@@ -1418,6 +1418,11 @@ QemuOptsList bdrv_runtime_opts = {
.type = QEMU_OPT_BOOL,
.help = "always accept other writers (default: off)",
},
+ {
+ .name = BDRV_OPT_COMPRESS,
+ .type = QEMU_OPT_BOOL,
+ .help = "compress all writes to the image (default: off)",
+ },
{ /* end of list */ }
},
};
@@ -2983,6 +2988,11 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
flags &= ~BDRV_O_RDWR;
}
+ if (!g_strcmp0(qdict_get_try_str(options, BDRV_OPT_COMPRESS), "on") ||
+ qdict_get_try_bool(options, BDRV_OPT_COMPRESS, false)) {
+ bs->all_write_compressed = true;
+ }
+
if (flags & BDRV_O_SNAPSHOT) {
snapshot_options = qdict_new();
bdrv_temp_snapshot_options(&snapshot_flags, snapshot_options,
@@ -3208,7 +3218,7 @@ static int bdrv_reset_options_allowed(BlockDriverState *bs,
* in bdrv_reopen_prepare() so they can be left out of @new_opts */
const char *const common_options[] = {
"node-name", "discard", "cache.direct", "cache.no-flush",
- "read-only", "auto-read-only", "detect-zeroes", NULL
+ "read-only", "auto-read-only", "detect-zeroes", "compress", NULL
};
for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
@@ -1922,7 +1922,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
} else if (flags & BDRV_REQ_ZERO_WRITE) {
bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO);
ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags);
- } else if (flags & BDRV_REQ_WRITE_COMPRESSED) {
+ } else if (flags & BDRV_REQ_WRITE_COMPRESSED || bs->all_write_compressed) {
ret = bdrv_driver_pwritev_compressed(bs, offset, bytes,
qiov, qiov_offset);
} else if (bytes <= max_transfer) {
@@ -1787,6 +1787,10 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
/* Encryption works on a sector granularity */
bs->bl.request_alignment = qcrypto_block_get_sector_size(s->crypto);
}
+ if (bs->all_write_compressed) {
+ bs->bl.request_alignment = MAX(bs->bl.request_alignment,
+ s->cluster_size);
+ }
bs->bl.pwrite_zeroes_alignment = s->cluster_size;
bs->bl.pdiscard_alignment = s->cluster_size;
}
@@ -4152,10 +4156,8 @@ fail:
return ret;
}
-/* XXX: put compressed sectors first, then all the cluster aligned
- tables to avoid losing bytes in alignment */
static coroutine_fn int
-qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+qcow2_co_pwritev_compressed_task(BlockDriverState *bs,
uint64_t offset, uint64_t bytes,
QEMUIOVector *qiov, size_t qiov_offset)
{
@@ -4165,32 +4167,11 @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
uint8_t *buf, *out_buf;
uint64_t cluster_offset;
- if (has_data_file(bs)) {
- return -ENOTSUP;
- }
-
- if (bytes == 0) {
- /* align end of file to a sector boundary to ease reading with
- sector based I/Os */
- int64_t len = bdrv_getlength(bs->file->bs);
- if (len < 0) {
- return len;
- }
- return bdrv_co_truncate(bs->file, len, PREALLOC_MODE_OFF, NULL);
- }
-
- if (offset_into_cluster(s, offset)) {
- return -EINVAL;
- }
+ assert(bytes == s->cluster_size || (bytes < s->cluster_size &&
+ (offset + bytes == bs->total_sectors << BDRV_SECTOR_BITS)));
buf = qemu_blockalign(bs, s->cluster_size);
- if (bytes != s->cluster_size) {
- if (bytes > s->cluster_size ||
- offset + bytes != bs->total_sectors << BDRV_SECTOR_BITS)
- {
- qemu_vfree(buf);
- return -EINVAL;
- }
+ if (bytes < s->cluster_size) {
/* Zero-pad last write if image size is not cluster aligned */
memset(buf + bytes, 0, s->cluster_size - bytes);
}
@@ -4239,6 +4220,77 @@ fail:
return ret;
}
+static coroutine_fn int qcow2_co_pwritev_compressed_task_entry(AioTask *task)
+{
+ Qcow2AioTask *t = container_of(task, Qcow2AioTask, task);
+
+ assert(!t->cluster_type && !t->l2meta);
+
+ return qcow2_co_pwritev_compressed_task(t->bs, t->offset, t->bytes, t->qiov,
+ t->qiov_offset);
+}
+
+/*
+ * XXX: put compressed sectors first, then all the cluster aligned
+ tables to avoid losing bytes in alignment
+ */
+static coroutine_fn int
+qcow2_co_pwritev_compressed_part(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes,
+ QEMUIOVector *qiov, size_t qiov_offset)
+{
+ BDRVQcow2State *s = bs->opaque;
+ AioTaskPool *aio = NULL;
+ int ret;
+
+ if (has_data_file(bs)) {
+ return -ENOTSUP;
+ }
+
+ if (bytes == 0) {
+ /*
+ * align end of file to a sector boundary to ease reading with
+ * sector based I/Os
+ */
+ int64_t len = bdrv_getlength(bs->file->bs);
+ if (len < 0) {
+ return len;
+ }
+ return bdrv_co_truncate(bs->file, len, PREALLOC_MODE_OFF, NULL);
+ }
+
+ if (offset_into_cluster(s, offset)) {
+ return -EINVAL;
+ }
+
+ while (bytes && aio_task_pool_status(aio) == 0) {
+ uint32_t chunk_size = MIN(bytes, s->cluster_size);
