summaryrefslogtreecommitdiffstats
path: root/xlators/cluster/afr/src/afr-self-heal-algorithm.c
diff options
context:
space:
mode:
authorBrian Foster <bfoster@redhat.com>2012-11-01 09:46:12 -0400
committerVijay Bellur <vbellur@redhat.com>2012-11-29 09:00:28 -0800
commit0314f16ec59d8c22597c8c14b53a473b736b8b1f (patch)
tree1e0e1dc470be5d04ff41c470c3812bc10bd0afb3 /xlators/cluster/afr/src/afr-self-heal-algorithm.c
parentc85a3eee54b4028573c905829d5b46c0b6512c56 (diff)
afr: handle short writes in afr_writev_wind and self-heal to avoid corruption
The current failure to handle short writes on writev fops leaves us open to file corruption. A short write on a user request is ignored and leaves replicas in an inconsistent state. A short write during a self-heal is ignored and incorrectly marks the files as consistent if the heal completes. Modify user writev handling to return the best case return value from each of the replicas. Short writes that occur relative to this value are marked as failed and will require a heal. Modify self-heal to set an error on a short write and abort the heal. BUG: 853690 Change-Id: I18b30f58702326249230eeebb361b29e40b535f5 Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-on: http://review.gluster.org/4150 Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com> Tested-by: Gluster Build System <jenkins@build.gluster.com>
Diffstat (limited to 'xlators/cluster/afr/src/afr-self-heal-algorithm.c')
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-algorithm.c20
1 files changed, 19 insertions, 1 deletions
diff --git a/xlators/cluster/afr/src/afr-self-heal-algorithm.c b/xlators/cluster/afr/src/afr-self-heal-algorithm.c
index 9ad40592088..e03e1cc45f0 100644
--- a/xlators/cluster/afr/src/afr-self-heal-algorithm.c
+++ b/xlators/cluster/afr/src/afr-self-heal-algorithm.c
@@ -434,11 +434,20 @@ sh_loop_write_cbk (call_frame_t *loop_frame, void *cookie, xlator_t *this,
sh->op_failed = 1;
afr_sh_set_error (loop_sh, op_errno);
- }
+ } else if (op_ret < loop_local->cont.writev.vector->iov_len) {
+ gf_log(this->name, GF_LOG_ERROR,
+ "incomplete write to %s on subvolume %s "
+ "(expected %lu, returned %d)", sh_local->loc.path,
+ priv->children[child_index]->name,
+ loop_local->cont.writev.vector->iov_len, op_ret);
+ sh->op_failed = 1;
+ }
call_count = afr_frame_return (loop_frame);
if (call_count == 0) {
+ iobref_unref(loop_local->cont.writev.iobref);
+
sh_loop_return (sh_frame, this, loop_frame,
loop_sh->op_ret, loop_sh->op_errno);
}
@@ -527,8 +536,17 @@ sh_loop_read_cbk (call_frame_t *loop_frame, void *cookie,
sh_loop_return (sh_frame, this, loop_frame, 0, 0);
goto out;
}
+
loop_local->call_count = call_count;
+ /*
+ * We only really need the request size at the moment, but the buffer
+ * is required if we want to issue a retry in the event of a short write.
+ * Therefore, we duplicate the vector and ref the iobref here...
+ */
+ loop_local->cont.writev.vector = iov_dup(vector, count);
+ loop_local->cont.writev.iobref = iobref_ref(iobref);
+
for (i = 0; i < priv->child_count; i++) {
if (!loop_sh->write_needed[i])
continue;