_ret, op_errno); + afr_lookup_handle_error (local, op_ret, op_errno, + xattr); goto unlock; } afr_lookup_handle_success (local, this, child_index, op_ret, diff --git a/xlators/cluster/afr/src/afr.h b/xlators/cluster/afr/src/afr.h index 9abb48694a2..af57d8b0eff 100644 --- a/xlators/cluster/afr/src/afr.h +++ b/xlators/cluster/afr/src/afr.h @@ -550,6 +550,7 @@ typedef struct _afr_local { int32_t **pending_matrix; gf_boolean_t fresh_lookup; gf_boolean_t possible_spb; + gf_boolean_t needs_fresh_lookup; } lookup; struct { |