From 6bff597bf6580ecc691258e849f652911dbdda7c Mon Sep 17 00:00:00 2001 From: Peter Krempa Date: Thu, 12 Oct 2017 16:14:10 +0200 Subject: [PATCH 01/35] block: don't add 'driver' to options when referring to backing via node name When referring to a backing file of an image via node name bdrv_open_backing_file would add the 'driver' option to the option list filling it with the backing format driver. This breaks construction of the backing chain via -blockdev, as bdrv_open_inherit reports an error if both 'reference' and 'options' are provided. $ qemu-img create -f raw /tmp/backing.raw 64M $ qemu-img create -f qcow2 -F raw -b /tmp/backing.raw /tmp/test.qcow2 $ qemu-system-x86_64 \ -blockdev driver=file,filename=/tmp/backing.raw,node-name=backing \ -blockdev driver=qcow2,file.driver=file,file.filename=/tmp/test.qcow2,node-name=root,backing=backing qemu-system-x86_64: -blockdev driver=qcow2,file.driver=file,file.filename=/tmp/test.qcow2,node-name=root,backing=backing: Could not open backing file: Cannot reference an existing block device with additional options or a new filename Signed-off-by: Peter Krempa Signed-off-by: Kevin Wolf --- block.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index 46eb1728da..684cb018da 100644 --- a/block.c +++ b/block.c @@ -2245,7 +2245,8 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, goto free_exit; } - if (bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) { + if (!reference && + bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) { qdict_put_str(options, "driver", bs->backing_format); } From 760c4d43ae43f5d4b5eec450a53f056c3c91fab1 Mon Sep 17 00:00:00 2001 From: Kevin Wolf Date: Tue, 17 Oct 2017 17:08:51 +0200 Subject: [PATCH 02/35] qemu-iotests: Test backing_fmt with backing node reference This changes test case 191 to include a backing image that has backing_fmt set in the image file, but is referenced by node name in the qemu command line. Signed-off-by: Kevin Wolf Reviewed-by: Eric Blake --- tests/qemu-iotests/191 | 3 ++- tests/qemu-iotests/191.out | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index ac2b88fd78..28bdea8f98 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -56,7 +56,8 @@ echo === Preparing and starting VM === echo TEST_IMG="${TEST_IMG}.base" _make_test_img $size -TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" +IMGOPTS=$(_optstr_add "$IMGOPTS" "backing_fmt=$IMGFMT") \ + TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" _make_test_img -b "${TEST_IMG}.mid" TEST_IMG="${TEST_IMG}.ovl2" _make_test_img -b "${TEST_IMG}.mid" diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out index 7bfcd2d5d8..6157fa520f 100644 --- a/tests/qemu-iotests/191.out +++ b/tests/qemu-iotests/191.out @@ -3,7 +3,7 @@ QA output created by 191 === Preparing and starting VM === Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 -Formatting 'TEST_DIR/t.IMGFMT.mid', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.base +Formatting 'TEST_DIR/t.IMGFMT.mid', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.mid Formatting 'TEST_DIR/t.IMGFMT.ovl2', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.mid wrote 65536/65536 bytes at offset 1048576 From 298a1665a2800f7264e483c2dd1f551574243a2f Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:46:57 -0500 Subject: [PATCH 03/35] block: Allow NULL file for bdrv_get_block_status() Not all callers care about which BDS owns the mapping for a given range of the file. This patch merely simplifies the callers by consolidating the logic in the common call point, while guaranteeing a non-NULL file to all the driver callbacks, for no semantic change. The only caller that does not care about pnum is bdrv_is_allocated, as invoked by vvfat; we can likewise add assertions that the rest of the stack does not have to worry about a NULL pnum. Furthermore, this will also set the stage for a future cleanup: when a caller does not care about which BDS owns an offset, it would be nice to allow the driver to optimize things to not have to return BDRV_BLOCK_OFFSET_VALID in the first place. In the case of fragmented allocation (for example, it's fairly easy to create a qcow2 image where consecutive guest addresses are not at consecutive host addresses), the current contract requires bdrv_get_block_status() to clamp *pnum to the limit where host addresses are no longer consecutive, but allowing a NULL file means that *pnum could be set to the full length of known-allocated data. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 49 +++++++++++++++++++++------------------ block/mirror.c | 3 +-- block/qcow2.c | 8 ++----- include/block/block_int.h | 10 ++++---- qemu-img.c | 10 ++++---- 5 files changed, 40 insertions(+), 40 deletions(-) diff --git a/block/io.c b/block/io.c index 0854e0fdac..93231b0e26 100644 --- a/block/io.c +++ b/block/io.c @@ -718,7 +718,6 @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { int64_t target_sectors, ret, nb_sectors, sector_num = 0; BlockDriverState *bs = child->bs; - BlockDriverState *file; int n; target_sectors = bdrv_nb_sectors(bs); @@ -731,7 +730,7 @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) if (nb_sectors <= 0) { return 0; } - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, &file); + ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, NULL); if (ret < 0) { error_report("error getting block status at sector %" PRId64 ": %s", sector_num, strerror(-ret)); @@ -1820,8 +1819,9 @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * beyond the end of the disk image it will be clamped; if 'pnum' is set to * the end of the image, then the returned value will include BDRV_BLOCK_EOF. * - * If returned value is positive and BDRV_BLOCK_OFFSET_VALID bit is set, 'file' - * points to the BDS which the sector range is allocated in. + * If returned value is positive, BDRV_BLOCK_OFFSET_VALID bit is set, and + * 'file' is non-NULL, then '*file' points to the BDS which the sector range + * is allocated in. */ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, int64_t sector_num, @@ -1831,20 +1831,23 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, int64_t total_sectors; int64_t n; int64_t ret, ret2; + BlockDriverState *local_file = NULL; - *file = NULL; + assert(pnum); + *pnum = 0; total_sectors = bdrv_nb_sectors(bs); if (total_sectors < 0) { - return total_sectors; + ret = total_sectors; + goto early_out; } if (sector_num >= total_sectors) { - *pnum = 0; - return BDRV_BLOCK_EOF; + ret = BDRV_BLOCK_EOF; + goto early_out; } if (!nb_sectors) { - *pnum = 0; - return 0; + ret = 0; + goto early_out; } n = total_sectors - sector_num; @@ -1860,23 +1863,23 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, } if (bs->drv->protocol_name) { ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); - *file = bs; + local_file = bs; } - return ret; + goto early_out; } bdrv_inc_in_flight(bs); ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum, - file); + &local_file); if (ret < 0) { *pnum = 0; goto out; } if (ret & BDRV_BLOCK_RAW) { - assert(ret & BDRV_BLOCK_OFFSET_VALID && *file); - ret = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS, - *pnum, pnum, file); + assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); + ret = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + *pnum, pnum, &local_file); goto out; } @@ -1894,14 +1897,13 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, } } - if (*file && *file != bs && + if (local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { - BlockDriverState *file2; int file_pnum; - ret2 = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS, - *pnum, &file_pnum, &file2); + ret2 = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + *pnum, &file_pnum, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it * is useful but not necessary. @@ -1927,6 +1929,10 @@ out: if (ret >= 0 && sector_num + *pnum == total_sectors) { ret |= BDRV_BLOCK_EOF; } +early_out: + if (file) { + *file = local_file; + } return ret; } @@ -2026,7 +2032,6 @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - BlockDriverState *file; int64_t sector_num = offset >> BDRV_SECTOR_BITS; int nb_sectors = bytes >> BDRV_SECTOR_BITS; int64_t ret; @@ -2035,7 +2040,7 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &psectors, - &file); + NULL); if (ret < 0) { return ret; } diff --git a/block/mirror.c b/block/mirror.c index 153758ca9f..e76e754d26 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -390,7 +390,6 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) int io_sectors; unsigned int io_bytes; int64_t io_bytes_acct; - BlockDriverState *file; enum MirrorMethod { MIRROR_METHOD_COPY, MIRROR_METHOD_ZERO, @@ -401,7 +400,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) ret = bdrv_get_block_status_above(source, NULL, offset >> BDRV_SECTOR_BITS, nb_chunks * sectors_per_chunk, - &io_sectors, &file); + &io_sectors, NULL); io_bytes = io_sectors * BDRV_SECTOR_SIZE; if (ret < 0) { io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes); diff --git a/block/qcow2.c b/block/qcow2.c index f63d1831f8..0e4c91cabc 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2976,7 +2976,6 @@ static bool is_zero_sectors(BlockDriverState *bs, int64_t start, uint32_t count) { int nr; - BlockDriverState *file; int64_t res; if (start + count > bs->total_sectors) { @@ -2986,8 +2985,7 @@ static bool is_zero_sectors(BlockDriverState *bs, int64_t start, if (!count) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start, count, - &nr, &file); + res = bdrv_get_block_status_above(bs, NULL, start, count, &nr, NULL); return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == count; } @@ -3703,13 +3701,11 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, offset += pnum * BDRV_SECTOR_SIZE) { int nb_sectors = MIN(ssize - offset, BDRV_REQUEST_MAX_BYTES) / BDRV_SECTOR_SIZE; - BlockDriverState *file; int64_t ret; ret = bdrv_get_block_status_above(in_bs, NULL, offset >> BDRV_SECTOR_BITS, - nb_sectors, - &pnum, &file); + nb_sectors, &pnum, NULL); if (ret < 0) { error_setg_errno(&local_err, -ret, "Unable to get block status"); diff --git a/include/block/block_int.h b/include/block/block_int.h index 885c08e989..246eee2e82 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -202,10 +202,12 @@ struct BlockDriver { int64_t offset, int bytes); /* - * Building block for bdrv_block_status[_above]. The driver should - * answer only according to the current layer, and should not - * set BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h - * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. + * Building block for bdrv_block_status[_above] and + * bdrv_is_allocated[_above]. The driver