block/gluster: prevent data loss after i/o error

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 write-behind-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.

Unfortunately, we have no way of knowing if the
'resync-failed-syncs-after-fsync' xlator option is supported, so for now
close the fd and set the BDS driver to NULL upon fsync error.

Signed-off-by: Jeff Cody <[email protected]>

diff --git a/block/gluster.c b/block/gluster.c
index d9aace625317c91d1e5916c22ad2a257d8505d39..a8aaacf645359483867aab51095b51bf2e68be9f 100644 (file)
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -314,6 +314,23 @@ 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);
@@ -366,6 +383,16 @@ 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 */
@@ -613,11 +640,35 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
 
     ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
     if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto error;
     }
 
     qemu_coroutine_yield();
+    if (acb.ret < 0) {
+        ret = acb.ret;
+        goto error;
+    }
+
     return acb.ret;
+
+error:
+    /* Some versions of Gluster (3.5.6 -> 3.5.8?) will not retain its cache
+     * after a fsync failure, so we have no way of allowing the guest to safely
+     * continue.  Gluster versions prior to 3.5.6 don't retain the cache
+     * either, but will invalidate the fd on error, so this is again our only
+     * option.
+     *
+     * The 'resync-failed-syncs-after-fsync' xlator option for the
+     * write-behind cache will cause later gluster versions to retain its
+     * cache after error, so long as the fd remains open.  However, we
+     * currently have no way of knowing if this option is supported.
+     *
+     * TODO: Once gluster provides a way for us to determine if the option
+     * is supported, bypass the closure and setting drv to NULL.  */
+    qemu_gluster_close(bs);
+    bs->drv = NULL;
+    return ret;
 }
 
 #ifdef CONFIG_GLUSTERFS_DISCARD

diff --git a/configure b/configure
index f1c307bfc69caf883509d1e4f336c9a3c61a6d61..ab54f3c8eed79c085d04872c1cd27701b09b4e4b 100755 (executable)
--- 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"
@@ -3400,6 +3401,9 @@ 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 $pkg_config --atleast-version=5 glusterfs-api; then
       glusterfs_discard="yes"
     fi
@@ -5342,6 +5346,10 @@ if test "$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