[Qemu-block] [PATCH for-2.6 2/2] block/gluster: prevent data loss after i/o error

[Jeff Cody]

Upon receiving an I/O error after an fsync, by default gluster will
dump its cache.  However, QEMU will retry the fsync, which is especially
useful when encountering errors such as ENOSPC when using the werror=stop
option.  When using caching with gluster, however, the last written data
will be lost upon encountering ENOSPC.  Using the cache xlator option of
'resync-failed-syncs-after-fsync' should cause gluster to retain the
cached data after a failed fsync, so that ENOSPC and other transient
errors are recoverable.

Signed-off-by: Jeff Cody <address@hidden>
---
 block/gluster.c | 27 +++++++++++++++++++++++++++
 configure       |  8 ++++++++
 2 files changed, 35 insertions(+)

diff --git a/block/gluster.c b/block/gluster.c
index 30a827e..b1cf71b 100644
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -330,6 +330,23 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict 
*options,
         goto out;
     }
 
+#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
+    /* Without this, if fsync fails for a recoverable reason (for instance,
+     * ENOSPC), gluster will dump its cache, preventing retries.  This means
+     * almost certain data loss.  Not all gluster versions support the
+     * 'resync-failed-syncs-after-fsync' key value, but there is no way to
+     * discover during runtime if it is supported (this api returns success for
+     * unknown key/value pairs) */
+    ret = glfs_set_xlator_option (s->glfs, "*-write-behind",
+                                           "resync-failed-syncs-after-fsync",
+                                           "on");
+    if (ret < 0) {
+        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
+        ret = -errno;
+        goto out;
+    }
+#endif
+
     qemu_gluster_parse_flags(bdrv_flags, &open_flags);
 
     s->fd = glfs_open(s->glfs, gconf->image, open_flags);
@@ -386,6 +403,16 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState 
*state,
         goto exit;
     }
 
+#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
+    ret = glfs_set_xlator_option(reop_s->glfs, "*-write-behind",
+                                 "resync-failed-syncs-after-fsync", "on");
+    if (ret < 0) {
+        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
+        ret = -errno;
+        goto exit;
+    }
+#endif
+
     reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
     if (reop_s->fd == NULL) {
         /* reops->glfs will be cleaned up in _abort */
diff --git a/configure b/configure
index 5db29f0..3e921fe 100755
--- a/configure
+++ b/configure
@@ -298,6 +298,7 @@ coroutine=""
 coroutine_pool=""
 seccomp=""
 glusterfs=""
+glusterfs_xlator_opt="no"
 glusterfs_discard="no"
 glusterfs_zerofill="no"
 archipelago="no"
@@ -3397,6 +3398,9 @@ if test "$glusterfs" != "no" ; then
     glusterfs="yes"
     glusterfs_cflags=`$pkg_config --cflags glusterfs-api`
     glusterfs_libs=`$pkg_config --libs glusterfs-api`
+    if $pkg_config --atleast-version=4 glusterfs-api; then
+      glusterfs_xlator_opt="yes"
+    fi
     if $pkg_config --atleast-version=5 glusterfs-api; then
       glusterfs_discard="yes"
     fi
@@ -5339,6 +5343,10 @@ if test "$glusterfs" = "yes" ; then
   echo "GLUSTERFS_LIBS=$glusterfs_libs" >> $config_host_mak
 fi
 
+if test "$glusterfs_xlator_opt" = "yes" ; then
+  echo "CONFIG_GLUSTERFS_XLATOR_OPT=y" >> $config_host_mak
+fi
+
 if test "$glusterfs_discard" = "yes" ; then
   echo "CONFIG_GLUSTERFS_DISCARD=y" >> $config_host_mak
 fi
-- 
1.9.3