should answer only + * according to the current layer, and should not set + * BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h + * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. The block + * layer guarantees non-NULL pnum and file. */ int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, diff --git a/qemu-img.c b/qemu-img.c index d6007b2a6d..e9c7b30c91 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1375,7 +1375,6 @@ static int img_compare(int argc, char **argv) for (;;) { int64_t status1, status2; - BlockDriverState *file; nb_sectors = sectors_to_process(total_sectors, sector_num); if (nb_sectors <= 0) { @@ -1383,7 +1382,7 @@ static int img_compare(int argc, char **argv) } status1 = bdrv_get_block_status_above(bs1, NULL, sector_num, total_sectors1 - sector_num, - &pnum1, &file); + &pnum1, NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -1393,7 +1392,7 @@ static int img_compare(int argc, char **argv) status2 = bdrv_get_block_status_above(bs2, NULL, sector_num, total_sectors2 - sector_num, - &pnum2, &file); + &pnum2, NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); @@ -1599,15 +1598,14 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); if (s->sector_next_status <= sector_num) { - BlockDriverState *file; if (s->target_has_backing) { ret = bdrv_get_block_status(blk_bs(s->src[src_cur]), sector_num - src_cur_offset, - n, &n, &file); + n, &n, NULL); } else { ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, sector_num - src_cur_offset, - n, &n, &file); + n, &n, NULL); } if (ret < 0) { return ret; From c9ce8c4da65b0c2b1dc82cbf2328ff3e23d76943 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:46:58 -0500 Subject: [PATCH 04/35] block: Add flag to avoid wasted work in bdrv_is_allocated() Not all callers care about which BDS owns the mapping for a given range of the file, or where the zeroes lie within that mapping. In particular, bdrv_is_allocated() cares more about finding the largest run of allocated data from the guest perspective, whether or not that data is consecutive from the host perspective, and whether or not the data reads as zero. Therefore, doing subsequent refinements such as checking how much of the format-layer allocation also satisfies BDRV_BLOCK_ZERO at the protocol layer is wasted work - in the best case, it just costs extra CPU cycles during a single bdrv_is_allocated(), but in the worst case, it results in a smaller *pnum, and forces callers to iterate through more status probes when visiting the entire file for even more extra CPU cycles. This patch only optimizes the block layer (no behavior change when want_zero is true, but skip unnecessary effort when it is false). Then when subsequent patches tweak the driver callback to be byte-based, we can also pass this hint through to the driver. Tweak BdrvCoGetBlockStatusData to declare arguments in parameter order, rather than mixing things up (minimizing padding is not necessary here). Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 57 +++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 41 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index 93231b0e26..8ba408c813 100644 --- a/block/io.c +++ b/block/io.c @@ -1769,10 +1769,11 @@ int bdrv_flush_all(void) typedef struct BdrvCoGetBlockStatusData { BlockDriverState *bs; BlockDriverState *base; - BlockDriverState **file; + bool want_zero; int64_t sector_num; int nb_sectors; int *pnum; + BlockDriverState **file; int64_t ret; bool done; } BdrvCoGetBlockStatusData; @@ -1808,6 +1809,11 @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * Drivers not implementing the functionality are assumed to not support * backing files, hence all their sectors are reported as allocated. * + * If 'want_zero' is true, the caller is querying for mapping purposes, + * and the result should include BDRV_BLOCK_OFFSET_VALID and + * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those + * bits particularly if it allows for a larger value in 'pnum'. + * * If 'sector_num' is beyond the end of the disk image the return value is * BDRV_BLOCK_EOF and 'pnum' is set to 0. * @@ -1824,6 +1830,7 @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * is allocated in. */ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, + bool want_zero, int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file) @@ -1878,31 +1885,34 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); - ret = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + ret = bdrv_co_get_block_status(local_file, want_zero, + ret >> BDRV_SECTOR_BITS, *pnum, pnum, &local_file); goto out; } if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) { ret |= BDRV_BLOCK_ALLOCATED; - } else { + } else if (want_zero) { if (bdrv_unallocated_blocks_are_zero(bs)) { ret |= BDRV_BLOCK_ZERO; } else if (bs->backing) { BlockDriverState *bs2 = bs->backing->bs; int64_t nb_sectors2 = bdrv_nb_sectors(bs2); + if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) { ret |= BDRV_BLOCK_ZERO; } } } - if (local_file && local_file != bs && + if (want_zero && local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { int file_pnum; - ret2 = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + ret2 = bdrv_co_get_block_status(local_file, want_zero, + ret >> BDRV_SECTOR_BITS, *pnum, &file_pnum, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it @@ -1938,6 +1948,7 @@ early_out: static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool want_zero, int64_t sector_num, int nb_sectors, int *pnum, @@ -1949,7 +1960,8 @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum, file); + ret = bdrv_co_get_block_status(p, want_zero, sector_num, nb_sectors, + pnum, file); if (ret < 0) { break; } @@ -1979,6 +1991,7 @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) BdrvCoGetBlockStatusData *data = opaque; data->ret = bdrv_co_get_block_status_above(data->bs, data->base, + data->want_zero, data->sector_num, data->nb_sectors, data->pnum, @@ -1991,20 +2004,22 @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) * * See bdrv_co_get_block_status_above() for details. */ -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +static int64_t bdrv_common_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, + int64_t sector_num, + int nb_sectors, int *pnum, + BlockDriverState **file) { Coroutine *co; BdrvCoGetBlockStatusData data = { .bs = bs, .base = base, - .file = file, + .want_zero = want_zero, .sector_num = sector_num, .nb_sectors = nb_sectors, .pnum = pnum, + .file = file, .done = false, }; @@ -2020,6 +2035,16 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, return data.ret; } +int64_t bdrv_get_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + int64_t sector_num, + int nb_sectors, int *pnum, + BlockDriverState **file) +{ + return bdrv_common_block_status_above(bs, base, true, sector_num, + nb_sectors, pnum, file); +} + int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, @@ -2032,15 +2057,15 @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - int64_t sector_num = offset >> BDRV_SECTOR_BITS; - int nb_sectors = bytes >> BDRV_SECTOR_BITS; int64_t ret; int psectors; assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &psectors, - NULL); + ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, + offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &psectors, + NULL); if (ret < 0) { return ret; } From 7cfd527525a7d6b1c904890a6b84c1227846415e Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:46:59 -0500 Subject: [PATCH 05/35] block: Make bdrv_round_to_clusters() signature more useful In the process of converting sector-based interfaces to bytes, I'm finding it easier to represent a byte count as a 64-bit integer at the block layer (even if we are internally capped by SIZE_MAX or even INT_MAX for individual transactions, it's still nicer to not have to worry about truncation/overflow issues on as many variables). Update the signature of bdrv_round_to_clusters() to uniformly use int64_t, matching the signature already chosen for bdrv_is_allocated and the fact that off_t is also a signed type, then adjust clients according to the required fallout (even where the result could now exceed 32 bits, no client is directly assigning the result into a 32-bit value without breaking things into a loop first). Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 6 +++--- block/mirror.c | 7 +++---- block/trace-events | 2 +- include/block/block.h | 4 ++-- 4 files changed, 9 insertions(+), 10 deletions(-) diff --git a/block/io.c b/block/io.c index 8ba408c813..db8dc59c94 100644 --- a/block/io.c +++ b/block/io.c @@ -469,9 +469,9 @@ static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) * Round a region to cluster boundaries */ void bdrv_round_to_clusters(BlockDriverState *bs, - int64_t offset, unsigned int bytes, + int64_t offset, int64_t bytes, int64_t *cluster_offset, - unsigned int *cluster_bytes) + int64_t *cluster_bytes) { BlockDriverInfo bdi; @@ -969,7 +969,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, struct iovec iov; QEMUIOVector local_qiov; int64_t cluster_offset; - unsigned int cluster_bytes; + int64_t cluster_bytes; size_t skip_bytes; int ret; int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, diff --git a/block/mirror.c b/block/mirror.c index e76e754d26..d11706c566 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -190,10 +190,9 @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset, bool need_cow; int ret = 0; int64_t align_offset = *offset; - unsigned int align_bytes = *bytes; + int64_t align_bytes = *bytes; int max_bytes = s->granularity * s->max_iov; - assert(*bytes < INT_MAX); need_cow = !test_bit(*offset / s->granularity, s->cow_bitmap); need_cow |= !test_bit((*offset + *bytes - 1) / s->granularity, s->cow_bitmap); @@ -388,7 +387,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) while (nb_chunks > 0 && offset < s->bdev_length) { int64_t ret; int io_sectors; - unsigned int io_bytes; + int64_t io_bytes; int64_t io_bytes_acct; enum MirrorMethod { MIRROR_METHOD_COPY, @@ -413,7 +412,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) io_bytes = s->granularity; } else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) { int64_t target_offset; - unsigned int target_bytes; + int64_t target_bytes; bdrv_round_to_clusters(blk_bs(s->target), offset, io_bytes, &target_offset, &target_bytes); if (target_offset == offset && diff --git a/block/trace-events b/block/trace-events index 25dd5a3026..11c8d5f590 100644 --- a/block/trace-events +++ b/block/trace-events @@ -12,7 +12,7 @@ blk_co_pwritev(void *blk, void *bs, int64_t offset, unsigned int bytes, int flag