summaryrefslogtreecommitdiffstats
path: root/qemu/block/gluster.c
diff options
context:
space:
mode:
Diffstat (limited to 'qemu/block/gluster.c')
-rw-r--r--qemu/block/gluster.c159
1 files changed, 96 insertions, 63 deletions
diff --git a/qemu/block/gluster.c b/qemu/block/gluster.c
index 1eb3a8c39..a8aaacf64 100644
--- a/qemu/block/gluster.c
+++ b/qemu/block/gluster.c
@@ -7,8 +7,10 @@
* See the COPYING file in the top-level directory.
*
*/
+#include "qemu/osdep.h"
#include <glusterfs/api/glfs.h>
#include "block/block_int.h"
+#include "qapi/error.h"
#include "qemu/uri.h"
typedef struct GlusterAIOCB {
@@ -245,7 +247,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
if (!ret || ret == acb->size) {
acb->ret = 0; /* Success */
} else if (ret < 0) {
- acb->ret = ret; /* Read/Write failed */
+ acb->ret = -errno; /* Read/Write failed */
} else {
acb->ret = -EIO; /* Partial read/write - fail it */
}
@@ -312,6 +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);
@@ -364,6 +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 */
@@ -429,28 +458,23 @@ static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
{
int ret;
- GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+ GlusterAIOCB acb;
BDRVGlusterState *s = bs->opaque;
off_t size = nb_sectors * BDRV_SECTOR_SIZE;
off_t offset = sector_num * BDRV_SECTOR_SIZE;
- acb->size = size;
- acb->ret = 0;
- acb->coroutine = qemu_coroutine_self();
- acb->aio_context = bdrv_get_aio_context(bs);
+ acb.size = size;
+ acb.ret = 0;
+ acb.coroutine = qemu_coroutine_self();
+ acb.aio_context = bdrv_get_aio_context(bs);
- ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
+ ret = glfs_zerofill_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
if (ret < 0) {
- ret = -errno;
- goto out;
+ return -errno;
}
qemu_coroutine_yield();
- ret = acb->ret;
-
-out:
- g_slice_free(GlusterAIOCB, acb);
- return ret;
+ return acb.ret;
}
static inline bool gluster_supports_zerofill(void)
@@ -541,35 +565,30 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write)
{
int ret;
- GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+ GlusterAIOCB acb;
BDRVGlusterState *s = bs->opaque;
size_t size = nb_sectors * BDRV_SECTOR_SIZE;
off_t offset = sector_num * BDRV_SECTOR_SIZE;
- acb->size = size;
- acb->ret = 0;
- acb->coroutine = qemu_coroutine_self();
- acb->aio_context = bdrv_get_aio_context(bs);
+ acb.size = size;
+ acb.ret = 0;
+ acb.coroutine = qemu_coroutine_self();
+ acb.aio_context = bdrv_get_aio_context(bs);
if (write) {
ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
- &gluster_finish_aiocb, acb);
+ gluster_finish_aiocb, &acb);
} else {
ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
- &gluster_finish_aiocb, acb);
+ gluster_finish_aiocb, &acb);
}
if (ret < 0) {
- ret = -errno;
- goto out;
+ return -errno;
}
qemu_coroutine_yield();
- ret = acb->ret;
-
-out:
- g_slice_free(GlusterAIOCB, acb);
- return ret;
+ return acb.ret;
}
static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
@@ -597,28 +616,58 @@ static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
}
+static void qemu_gluster_close(BlockDriverState *bs)
+{
+ BDRVGlusterState *s = bs->opaque;
+
+ if (s->fd) {
+ glfs_close(s->fd);
+ s->fd = NULL;
+ }
+ glfs_fini(s->glfs);
+}
+
static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
{
int ret;
- GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+ GlusterAIOCB acb;
BDRVGlusterState *s = bs->opaque;
- acb->size = 0;
- acb->ret = 0;
- acb->coroutine = qemu_coroutine_self();
- acb->aio_context = bdrv_get_aio_context(bs);
+ acb.size = 0;
+ acb.ret = 0;
+ acb.coroutine = qemu_coroutine_self();
+ acb.aio_context = bdrv_get_aio_context(bs);
- ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
+ ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
if (ret < 0) {
ret = -errno;
- goto out;
+ goto error;
}
qemu_coroutine_yield();
- ret = acb->ret;
-
-out:
- g_slice_free(GlusterAIOCB, acb);
+ 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;
}
@@ -627,28 +676,23 @@ static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
int64_t sector_num, int nb_sectors)
{
int ret;
- GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+ GlusterAIOCB acb;
BDRVGlusterState *s = bs->opaque;
size_t size = nb_sectors * BDRV_SECTOR_SIZE;
off_t offset = sector_num * BDRV_SECTOR_SIZE;
- acb->size = 0;
- acb->ret = 0;
- acb->coroutine = qemu_coroutine_self();
- acb->aio_context = bdrv_get_aio_context(bs);
+ acb.size = 0;
+ acb.ret = 0;
+ acb.coroutine = qemu_coroutine_self();
+ acb.aio_context = bdrv_get_aio_context(bs);
- ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
+ ret = glfs_discard_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
if (ret < 0) {
- ret = -errno;
- goto out;
+ return -errno;
}
qemu_coroutine_yield();
- ret = acb->ret;
-
-out:
- g_slice_free(GlusterAIOCB, acb);
- return ret;
+ return acb.ret;
}
#endif
@@ -679,17 +723,6 @@ static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
}
}
-static void qemu_gluster_close(BlockDriverState *bs)
-{
- BDRVGlusterState *s = bs->opaque;
-
- if (s->fd) {
- glfs_close(s->fd);
- s->fd = NULL;
- }
- glfs_fini(s->glfs);
-}
-
static int qemu_gluster_has_zero_init(BlockDriverState *bs)
{
/* GlusterFS volume could be backed by a block device */