+
+ if (!aio && chunk_size != bytes) {
+ aio = aio_task_pool_new(QCOW2_MAX_WORKERS);
+ }
+
+ ret = qcow2_add_task(bs, aio, qcow2_co_pwritev_compressed_task_entry,
+ 0, 0, offset, chunk_size, qiov, qiov_offset, NULL);
+ if (ret < 0) {
+ break;
+ }
+ qiov_offset += chunk_size;
+ offset += chunk_size;
+ bytes -= chunk_size;
+ }
+
+ if (aio) {
+ aio_task_pool_wait_all(aio);
+ if (ret == 0) {
+ ret = aio_task_pool_status(aio);
+ }
+ g_free(aio);
+ }
+
+ return ret;
+}
+
static int coroutine_fn
qcow2_co_preadv_compressed(BlockDriverState *bs,
uint64_t file_cluster_offset,
@@ -120,6 +120,7 @@
#define QCOW2_OPT_L2_CACHE_ENTRY_SIZE "l2-cache-entry-size"
#define QCOW2_OPT_REFCOUNT_CACHE_SIZE "refcount-cache-size"
#define QCOW2_OPT_CACHE_CLEAN_INTERVAL "cache-clean-interval"
+#define QCOW2_OPT_COMPRESS "compress"
typedef struct QCowHeader {
uint32_t magic;
@@ -4682,6 +4682,10 @@ QemuOptsList qemu_common_drive_opts = {
.name = BDRV_OPT_READ_ONLY,
.type = QEMU_OPT_BOOL,
.help = "open drive file as read-only",
+ },{
+ .name = BDRV_OPT_COMPRESS,
+ .type = QEMU_OPT_BOOL,
+ .help = "compress all writes to image",
},
THROTTLE_OPTS,
@@ -139,6 +139,7 @@ typedef struct HDGeometry {
#define BDRV_OPT_AUTO_READ_ONLY "auto-read-only"
#define BDRV_OPT_DISCARD "discard"
#define BDRV_OPT_FORCE_SHARE "force-share"
+#define BDRV_OPT_COMPRESS "compress"
#define BDRV_SECTOR_BITS 9
@@ -922,6 +922,8 @@ struct BlockDriverState {
/* BdrvChild links to this node may never be frozen */
bool never_freeze;
+ /* Compress all writes to the image */
+ bool all_write_compressed;
};
struct BlockBackendRootState {
@@ -3949,6 +3949,9 @@
# @force-share: force share all permission on added nodes.
# Requires read-only=true. (Since 2.10)
#
+# @compress: compress all writes to the image (Since 4.2)
+# (default: false)
+#
# Remaining options are determined by the block driver.
#
# Since: 2.9
@@ -3961,7 +3964,8 @@
'*read-only': 'bool',
'*auto-read-only': 'bool',
'*force-share': 'bool',
- '*detect-zeroes': 'BlockdevDetectZeroesOptions' },
+ '*detect-zeroes': 'BlockdevDetectZeroesOptions',
+ '*compress': 'bool' },
'discriminator': 'driver',
'data': {
'blkdebug': 'BlockdevOptionsBlkdebug',
@@ -850,7 +850,7 @@ DEF("blockdev", HAS_ARG, QEMU_OPTION_blockdev,
"-blockdev [driver=]driver[,node-name=N][,discard=ignore|unmap]\n"
" [,cache.direct=on|off][,cache.no-flush=on|off]\n"
" [,read-only=on|off][,detect-zeroes=on|off|unmap]\n"
- " [,driver specific parameters...]\n"
+ " [,compress=on|off][,driver specific parameters...]\n"
" configure a block backend\n", QEMU_ARCH_ALL)
STEXI
@item -blockdev @var{option}[,@var{option}[,@var{option}[,...]]]
@@ -905,6 +905,8 @@ discard requests.
conversion of plain zero writes by the OS to driver specific optimized
zero write commands. You may even choose "unmap" if @var{discard} is set
to "unmap" to allow a zero write to be converted to an @code{unmap} operation.
+@item compress
+Compress all writes to the image.
@end table
@item Driver-specific options for @code{file}
@@ -1026,7 +1028,7 @@ DEF("drive", HAS_ARG, QEMU_OPTION_drive,
" [,cache=writethrough|writeback|none|directsync|unsafe][,format=f]\n"
" [,snapshot=on|off][,rerror=ignore|stop|report]\n"
" [,werror=ignore|stop|report|enospc][,id=name][,aio=threads|native]\n"
- " [,readonly=on|off][,copy-on-read=on|off]\n"
+ " [,readonly=on|off][,copy-on-read=on|off][,compress=on|off]\n"
" [,discard=ignore|unmap][,detect-zeroes=on|off|unmap]\n"
" [[,bps=b]|[[,bps_rd=r][,bps_wr=w]]]\n"
" [[,iops=i]|[[,iops_rd=r][,iops_wr=w]]]\n"
QEMU currently supports writing compressed data of the size equal to one cluster. This patch allows writing QCOW2 compressed data that exceed one cluster. Now, we split buffered data into separate clusters and write them compressed using the existing functionality. To inform the block layer about writing all the data compressed, we introduce the 'compress' command line option. Based on that option, the written data will be aligned by the cluster size at the generic layer. Suggested-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Suggested-by: Roman Kagan <rkagan@virtuozzo.com> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@virtuozzo.com> --- block.c | 12 +++++- block/io.c | 2 +- block/qcow2.c | 106 ++++++++++++++++++++++++++++++++++------------ block/qcow2.h | 1 + blockdev.c | 4 ++ include/block/block.h | 1 + include/block/block_int.h | 2 + qapi/block-core.json | 6 ++- qemu-options.hx | 6 ++- 9 files changed, 108 insertions(+), 32 deletions(-)