bdrv_co_preadv(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x" bdrv_co_pwritev(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x" bdrv_co_pwrite_zeroes(void *bs, int64_t offset, int count, int flags) "bs %p offset %"PRId64" count %d flags 0x%x" -bdrv_co_do_copy_on_readv(void *bs, int64_t offset, unsigned int bytes, int64_t cluster_offset, unsigned int cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %u" +bdrv_co_do_copy_on_readv(void *bs, int64_t offset, unsigned int bytes, int64_t cluster_offset, int64_t cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %"PRId64 # block/stream.c stream_one_iteration(void *s, int64_t offset, uint64_t bytes, int is_allocated) "s %p offset %" PRId64 " bytes %" PRIu64 " is_allocated %d" diff --git a/include/block/block.h b/include/block/block.h index d5c2731a03..440f3e9e39 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -474,9 +474,9 @@ int bdrv_get_flags(BlockDriverState *bs); int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi); ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs); void bdrv_round_to_clusters(BlockDriverState *bs, - int64_t offset, unsigned int bytes, + int64_t offset, int64_t bytes, int64_t *cluster_offset, - unsigned int *cluster_bytes); + int64_t *cluster_bytes); const char *bdrv_get_encrypted_filename(BlockDriverState *bs); void bdrv_get_backing_filename(BlockDriverState *bs, From f06f6b66c789c41165b46f98c88141b955cd594d Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:00 -0500 Subject: [PATCH 06/35] qcow2: Switch is_zero_sectors() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change), and rename it to is_zero() in the process. Signed-off-by: Eric Blake Reviewed-by: Fam Zheng Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- block/qcow2.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index 0e4c91cabc..795be673e7 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2972,21 +2972,29 @@ finish: } -static bool is_zero_sectors(BlockDriverState *bs, int64_t start, - uint32_t count) +static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { int nr; int64_t res; + int64_t start; - if (start + count > bs->total_sectors) { - count = bs->total_sectors - start; + /* TODO: Widening to sector boundaries should only be needed as + * long as we can't query finer granularity. */ + start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); + bytes = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE) - start; + + /* Clamp to image length, before checking status of underlying sectors */ + if (start + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { + bytes = bs->total_sectors * BDRV_SECTOR_SIZE - start; } - if (!count) { + if (!bytes) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start, count, &nr, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == count; + res = bdrv_get_block_status_above(bs, NULL, start >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &nr, NULL); + return res >= 0 && (res & BDRV_BLOCK_ZERO) && + nr * BDRV_SECTOR_SIZE == bytes; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, @@ -3004,24 +3012,21 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, } if (head || tail) { - int64_t cl_start = (offset - head) >> BDRV_SECTOR_BITS; uint64_t off; unsigned int nr; assert(head + bytes <= s->cluster_size); /* check whether remainder of cluster already reads as zero */ - if (!(is_zero_sectors(bs, cl_start, - DIV_ROUND_UP(head, BDRV_SECTOR_SIZE)) && - is_zero_sectors(bs, (offset + bytes) >> BDRV_SECTOR_BITS, - DIV_ROUND_UP(-tail & (s->cluster_size - 1), - BDRV_SECTOR_SIZE)))) { + if (!(is_zero(bs, offset - head, head) && + is_zero(bs, offset + bytes, + tail ? s->cluster_size - tail : 0))) { return -ENOTSUP; } qemu_co_mutex_lock(&s->lock); /* We can have new write after previous check */ - offset = cl_start << BDRV_SECTOR_BITS; + offset = QEMU_ALIGN_DOWN(offset, s->cluster_size); bytes = s->cluster_size; nr = s->cluster_size; ret = qcow2_get_cluster_offset(bs, offset, &nr, &off); From 7286d6106fd2c8f2646415c8e02438db3c21a46f Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:01 -0500 Subject: [PATCH 07/35] block: Switch bdrv_make_zero() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Change the internal loop iteration of zeroing a device to track by bytes instead of sectors (although we are still guaranteed that we iterate by steps that are sector-aligned). Signed-off-by: Eric Blake Reviewed-by: Fam Zheng Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- block/io.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index db8dc59c94..ad84d84888 100644 --- a/block/io.c +++ b/block/io.c @@ -716,38 +716,38 @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, */ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { - int64_t target_sectors, ret, nb_sectors, sector_num = 0; + int64_t target_size, ret, bytes, offset = 0; BlockDriverState *bs = child->bs; - int n; + int n; /* sectors */ - target_sectors = bdrv_nb_sectors(bs); - if (target_sectors < 0) { - return target_sectors; + target_size = bdrv_getlength(bs); + if (target_size < 0) { + return target_size; } for (;;) { - nb_sectors = MIN(target_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); - if (nb_sectors <= 0) { + bytes = MIN(target_size - offset, BDRV_REQUEST_MAX_BYTES); + if (bytes <= 0) { return 0; } - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, NULL); + ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &n, NULL); if (ret < 0) { - error_report("error getting block status at sector %" PRId64 ": %s", - sector_num, strerror(-ret)); + error_report("error getting block status at offset %" PRId64 ": %s", + offset, strerror(-ret)); return ret; } if (ret & BDRV_BLOCK_ZERO) { - sector_num += n; + offset += n * BDRV_SECTOR_BITS; continue; } - ret = bdrv_pwrite_zeroes(child, sector_num << BDRV_SECTOR_BITS, - n << BDRV_SECTOR_BITS, flags); + ret = bdrv_pwrite_zeroes(child, offset, n * BDRV_SECTOR_SIZE, flags); if (ret < 0) { - error_report("error writing zeroes at sector %" PRId64 ": %s", - sector_num, strerror(-ret)); + error_report("error writing zeroes at offset %" PRId64 ": %s", + offset, strerror(-ret)); return ret; } - sector_num += n; + offset += n * BDRV_SECTOR_SIZE; } } From 5e344dd8c2e4214f6515385de879ca7eb896902f Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:02 -0500 Subject: [PATCH 08/35] qemu-img: Switch get_block_status() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Continue by converting an internal function (no semantic change), and simplifying its caller accordingly. Signed-off-by: Eric Blake Reviewed-by: Fam Zheng Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index e9c7b30c91..af3effdec5 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -2671,14 +2671,16 @@ static void dump_map_entry(OutputFormat output_format, MapEntry *e, } } -static int get_block_status(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, MapEntry *e) +static int get_block_status(BlockDriverState *bs, int64_t offset, + int64_t bytes, MapEntry *e) { int64_t ret; int depth; BlockDriverState *file; bool has_offset; + int nb_sectors = bytes >> BDRV_SECTOR_BITS; + assert(bytes < INT_MAX); /* As an optimization, we could cache the current range of unallocated * clusters in each file of the chain, and avoid querying the same * range repeatedly. @@ -2686,8 +2688,8 @@ static int get_block_status(BlockDriverState *bs, int64_t sector_num, depth = 0; for (;;) { - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &nb_sectors, - &file); + ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, nb_sectors, + &nb_sectors, &file); if (ret < 0) { return ret; } @@ -2707,7 +2709,7 @@ static int get_block_status(BlockDriverState *bs, int64_t sector_num, has_offset = !!(ret & BDRV_BLOCK_OFFSET_VALID); *e = (MapEntry) { - .start = sector_num * BDRV_SECTOR_SIZE, + .start = offset, .length = nb_sectors * BDRV_SECTOR_SIZE, .data = !!(ret & BDRV_BLOCK_DATA), .zero = !!(ret & BDRV_BLOCK_ZERO), @@ -2837,16 +2839,12 @@ static int img_map(int argc, char **argv) length = blk_getlength(blk); while (curr.start + curr.length < length) { - int64_t nsectors_left; - int64_t sector_num; - int n; - - sector_num = (curr.start + curr.length) >> BDRV_SECTOR_BITS; + int64_t offset = curr.start + curr.length; + int64_t n; /* Probe up to 1 GiB at a time. */ - nsectors_left = DIV_ROUND_UP(length, BDRV_SECTOR_SIZE) - sector_num; - n = MIN(1 << (30 - BDRV_SECTOR_BITS), nsectors_left); - ret = get_block_status(bs, sector_num, n, &next); + n = QEMU_ALIGN_DOWN(MIN(1 << 30, length - offset), BDRV_SECTOR_SIZE); + ret = get_block_status(bs, offset, n, &next); if (ret < 0) { error_report("Could not read file metadata: %s", strerror(-ret)); From 237d78f8fc62e62f62246883ecf62e44ed35fb80 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:03 -0500 Subject: [PATCH 09/35] block: Convert bdrv_get_block_status() to bytes We are gradually moving away from sector-based interfaces, towards byte-based. In the common case, allocation is unlikely to ever use values that are not naturally sector-aligned, but it is possible that byte-based values will let us be more precise about allocation at the end of an unaligned file that can do byte-based access. Changing the name of the function from bdrv_get_block_status() to bdrv_block_status() ensures that the compiler enforces that all callers are updated. For now, the io.c layer still assert()s that all callers are sector-aligned, but that can be relaxed when a later patch implements byte-based block status in the drivers. There was an inherent limitation in returning the offset via the return value: we only have room for BDRV_BLOCK_OFFSET_MASK bits, which means an offset can only be mapped for sector-aligned queries (or, if we declare that non-aligned input is at the same relative position modulo 512 of the answer), so the new interface also changes things to return the offset via output through a parameter by reference rather than mashed into the return value. We'll have some glue code that munges between the two styles until we finish converting all uses. For the most part this patch is just the addition of scaling at the callers followed by inverse scaling at bdrv_block_status(), coupled with the tweak in calling convention. But some code, particularly bdrv_is_allocated(), gets a lot simpler because it no longer has to mess with sectors. For ease of review, bdrv_get_block_status_above() will be tackled separately. