Implement alignment probing similar to file-posix, by reading from the
first 4k of the image.
Before this change, provisioning a VM on storage with sector size of
4096 bytes would fail when the installer try to create filesystems. Here
is an example command that reproduces this issue:
$ qemu-system-x86_64 -accel kvm -m 2048 -smp 2 \
-drive file=gluster://gluster1/gv0/fedora29.raw,format=raw,cache=none \
-cdrom Fedora-Server-dvd-x86_64-29-1.2.iso
The installer fails in few seconds when trying to create filesystem on
/dev/mapper/fedora-root. In error report we can see that it failed with
EINVAL (I could not extract the error from guest).
Copying disk fails with EINVAL:
$ qemu-img convert -p -f raw -O raw -t none -T none \
gluster://gluster1/gv0/fedora29.raw \
gluster://gluster1/gv0/fedora29-clone.raw
qemu-img: error while writing sector 4190208: Invalid argument
This is a fix to same issue fixed in commit a6b257a08e3d (file-posix:
Handle undetectable alignment) for gluster:// images.
This fix has the same limit, that the first block of the image should be
allocated, otherwise we cannot detect the alignment and fallback to a
safe value (4096) even when using storage with sector size of 512 bytes.
Signed-off-by: Nir Soffer <nsof...@redhat.com>
---
block/gluster.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/block/gluster.c b/block/gluster.c
index f64dc5b01e..d936240b72 100644
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -52,6 +52,9 @@
#define GERR_INDEX_HINT "hint: check in 'server' array index '%d'\n"
+/* The value is known only on the server side. */
+#define MAX_ALIGN 4096
+
typedef struct GlusterAIOCB {
int64_t size;
int ret;
@@ -902,8 +905,52 @@ out:
return ret;
}
+/*
+ * Check if read is allowed with given memory buffer and length.
+ *
+ * This function is used to check O_DIRECT request alignment.
+ */
+static bool gluster_is_io_aligned(struct glfs_fd *fd, void *buf, size_t len)
+{
+ ssize_t ret = glfs_pread(fd, buf, len, 0, 0, NULL);
+ return ret >= 0 || errno != EINVAL;
+}
+
+static void gluster_probe_alignment(BlockDriverState *bs, struct glfs_fd *fd,
+ Error **errp)
+{
+ char *buf;
+ size_t alignments[] = {1, 512, 1024, 2048, 4096};
+ size_t align;
+ int i;
+
+ buf = qemu_memalign(MAX_ALIGN, MAX_ALIGN);
+
+ for (i = 0; i < ARRAY_SIZE(alignments); i++) {
+ align = alignments[i];
+ if (gluster_is_io_aligned(fd, buf, align)) {
+ /* Fallback to safe value. */
+ bs->bl.request_alignment = (align != 1) ? align : MAX_ALIGN;
+ break;
+ }
+ }
+
+ qemu_vfree(buf);
+
+ if (!bs->bl.request_alignment) {
+ error_setg(errp, "Could not find working O_DIRECT alignment");
+ error_append_hint(errp, "Try cache.direct=off\n");
+ }
+}
+
static void qemu_gluster_refresh_limits(BlockDriverState *bs, Error **errp)
{
+ BDRVGlusterState *s = bs->opaque;
+
+ gluster_probe_alignment(bs, s->fd, errp);
+
+ bs->bl.min_mem_alignment = bs->bl.request_alignment;
+ bs->bl.opt_mem_alignment = MAX(bs->bl.request_alignment, MAX_ALIGN);
bs->bl.max_transfer = GLUSTER_MAX_TRANSFER;
}
--
2.20.1