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 47 +++++++++++++++++++++++++++++++------------ block/qcow2-cluster.c | 2 +- include/block/block.h | 17 ++++++++-------- qemu-img.c | 25 +++++++++++++---------- 4 files changed, 58 insertions(+), 33 deletions(-) diff --git a/block/io.c b/block/io.c index ad84d84888..890d3c073b 100644 --- a/block/io.c +++ b/block/io.c @@ -716,9 +716,9 @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, */ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { - int64_t target_size, ret, bytes, offset = 0; + int ret; + int64_t target_size, bytes, offset = 0; BlockDriverState *bs = child->bs; - int n; /* sectors */ target_size = bdrv_getlength(bs); if (target_size < 0) { @@ -730,24 +730,23 @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) if (bytes <= 0) { return 0; } - ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &n, NULL); + ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL); if (ret < 0) { error_report("error getting block status at offset %" PRId64 ": %s", offset, strerror(-ret)); return ret; } if (ret & BDRV_BLOCK_ZERO) { - offset += n * BDRV_SECTOR_BITS; + offset += bytes; continue; } - ret = bdrv_pwrite_zeroes(child, offset, n * BDRV_SECTOR_SIZE, flags); + ret = bdrv_pwrite_zeroes(child, offset, bytes, flags); if (ret < 0) { error_report("error writing zeroes at offset %" PRId64 ": %s", offset, strerror(-ret)); return ret; } - offset += n * BDRV_SECTOR_SIZE; + offset += bytes; } } @@ -2045,13 +2044,35 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, nb_sectors, pnum, file); } -int64_t bdrv_get_block_status(BlockDriverState *bs, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, BlockDriverState **file) { - return bdrv_get_block_status_above(bs, backing_bs(bs), - sector_num, nb_sectors, pnum, file); + int64_t ret; + int n; + + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + assert(pnum); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); + ret = bdrv_get_block_status_above(bs, backing_bs(bs), + offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &n, file); + if (ret < 0) { + assert(INT_MIN <= ret); + *pnum = 0; + return ret; + } + *pnum = n * BDRV_SECTOR_SIZE; + if (map) { + *map = ret & BDRV_BLOCK_OFFSET_MASK; + } else { + ret &= ~BDRV_BLOCK_OFFSET_VALID; + } + return ret & ~BDRV_BLOCK_OFFSET_MASK; } int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 0e5aec81cb..fb10e26068 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -1632,7 +1632,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset, * cluster is already marked as zero, or if it's unallocated and we * don't have a backing file. * - * TODO We might want to use bdrv_get_block_status(bs) here, but we're + * TODO We might want to use bdrv_block_status(bs) here, but we're * holding s->lock, so that doesn't work today. * * If full_discard is true, the sector should not read back as zeroes, diff --git a/include/block/block.h b/include/block/block.h index 440f3e9e39..7ac851f82f 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -121,7 +121,7 @@ typedef struct HDGeometry { #define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) /* - * Allocation status flags for bdrv_get_block_status() and friends. + * Allocation status flags for bdrv_block_status() and friends. * * Public flags: * BDRV_BLOCK_DATA: allocation for data at offset is tied to this layer @@ -136,10 +136,11 @@ typedef struct HDGeometry { * that the block layer recompute the answer from the returned * BDS; must be accompanied by just BDRV_BLOCK_OFFSET_VALID. * - * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 (BDRV_BLOCK_OFFSET_MASK) - * represent the offset in the returned BDS that is allocated for the - * corresponding raw data; however, whether that offset actually contains - * data also depends on BDRV_BLOCK_DATA and BDRV_BLOCK_ZERO, as follows: + * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 (BDRV_BLOCK_OFFSET_MASK) of + * the return value (old interface) or the entire map parameter (new + * interface) represent the offset in the returned BDS that is allocated for + * the corresponding raw data. However, whether that offset actually + * contains data also depends on BDRV_BLOCK_DATA, as follows: * * DATA ZERO OFFSET_VALID * t t t sectors read as zero, returned file is zero at offset @@ -421,9 +422,9 @@ int bdrv_has_zero_init_1(BlockDriverState *bs); int bdrv_has_zero_init(BlockDriverState *bs); bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); -int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file); +int bdrv_block_status(BlockDriverState *bs, int64_t offset, + int64_t bytes, int64_t *pnum, int64_t *map, + BlockDriverState **file); int64_t bdrv_get_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t sector_num, diff --git a/qemu-img.c b/qemu-img.c index af3effdec5..c81d6ce733 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1599,9 +1599,14 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) if (s->sector_next_status <= sector_num) { if (s->target_has_backing) { - ret = bdrv_get_block_status(blk_bs(s->src[src_cur]), - sector_num - src_cur_offset, - n, &n, NULL); + int64_t count = n * BDRV_SECTOR_SIZE; + + ret = bdrv_block_status(blk_bs(s->src[src_cur]), + (sector_num - src_cur_offset) * + BDRV_SECTOR_SIZE, + count, &count, NULL, NULL); + assert(ret < 0 || QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); + n = count >> BDRV_SECTOR_BITS; } else { ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, sector_num - src_cur_offset, @@ -2674,13 +2679,12 @@ static void dump_map_entry(OutputFormat output_format, MapEntry *e, static int get_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, MapEntry *e) { - int64_t ret; + int ret; int depth; BlockDriverState *file; bool has_offset; - int nb_sectors = bytes >> BDRV_SECTOR_BITS; + int64_t map; - assert(bytes < INT_MAX); /* As an optimization, we could cache the current range of unallocated * clusters in each file of the chain, and avoid querying the same * range repeatedly. @@ -2688,12 +2692,11 @@ static int get_block_status(BlockDriverState *bs, int64_t offset, depth = 0; for (;;) { - ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, nb_sectors, - &nb_sectors, &file); + ret = bdrv_block_status(bs, offset, bytes, &bytes, &map, &file); if (ret < 0) { return ret; } - assert(nb_sectors); + assert(bytes); if (ret & (BDRV_BLOCK_ZERO|BDRV_BLOCK_DATA)) { break; } @@ -2710,10 +2713,10 @@ static int get_block_status(BlockDriverState *bs, int64_t offset, *e = (MapEntry) { .start = offset, - .length = nb_sectors * BDRV_SECTOR_SIZE, + .length = bytes, .data = !!(ret & BDRV_BLOCK_DATA), .zero = !!(ret & BDRV_BLOCK_ZERO), - .offset = ret & BDRV_BLOCK_OFFSET_MASK, + .offset = map, .has_offset = has_offset, .depth = depth, .has_filename = file && has_offset, From 2e8bc7874bb674b7d6837706b1249bf871941637 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:04 -0500 Subject: [PATCH 10/35] block: Switch bdrv_co_get_block_status() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change); and as with its public counterpart, rename to bdrv_co_block_status() and split the offset return, to make the compiler enforce that we catch all uses. For now, we assert that callers and the return value still use aligned data, but ultimately, this will be the function where we hand off to a byte-based driver callback, and will eventually need to add logic to ensure we round calls according to the driver's request_alignment then touch up the result handed back to the caller, to start permitting a caller to pass unaligned offsets. Note that we are now prepared to accepts 'bytes' larger than INT_MAX; this is okay as long as we clamp things internally before violating any 32-bit limits, and makes no difference to how a client will use the information (clients looping over the entire file must already be prepared for consecutive calls to return the same status, as drivers are already free to return shorter-than-maximal status due to any other convenient split points, such as when the L2 table crosses cluster boundaries in qcow2). Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 122 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 80 insertions(+), 42 deletions(-) diff --git a/block/io.c b/block/io.c index 890d3c073b..1c4dc4b1a1 100644 --- a/block/io.c +++ b/block/io.c @@ -1813,80 +1813,102 @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those * bits particularly if it allows for a larger value in 'pnum'. * - * If 'sector_num' is beyond the end of the disk image the return value is + * If 'offset' is beyond the end of the disk image the return value is * BDRV_BLOCK_EOF and 'pnum' is set to 0. * - * 'pnum' is set to the number of sectors (including and immediately following - * the specified sector) that are known to be in the same - * allocated/unallocated state. - * - * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes + * 'bytes' is the max value 'pnum' should be set to. If bytes goes * beyond the end of the disk image it will be clamped; if 'pnum' is set to * the end of the image, then the returned value will include BDRV_BLOCK_EOF. * - * If returned value is positive, BDRV_BLOCK_OFFSET_VALID bit is set, and - * 'file' is non-NULL, then '*file' points to the BDS which the sector range - * is allocated in. + * 'pnum' is set to the number of bytes (including and immediately + * following the specified offset) that are easily known to be in the + * same allocated/unallocated state. Note that a second call starting + * at the original offset plus returned pnum may have the same status. + * The returned value is non-zero on success except at end-of-file. + * + * Returns negative errno on failure. Otherwise, if the + * BDRV_BLOCK_OFFSET_VALID bit is set, 'map' and 'file' (if non-NULL) are + * set to the host mapping and BDS corresponding to the guest offset. */ -static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, - bool want_zero, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, + bool want_zero, + int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, + BlockDriverState **file) { - int64_t total_sectors; - int64_t n; - int64_t ret, ret2; + int64_t total_size; + int64_t n; /* bytes */ + int64_t ret; + int64_t local_map = 0; BlockDriverState *local_file = NULL; + int count; /* sectors */ assert(pnum); *pnum = 0; - total_sectors = bdrv_nb_sectors(bs); - if (total_sectors < 0) { - ret = total_sectors; + total_size = bdrv_getlength(bs); + if (total_size < 0) { + ret = total_size; goto early_out; } - if (sector_num >= total_sectors) { + if (offset >= total_size) { ret = BDRV_BLOCK_EOF; goto early_out; } - if (!nb_sectors) { + if (!bytes) { ret = 0; goto early_out; } - n = total_sectors - sector_num; - if (n < nb_sectors) { - nb_sectors = n; + n = total_size - offset; + if (n < bytes) { + bytes = n; } if (!bs->drv->bdrv_co_get_block_status) { - *pnum = nb_sectors; + *pnum = bytes; ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED; - if (sector_num + nb_sectors == total_sectors) { + if (offset + bytes == total_size) { ret |= BDRV_BLOCK_EOF; } if (bs->drv->protocol_name) { - ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); + ret |= BDRV_BLOCK_OFFSET_VALID; + local_map = offset; local_file = bs; } goto early_out; } bdrv_inc_in_flight(bs); - ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum, + /* + * TODO: Rather than require aligned offsets, we could instead + * round to the driver's request_alignment here, then touch up + * count afterwards back to the caller's expectations. + */ + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); + ret = bs->drv->bdrv_co_get_block_status(bs, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &count, &local_file); if (ret < 0) { - *pnum = 0; goto out; } + if (ret & BDRV_BLOCK_OFFSET_VALID) { + local_map = ret & BDRV_BLOCK_OFFSET_MASK; + } + *pnum = count * BDRV_SECTOR_SIZE; if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); - ret = bdrv_co_get_block_status(local_file, want_zero, - ret >> BDRV_SECTOR_BITS, - *pnum, pnum, &local_file); + ret = bdrv_co_block_status(local_file, want_zero, local_map, + *pnum, pnum, &local_map, &local_file); + assert(ret < 0 || + QEMU_IS_ALIGNED(*pnum | local_map, BDRV_SECTOR_SIZE)); goto out; } @@ -1897,9 +1919,9 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, ret |= BDRV_BLOCK_ZERO; } else if (bs->backing) { BlockDriverState *bs2 = bs->backing->bs; - int64_t nb_sectors2 = bdrv_nb_sectors(bs2); + int64_t size2 = bdrv_getlength(bs2); - if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) { + if (size2 >= 0 && offset >= size2) { ret |= BDRV_BLOCK_ZERO; } } @@ -1908,11 +1930,11 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, if (want_zero && local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { - int file_pnum; + int64_t file_pnum; + int ret2; - ret2 = bdrv_co_get_block_status(local_file, want_zero, - ret >> BDRV_SECTOR_BITS, - *pnum, &file_pnum, NULL); + ret2 = bdrv_co_block_status(local_file, want_zero, local_map, + *pnum, &file_pnum, NULL, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it * is useful but not necessary. @@ -1935,13 +1957,21 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, out: bdrv_dec_in_flight(bs); - if (ret >= 0 && sector_num + *pnum == total_sectors) { + if (ret >= 0 && offset + *pnum == total_size) { ret |= BDRV_BLOCK_EOF; } early_out: if (file) { *file = local_file; } + if (map) { + *map = local_map; + } + if (ret >= 0) { + ret &= ~BDRV_BLOCK_OFFSET_MASK; + } else { + assert(INT_MIN <= ret); + } return ret; } @@ -1956,14 +1986,22 @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t ret = 0; bool first = true; + int64_t map = 0; assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - ret = bdrv_co_get_block_status(p, want_zero, sector_num, nb_sectors, - pnum, file); + int64_t count; + + ret = bdrv_co_block_status(p, want_zero, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, &count, + &map, file); if (ret < 0) { break; } + assert(QEMU_IS_ALIGNED(count | map, BDRV_SECTOR_SIZE)); + ret |= map; + *pnum = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { /* * Reading beyond the end of the file continues to read From 4bcd936e47c45ebf7236b0414982dd625a957410 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:05 -0500 Subject: [PATCH 11/35] block: Switch BdrvCoGetBlockStatusData to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal type (no semantic change), and rename it to match the corresponding public function rename. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 56 ++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 18 deletions(-) diff --git a/block/io.c b/block/io.c index 1c4dc4b1a1..71d5f18d04 100644 --- a/block/io.c +++ b/block/io.c @@ -1765,17 +1765,18 @@ int bdrv_flush_all(void) } -typedef struct BdrvCoGetBlockStatusData { +typedef struct BdrvCoBlockStatusData { BlockDriverState *bs; BlockDriverState *base; bool want_zero; - int64_t sector_num; - int nb_sectors; - int *pnum; + int64_t offset; + int64_t bytes; + int64_t *pnum; + int64_t *map; BlockDriverState **file; - int64_t ret; + int ret; bool done; -} BdrvCoGetBlockStatusData; +} BdrvCoBlockStatusData; int64_t coroutine_fn bdrv_co_get_block_status_from_file(BlockDriverState *bs, int64_t sector_num, @@ -2025,14 +2026,24 @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, /* Coroutine wrapper for bdrv_get_block_status_above() */ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) { - BdrvCoGetBlockStatusData *data = opaque; + BdrvCoBlockStatusData *data = opaque; + int n = 0; + int64_t ret; - data->ret = bdrv_co_get_block_status_above(data->bs, data->base, - data->want_zero, - data->sector_num, - data->nb_sectors, - data->pnum, - data->file); + ret = bdrv_co_get_block_status_above(data->bs, data->base, + data->want_zero, + data->offset >> BDRV_SECTOR_BITS, + data->bytes >> BDRV_SECTOR_BITS, + &n, + data->file); + if (ret < 0) { + assert(INT_MIN <= ret); + data->ret = ret; + } else { + *data->pnum = n * BDRV_SECTOR_SIZE; + *data->map = ret & BDRV_BLOCK_OFFSET_MASK; + data->ret = ret & ~BDRV_BLOCK_OFFSET_MASK; + } data->done = true; } @@ -2049,13 +2060,16 @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState **file) { Coroutine *co; - BdrvCoGetBlockStatusData data = { + int64_t n; + int64_t map; + BdrvCoBlockStatusData data = { .bs = bs, .base = base, .want_zero = want_zero, - .sector_num = sector_num, - .nb_sectors = nb_sectors, - .pnum = pnum, + .offset = sector_num * BDRV_SECTOR_SIZE, + .bytes = nb_sectors * BDRV_SECTOR_SIZE, + .pnum = &n, + .map = &map, .file = file, .done = false, }; @@ -2069,7 +2083,13 @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } - return data.ret; + if (data.ret < 0) { + *pnum = 0; + return data.ret; + } + assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); + *pnum = n >> BDRV_SECTOR_BITS; + return data.ret | map; } int64_t bdrv_get_block_status_above(BlockDriverState *bs, From 7ddb99b9dc454a5ed9821c97d3066f358a7a73ae Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:06 -0500 Subject: [PATCH 12/35] block: Switch bdrv_common_block_status_above() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change). Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 61 +++++++++++++++++++++++++++--------------------------- 1 file changed, 30 insertions(+), 31 deletions(-) diff --git a/block/io.c b/block/io.c index 71d5f18d04..3a9a4c5db9 100644 --- a/block/io.c +++ b/block/io.c @@ -2052,24 +2052,22 @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) * * See bdrv_co_get_block_status_above() for details. */ -static int64_t bdrv_common_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - bool want_zero, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +static int bdrv_common_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, int64_t offset, + int64_t bytes, int64_t *pnum, + int64_t *map, + BlockDriverState **file) { Coroutine *co; - int64_t n; - int64_t map; BdrvCoBlockStatusData data = { .bs = bs, .base = base, .want_zero = want_zero, - .offset = sector_num * BDRV_SECTOR_SIZE, - .bytes = nb_sectors * BDRV_SECTOR_SIZE, - .pnum = &n, - .map = &map, + .offset = offset, + .bytes = bytes, + .pnum = pnum, + .map = map, .file = file, .done = false, }; @@ -2083,13 +2081,7 @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } - if (data.ret < 0) { - *pnum = 0; - return data.ret; - } - assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); - *pnum = n >> BDRV_SECTOR_BITS; - return data.ret | map; + return data.ret; } int64_t bdrv_get_block_status_above(BlockDriverState *bs, @@ -2098,8 +2090,21 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, int nb_sectors, int *pnum, BlockDriverState **file) { - return bdrv_common_block_status_above(bs, base, true, sector_num, - nb_sectors, pnum, file); + int64_t ret; + int64_t n; + int64_t map; + + ret = bdrv_common_block_status_above(bs, base, true, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, + &n, &map, file); + if (ret < 0) { + *pnum = 0; + return ret; + } + assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); + *pnum = n >> BDRV_SECTOR_BITS; + return ret | map; } int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, @@ -2136,21 +2141,15 @@ int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - int64_t ret; - int psectors; + int ret; + int64_t dummy; - assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); - ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, - offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &psectors, + ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, offset, + bytes, pnum ? pnum : &dummy, NULL, NULL); if (ret < 0) { return ret; } - if (pnum) { - *pnum = psectors * BDRV_SECTOR_SIZE; - } return !!(ret & BDRV_BLOCK_ALLOCATED); } From 5b648c67e3acea3e0136d0bb1bd47341996e0e4e Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:07 -0500 Subject: [PATCH 13/35] block: Switch bdrv_co_get_block_status_above() to byte-based We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal type (no semantic change), and rename it to match the corresponding public function rename. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 68 +++++++++++++++++++----------------------------------- 1 file changed, 24 insertions(+), 44 deletions(-) diff --git a/block/io.c b/block/io.c index 3a9a4c5db9..61b3477cd1 100644 --- a/block/io.c +++ b/block/io.c @@ -1976,33 +1976,26 @@ early_out: return ret; } -static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - bool want_zero, - int64_t sector_num, - int nb_sectors, - int *pnum, - BlockDriverState **file) +static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, + int64_t offset, + int64_t bytes, + int64_t *pnum, + int64_t *map, + BlockDriverState **file) { BlockDriverState *p; - int64_t ret = 0; + int ret = 0; bool first = true; - int64_t map = 0; assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - int64_t count; - - ret = bdrv_co_block_status(p, want_zero, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, &count, - &map, file); + ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, + file); if (ret < 0) { break; } - assert(QEMU_IS_ALIGNED(count | map, BDRV_SECTOR_SIZE)); - ret |= map; - *pnum = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { /* * Reading beyond the end of the file continues to read @@ -2010,47 +2003,35 @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, * unallocated length we learned from an earlier * iteration. */ - *pnum = nb_sectors; + *pnum = bytes; } if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { break; } - /* [sector_num, pnum] unallocated on this layer, which could be only - * the first part of [sector_num, nb_sectors]. */ - nb_sectors = MIN(nb_sectors, *pnum); + /* [offset, pnum] unallocated on this layer, which could be only + * the first part of [offset, bytes]. */ + bytes = MIN(bytes, *pnum); first = false; } return ret; } /* Coroutine wrapper for bdrv_get_block_status_above() */ -static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) +static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque) { BdrvCoBlockStatusData *data = opaque; - int n = 0; - int64_t ret; - ret = bdrv_co_get_block_status_above(data->bs, data->base, - data->want_zero, - data->offset >> BDRV_SECTOR_BITS, - data->bytes >> BDRV_SECTOR_BITS, - &n, - data->file); - if (ret < 0) { - assert(INT_MIN <= ret); - data->ret = ret; - } else { - *data->pnum = n * BDRV_SECTOR_SIZE; - *data->map = ret & BDRV_BLOCK_OFFSET_MASK; - data->ret = ret & ~BDRV_BLOCK_OFFSET_MASK; - } + data->ret = bdrv_co_block_status_above(data->bs, data->base, + data->want_zero, + data->offset, data->bytes, + data->pnum, data->map, data->file); data->done = true; } /* - * Synchronous wrapper around bdrv_co_get_block_status_above(). + * Synchronous wrapper around bdrv_co_block_status_above(). * - * See bdrv_co_get_block_status_above() for details. + * See bdrv_co_block_status_above() for details. */ static int bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, @@ -2074,10 +2055,9 @@ static int bdrv_common_block_status_above(BlockDriverState *bs, if (qemu_in_coroutine()) { /* Fast-path if already in coroutine context */ - bdrv_get_block_status_above_co_entry(&data); + bdrv_block_status_above_co_entry(&data); } else { - co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry, - &data); + co = qemu_coroutine_create(bdrv_block_status_above_co_entry, &data); bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } From 3182664220571d11d4fe03ecdc10fcc1e842ed32 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:08 -0500 Subject: [PATCH 14/35] block: Convert bdrv_get_block_status_above() to bytes We are gradually moving away from sector-based interfaces, towards byte-based. In the common case, allocation is unlikely to ever use values that are not naturally sector-aligned, but it is possible that byte-based values will let us be more precise about allocation at the end of an unaligned file that can do byte-based access. Changing the name of the function from bdrv_get_block_status_above() to bdrv_block_status_above() ensures that the compiler enforces that all callers are updated. Likewise, since it a byte interface allows an offset mapping that might not be sector aligned, split the mapping out of the return value and into a pass-by-reference parameter. For now, the io.c layer still assert()s that all uses are sector-aligned, but that can be relaxed when a later patch implements byte-based block status in the drivers. For the most part this patch is just the addition of scaling at the callers followed by inverse scaling at bdrv_block_status(), plus updates for the new split return interface. But some code, particularly bdrv_block_status(), gets a lot simpler because it no longer has to mess with sectors. Likewise, mirror code no longer computes s->granularity >> BDRV_SECTOR_BITS, and can therefore drop an assertion about alignment because the loop no longer depends on alignment (never mind that we don't really have a driver that reports sub-sector alignments, so it's not really possible to test the effect of sub-sector mirroring). Fix a neighboring assertion to use is_power_of_2 while there. For ease of review, bdrv_get_block_status() was tackled separately. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/io.c | 55 +++++++------------------------------------ block/mirror.c | 18 +++++--------- block/qcow2.c | 30 ++++++++++------------- include/block/block.h | 8 +++---- qemu-img.c | 49 +++++++++++++++++++++----------------- 5 files changed, 57 insertions(+), 103 deletions(-) diff --git a/block/io.c b/block/io.c index 61b3477cd1..e64b1cb294 100644 --- a/block/io.c +++ b/block/io.c @@ -2016,7 +2016,7 @@ static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, return ret; } -/* Coroutine wrapper for bdrv_get_block_status_above() */ +/* Coroutine wrapper for bdrv_block_status_above() */ static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque) { BdrvCoBlockStatusData *data = opaque; @@ -2064,58 +2064,19 @@ static int bdrv_common_block_status_above(BlockDriverState *bs, return data.ret; } -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, + int64_t offset, int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file) { - int64_t ret; - int64_t n; - int64_t map; - - ret = bdrv_common_block_status_above(bs, base, true, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, - &n, &map, file); - if (ret < 0) { - *pnum = 0; - return ret; - } - assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); - *pnum = n >> BDRV_SECTOR_BITS; - return ret | map; + return bdrv_common_block_status_above(bs, base, true, offset, bytes, + pnum, map, file); } int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) { - int64_t ret; - int n; - - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - assert(pnum); - /* - * The contract allows us to return pnum smaller than bytes, even - * if the next query would see the same status; we truncate the - * request to avoid overflowing the driver's 32-bit interface. - */ - bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); - ret = bdrv_get_block_status_above(bs, backing_bs(bs), - offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &n, file); - if (ret < 0) { - assert(INT_MIN <= ret); - *pnum = 0; - return ret; - } - *pnum = n * BDRV_SECTOR_SIZE; - if (map) { - *map = ret & BDRV_BLOCK_OFFSET_MASK; - } else { - ret &= ~BDRV_BLOCK_OFFSET_VALID; - } - return ret & ~BDRV_BLOCK_OFFSET_MASK; + return bdrv_block_status_above(bs, backing_bs(bs), + offset, bytes, pnum, map, file); } int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, diff --git a/block/mirror.c b/block/mirror.c index d11706c566..307b6391a8 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -328,7 +328,6 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) uint64_t delay_ns = 0; /* At least the first dirty chunk is mirrored in one iteration. */ int nb_chunks = 1; - int sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS; bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target)); int max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES); @@ -376,7 +375,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) } /* Clear dirty bits before querying the block status, because - * calling bdrv_get_block_status_above could yield - if some blocks are + * calling bdrv_block_status_above could yield - if some blocks are * marked dirty in this window, we need to know. */ bdrv_reset_dirty_bitmap_locked(s->dirty_bitmap, offset, @@ -385,8 +384,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) bitmap_set(s->in_flight_bitmap, offset / s->granularity, nb_chunks); while (nb_chunks > 0 && offset < s->bdev_length) { - int64_t ret; - int io_sectors; + int ret; int64_t io_bytes; int64_t io_bytes_acct; enum MirrorMethod { @@ -396,11 +394,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) } mirror_method = MIRROR_METHOD_COPY; assert(!(offset % s->granularity)); - ret = bdrv_get_block_status_above(source, NULL, - offset >> BDRV_SECTOR_BITS, - nb_chunks * sectors_per_chunk, - &io_sectors, NULL); - io_bytes = io_sectors * BDRV_SECTOR_SIZE; + ret = bdrv_block_status_above(source, NULL, offset, + nb_chunks * s->granularity, + &io_bytes, NULL, NULL); if (ret < 0) { io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes); } else if (ret & BDRV_BLOCK_DATA) { @@ -1131,9 +1127,7 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs, granularity = bdrv_get_default_bitmap_granularity(target); } - assert ((granularity & (granularity - 1)) == 0); - /* Granularity must be large enough for sector-based dirty bitmap */ - assert(granularity >= BDRV_SECTOR_SIZE); + assert(is_power_of_2(granularity)); if (buf_size < 0) { error_setg(errp, "Invalid parameter 'buf-size'"); diff --git a/block/qcow2.c b/block/qcow2.c index 795be673e7..29d0a50955 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2974,8 +2974,8 @@ finish: static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { - int nr; - int64_t res; + int64_t nr; + int res; int64_t start; /* TODO: Widening to sector boundaries should only be needed as @@ -2991,10 +2991,8 @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) if (!bytes) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &nr, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && - nr * BDRV_SECTOR_SIZE == bytes; + res = bdrv_block_status_above(bs, NULL, start, bytes, &nr, NULL, NULL); + return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, @@ -3700,17 +3698,14 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, required = virtual_size; } else { int64_t offset; - int pnum = 0; + int64_t pnum = 0; - for (offset = 0; offset < ssize; - offset += pnum * BDRV_SECTOR_SIZE) { - int nb_sectors = MIN(ssize - offset, - BDRV_REQUEST_MAX_BYTES) / BDRV_SECTOR_SIZE; - int64_t ret; + for (offset = 0; offset < ssize; offset += pnum) { + int ret; - ret = bdrv_get_block_status_above(in_bs, NULL, - offset >> BDRV_SECTOR_BITS, - nb_sectors, &pnum, NULL); + ret = bdrv_block_status_above(in_bs, NULL, offset, + ssize - offset, &pnum, NULL, + NULL); if (ret < 0) { error_setg_errno(&local_err, -ret, "Unable to get block status"); @@ -3722,11 +3717,10 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, } else if ((ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED)) == (BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED)) { /* Extend pnum to end of cluster for next iteration */ - pnum = (ROUND_UP(offset + pnum * BDRV_SECTOR_SIZE, - cluster_size) - offset) >> BDRV_SECTOR_BITS; + pnum = ROUND_UP(offset + pnum, cluster_size) - offset; /* Count clusters we've seen */ - required += offset % cluster_size + pnum * BDRV_SECTOR_SIZE; + required += offset % cluster_size + pnum; } } } diff --git a/include/block/block.h b/include/block/block.h index 7ac851f82f..fbc21daf62 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -425,11 +425,9 @@ bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file); +int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, + int64_t offset, int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file); int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum); int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, diff --git a/qemu-img.c b/qemu-img.c index c81d6ce733..78c820e487 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1226,7 +1226,7 @@ static int img_compare(int argc, char **argv) BlockDriverState *bs1, *bs2; int64_t total_sectors1, total_sectors2; uint8_t *buf1 = NULL, *buf2 = NULL; - int pnum1, pnum2; + int64_t pnum1, pnum2; int allocated1, allocated2; int ret = 0; /* return value - 0 Ident, 1 Different, >1 Error */ bool progress = false, quiet = false, strict = false; @@ -1374,15 +1374,17 @@ static int img_compare(int argc, char **argv) } for (;;) { - int64_t status1, status2; + int status1, status2; nb_sectors = sectors_to_process(total_sectors, sector_num); if (nb_sectors <= 0) { break; } - status1 = bdrv_get_block_status_above(bs1, NULL, sector_num, - total_sectors1 - sector_num, - &pnum1, NULL); + status1 = bdrv_block_status_above(bs1, NULL, + sector_num * BDRV_SECTOR_SIZE, + (total_sectors1 - sector_num) * + BDRV_SECTOR_SIZE, + &pnum1, NULL, NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -1390,25 +1392,29 @@ static int img_compare(int argc, char **argv) } allocated1 = status1 & BDRV_BLOCK_ALLOCATED; - status2 = bdrv_get_block_status_above(bs2, NULL, sector_num, - total_sectors2 - sector_num, - &pnum2, NULL); + status2 = bdrv_block_status_above(bs2, NULL, + sector_num * BDRV_SECTOR_SIZE, + (total_sectors2 - sector_num) * + BDRV_SECTOR_SIZE, + &pnum2, NULL, NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); goto out; } allocated2 = status2 & BDRV_BLOCK_ALLOCATED; + /* TODO: Relax this once comparison is byte-based, and we no longer + * have to worry about sector alignment */ + assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); if (pnum1) { - nb_sectors = MIN(nb_sectors, pnum1); + nb_sectors = MIN(nb_sectors, pnum1 >> BDRV_SECTOR_BITS); } if (pnum2) { - nb_sectors = MIN(nb_sectors, pnum2); + nb_sectors = MIN(nb_sectors, pnum2 >> BDRV_SECTOR_BITS); } if (strict) { - if ((status1 & ~BDRV_BLOCK_OFFSET_MASK) != - (status2 & ~BDRV_BLOCK_OFFSET_MASK)) { + if (status1 != status2) { ret = 1; qprintf(quiet, "Strict mode: Offset %" PRId64 " block status mismatch!\n", @@ -1417,7 +1423,7 @@ static int img_compare(int argc, char **argv) } } if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) { - nb_sectors = MIN(pnum1, pnum2); + nb_sectors = DIV_ROUND_UP(MIN(pnum1, pnum2), BDRV_SECTOR_SIZE); } else if (allocated1 == allocated2) { if (allocated1) { ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, @@ -1589,8 +1595,8 @@ static void convert_select_part(ImgConvertState *s, int64_t sector_num, static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) { - int64_t ret, src_cur_offset; - int n, src_cur; + int64_t src_cur_offset; + int ret, n, src_cur; convert_select_part(s, sector_num, &src_cur, &src_cur_offset); @@ -1598,23 +1604,24 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); if (s->sector_next_status <= sector_num) { + int64_t count = n * BDRV_SECTOR_SIZE; + if (s->target_has_backing) { - int64_t count = n * BDRV_SECTOR_SIZE; ret = bdrv_block_status(blk_bs(s->src[src_cur]), (sector_num - src_cur_offset) * BDRV_SECTOR_SIZE, count, &count, NULL, NULL); - assert(ret < 0 || QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - n = count >> BDRV_SECTOR_BITS; } else { - ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, - sector_num - src_cur_offset, - n, &n, NULL); + ret = bdrv_block_status_above(blk_bs(s->src[src_cur]), NULL, + (sector_num - src_cur_offset) * + BDRV_SECTOR_SIZE, + count, &count, NULL, NULL); } if (ret < 0) { return ret; } + n = DIV_ROUND_UP(count, BDRV_SECTOR_SIZE); if (ret & BDRV_BLOCK_ZERO) { s->status = BLK_ZERO; From 7daddc615e694ede5dd75366e8a0407f2404ccd8 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:09 -0500 Subject: [PATCH 15/35] qemu-img: Simplify logic in img_compare() As long as we are querying the status for a chunk smaller than the known image size, we are guaranteed that a successful return will have set pnum to a non-zero size (pnum is zero only for queries beyond the end of the file). Use that to slightly simplify the calculation of the current chunk size being compared. Likewise, we don't have to shrink the amount of data operated on until we know we have to read the file, and therefore have to fit in the bounds of our buffer. Also, note that 'total_sectors_over' is equivalent to 'progress_base'. With these changes in place, sectors_to_process() is now dead code, and can be removed. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- qemu-img.c | 38 +++++++++++--------------------------- 1 file changed, 11 insertions(+), 27 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index 78c820e487..cfa28d41d5 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1172,11 +1172,6 @@ static int64_t sectors_to_bytes(int64_t sectors) return sectors << BDRV_SECTOR_BITS; } -static int64_t sectors_to_process(int64_t total, int64_t from) -{ - return MIN(total - from, IO_BUF_SIZE >> BDRV_SECTOR_BITS); -} - /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * @@ -1373,13 +1368,9 @@ static int img_compare(int argc, char **argv) goto out; } - for (;;) { + while (sector_num < total_sectors) { int status1, status2; - nb_sectors = sectors_to_process(total_sectors, sector_num); - if (nb_sectors <= 0) { - break; - } status1 = bdrv_block_status_above(bs1, NULL, sector_num * BDRV_SECTOR_SIZE, (total_sectors1 - sector_num) * @@ -1406,12 +1397,9 @@ static int img_compare(int argc, char **argv) /* TODO: Relax this once comparison is byte-based, and we no longer * have to worry about sector alignment */ assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); - if (pnum1) { - nb_sectors = MIN(nb_sectors, pnum1 >> BDRV_SECTOR_BITS); - } - if (pnum2) { - nb_sectors = MIN(nb_sectors, pnum2 >> BDRV_SECTOR_BITS); - } + + assert(pnum1 && pnum2); + nb_sectors = MIN(pnum1, pnum2) >> BDRV_SECTOR_BITS; if (strict) { if (status1 != status2) { @@ -1423,9 +1411,10 @@ static int img_compare(int argc, char **argv) } } if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) { - nb_sectors = DIV_ROUND_UP(MIN(pnum1, pnum2), BDRV_SECTOR_SIZE); + /* nothing to do */ } else if (allocated1 == allocated2) { if (allocated1) { + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, nb_sectors << BDRV_SECTOR_BITS); if (ret < 0) { @@ -1454,7 +1443,7 @@ static int img_compare(int argc, char **argv) } } } else { - + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); if (allocated1) { ret = check_empty_sectors(blk1, sector_num, nb_sectors, filename1, buf1, quiet); @@ -1477,30 +1466,24 @@ static int img_compare(int argc, char **argv) if (total_sectors1 != total_sectors2) { BlockBackend *blk_over; - int64_t total_sectors_over; const char *filename_over; qprintf(quiet, "Warning: Image size mismatch!\n"); if (total_sectors1 > total_sectors2) { - total_sectors_over = total_sectors1; blk_over = blk1; filename_over = filename1; } else { - total_sectors_over = total_sectors2; blk_over = blk2; filename_over = filename2; } - for (;;) { + while (sector_num < progress_base) { int64_t count; - nb_sectors = sectors_to_process(total_sectors_over, sector_num); - if (nb_sectors <= 0) { - break; - } ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + (progress_base - sector_num) * + BDRV_SECTOR_SIZE, &count); if (ret < 0) { ret = 3; @@ -1514,6 +1497,7 @@ static int img_compare(int argc, char **argv) assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); nb_sectors = count >> BDRV_SECTOR_BITS; if (ret) { + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); if (ret) { From 391cb1aacad155bea4270b863710bba9adabe311 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:10 -0500 Subject: [PATCH 16/35] qemu-img: Speed up compare on pre-allocated larger file Compare the following images with all-zero contents: $ truncate --size 1M A $ qemu-img create -f qcow2 -o preallocation=off B 1G $ qemu-img create -f qcow2 -o preallocation=metadata C 1G On my machine, the difference is noticeable for pre-patch speeds, with more than an order of magnitude in difference caused by the choice of preallocation in the qcow2 file: $ time ./qemu-img compare -f raw -F qcow2 A B Warning: Image size mismatch! Images are identical. real 0m0.014s user 0m0.007s sys 0m0.007s $ time ./qemu-img compare -f raw -F qcow2 A C Warning: Image size mismatch! Images are identical. real 0m0.341s user 0m0.144s sys 0m0.188s Why? Because bdrv_is_allocated() returns false for image B but true for image C, throwing away the fact that both images know via lseek(SEEK_HOLE) that the entire image still reads as zero. From there, qemu-img ends up calling bdrv_pread() for every byte of the tail, instead of quickly looking for the next allocation. The solution: use block_status instead of is_allocated, giving: $ time ./qemu-img compare -f raw -F qcow2 A C Warning: Image size mismatch! Images are identical. real 0m0.014s user 0m0.011s sys 0m0.003s which is on par with the speeds for no pre-allocation. Signed-off-by: Eric Blake Reviewed-by: John Snow Reviewed-by: Vladimir Sementsov-Ogievskiy Signed-off-by: Kevin Wolf --- qemu-img.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index cfa28d41d5..e4b84c4f56 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1480,11 +1480,11 @@ static int img_compare(int argc, char **argv) while (sector_num < progress_base) { int64_t count; - ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, + ret = bdrv_block_status_above(blk_bs(blk_over), NULL, sector_num * BDRV_SECTOR_SIZE, (progress_base - sector_num) * BDRV_SECTOR_SIZE, - &count); + &count, NULL, NULL); if (ret < 0) { ret = 3; error_report("Sector allocation test failed for %s", @@ -1492,11 +1492,11 @@ static int img_compare(int argc, char **argv) goto out; } - /* TODO relax this once bdrv_is_allocated_above does not enforce + /* TODO relax this once bdrv_block_status_above does not enforce * sector alignment */ assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); nb_sectors = count >> BDRV_SECTOR_BITS; - if (ret) { + if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); From debb38a4cec34709604a00e23368e6cd8932fe3d Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:11 -0500 Subject: [PATCH 17/35] qemu-img: Add find_nonzero() During 'qemu-img compare', when we are checking that an allocated portion of one file is all zeros, we don't need to waste time computing how many additional sectors after the first non-zero byte are also non-zero. Create a new helper find_nonzero() to do the check for a first non-zero sector, and rebase check_empty_sectors() to use it. The new interface intentionally uses bytes in its interface, even though it still crawls the buffer a sector at a time; it is robust to a partial sector at the end of the buffer. Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index e4b84c4f56..89f1093d81 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1064,6 +1064,28 @@ done: return 0; } +/* + * Returns -1 if 'buf' contains only zeroes, otherwise the byte index + * of the first sector boundary within buf where the sector contains a + * non-zero byte. This function is robust to a buffer that is not + * sector-aligned. + */ +static int64_t find_nonzero(const uint8_t *buf, int64_t n) +{ + int64_t i; + int64_t end = QEMU_ALIGN_DOWN(n, BDRV_SECTOR_SIZE); + + for (i = 0; i < end; i += BDRV_SECTOR_SIZE) { + if (!buffer_is_zero(buf + i, BDRV_SECTOR_SIZE)) { + return i; + } + } + if (i < n && !buffer_is_zero(buf + i, n - end)) { + return i; + } + return -1; +} + /* * Returns true iff the first sector pointed to by 'buf' contains at least * a non-NUL byte. @@ -1189,7 +1211,9 @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, int sect_count, const char *filename, uint8_t *buffer, bool quiet) { - int pnum, ret = 0; + int ret = 0; + int64_t idx; + ret = blk_pread(blk, sect_num << BDRV_SECTOR_BITS, buffer, sect_count << BDRV_SECTOR_BITS); if (ret < 0) { @@ -1197,10 +1221,10 @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, sectors_to_bytes(sect_num), filename, strerror(-ret)); return ret; } - ret = is_allocated_sectors(buffer, sect_count, &pnum); - if (ret || pnum != sect_count) { + idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); + if (idx >= 0) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(ret ? sect_num : sect_num + pnum)); + sectors_to_bytes(sect_num) + idx); return 1; } From 0608e40e8e1934b22a3d218cf04abc4eb108c493 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:12 -0500 Subject: [PATCH 18/35] qemu-img: Drop redundant error message in compare If a read error is encountered during 'qemu-img compare', we were printing the "Error while reading offset ..." message twice; this was because our helper function was awkward, printing output on some but not all paths. Fix it to consistently report errors on all paths, so that the callers do not risk a redundant message, and update the testsuite for the improved output. Further simplify the code by hoisting the conversion from an error message to an exit code into the helper function, rather than repeating that logic at all callers (yes, the helper function is now less generic, but it's a net win in lines of code). Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 19 +++++-------------- tests/qemu-iotests/074.out | 2 -- 2 files changed, 5 insertions(+), 16 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index 89f1093d81..53cae6bb66 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1197,8 +1197,10 @@ static int64_t sectors_to_bytes(int64_t sectors) /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * - * Returns 0 in case sectors are filled with 0, 1 if sectors contain non-zero - * data and negative value on error. + * Intended for use by 'qemu-img compare': Returns 0 in case sectors are + * filled with 0, 1 if sectors contain non-zero data (this is a comparison + * failure), and 4 on error (the exit status for read errors), after emitting + * an error message. * * @param blk: BlockBackend for the image * @param sect_num: Number of first sector to check @@ -1219,7 +1221,7 @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", sectors_to_bytes(sect_num), filename, strerror(-ret)); - return ret; + return 4; } idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); if (idx >= 0) { @@ -1476,11 +1478,6 @@ static int img_compare(int argc, char **argv) filename2, buf1, quiet); } if (ret) { - if (ret < 0) { - error_report("Error while reading offset %" PRId64 ": %s", - sectors_to_bytes(sector_num), strerror(-ret)); - ret = 4; - } goto out; } } @@ -1525,12 +1522,6 @@ static int img_compare(int argc, char **argv) ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); if (ret) { - if (ret < 0) { - error_report("Error while reading offset %" PRId64 - " of %s: %s", sectors_to_bytes(sector_num), - filename_over, strerror(-ret)); - ret = 4; - } goto out; } } diff --git a/tests/qemu-iotests/074.out b/tests/qemu-iotests/074.out index 8fba5aea9c..ede66c3f81 100644 --- a/tests/qemu-iotests/074.out +++ b/tests/qemu-iotests/074.out @@ -4,7 +4,6 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 wrote 512/512 bytes at offset 512 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error -qemu-img: Error while reading offset 0: Input/output error 4 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=0 @@ -12,7 +11,6 @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=0 wrote 512/512 bytes at offset 512 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error -qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error Warning: Image size mismatch! 4 Cleanup From c41508edc68aefb784c3b750bbbff472eca1a3c5 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:13 -0500 Subject: [PATCH 19/35] qemu-img: Change check_empty_sectors() to byte-based Continue on the quest to make more things byte-based instead of sector-based. Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index 53cae6bb66..66d595be3d 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1203,30 +1203,29 @@ static int64_t sectors_to_bytes(int64_t sectors) * an error message. * * @param blk: BlockBackend for the image - * @param sect_num: Number of first sector to check - * @param sect_count: Number of sectors to check + * @param offset: Starting offset to check + * @param bytes: Number of bytes to check * @param filename: Name of disk file we are checking (logging purpose) * @param buffer: Allocated buffer for storing read data * @param quiet: Flag for quiet mode */ -static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, - int sect_count, const char *filename, +static int check_empty_sectors(BlockBackend *blk, int64_t offset, + int64_t bytes, const char *filename, uint8_t *buffer, bool quiet) { int ret = 0; int64_t idx; - ret = blk_pread(blk, sect_num << BDRV_SECTOR_BITS, buffer, - sect_count << BDRV_SECTOR_BITS); + ret = blk_pread(blk, offset, buffer, bytes); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", - sectors_to_bytes(sect_num), filename, strerror(-ret)); + offset, filename, strerror(-ret)); return 4; } - idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); + idx = find_nonzero(buffer, bytes); if (idx >= 0) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(sect_num) + idx); + offset + idx); return 1; } @@ -1471,10 +1470,12 @@ static int img_compare(int argc, char **argv) } else { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); if (allocated1) { - ret = check_empty_sectors(blk1, sector_num, nb_sectors, + ret = check_empty_sectors(blk1, sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename1, buf1, quiet); } else { - ret = check_empty_sectors(blk2, sector_num, nb_sectors, + ret = check_empty_sectors(blk2, sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename2, buf1, quiet); } if (ret) { @@ -1519,7 +1520,9 @@ static int img_compare(int argc, char **argv) nb_sectors = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = check_empty_sectors(blk_over, sector_num, nb_sectors, + ret = check_empty_sectors(blk_over, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename_over, buf1, quiet); if (ret) { goto out; From dc61cd3b144151024a247a109f360d2e2cab0f81 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:14 -0500 Subject: [PATCH 20/35] qemu-img: Change compare_sectors() to be byte-based In the continuing quest to make more things byte-based, change compare_sectors(), renaming it to compare_buffers() in the process. Note that one caller (qemu-img compare) only cares about the first difference, while the other (qemu-img rebase) cares about how many consecutive sectors have the same equal/different status; however, this patch does not bother to micro-optimize the compare case to avoid the comparisons of sectors beyond the first mismatch. Both callers are always passing valid buffers in, so the initial check for buffer size can be turned into an assertion. Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 55 +++++++++++++++++++++++++++--------------------------- 1 file changed, 27 insertions(+), 28 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index 66d595be3d..c6b6263853 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1156,31 +1156,28 @@ static int is_allocated_sectors_min(const uint8_t *buf, int n, int *pnum, } /* - * Compares two buffers sector by sector. Returns 0 if the first sector of both - * buffers matches, non-zero otherwise. + * Compares two buffers sector by sector. Returns 0 if the first + * sector of each buffer matches, non-zero otherwise. * - * pnum is set to the number of sectors (including and immediately following - * the first one) that are known to have the same comparison result + * pnum is set to the sector-aligned size of the buffer prefix that + * has the same matching status as the first sector. */ -static int compare_sectors(const uint8_t *buf1, const uint8_t *buf2, int n, - int *pnum) +static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2, + int64_t bytes, int64_t *pnum) { bool res; - int i; + int64_t i = MIN(bytes, BDRV_SECTOR_SIZE); - if (n <= 0) { - *pnum = 0; - return 0; - } + assert(bytes > 0); - res = !!memcmp(buf1, buf2, 512); - for(i = 1; i < n; i++) { - buf1 += 512; - buf2 += 512; + res = !!memcmp(buf1, buf2, i); + while (i < bytes) { + int64_t len = MIN(bytes - i, BDRV_SECTOR_SIZE); - if (!!memcmp(buf1, buf2, 512) != res) { + if (!!memcmp(buf1 + i, buf2 + i, len) != res) { break; } + i += len; } *pnum = i; @@ -1255,7 +1252,7 @@ static int img_compare(int argc, char **argv) int64_t total_sectors; int64_t sector_num = 0; int64_t nb_sectors; - int c, pnum; + int c; uint64_t progress_base; bool image_opts = false; bool force_share = false; @@ -1439,6 +1436,8 @@ static int img_compare(int argc, char **argv) /* nothing to do */ } else if (allocated1 == allocated2) { if (allocated1) { + int64_t pnum; + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, nb_sectors << BDRV_SECTOR_BITS); @@ -1458,11 +1457,11 @@ static int img_compare(int argc, char **argv) ret = 4; goto out; } - ret = compare_sectors(buf1, buf2, nb_sectors, &pnum); - if (ret || pnum != nb_sectors) { + ret = compare_buffers(buf1, buf2, + nb_sectors * BDRV_SECTOR_SIZE, &pnum); + if (ret || pnum != nb_sectors * BDRV_SECTOR_SIZE) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes( - ret ? sector_num : sector_num + pnum)); + sectors_to_bytes(sector_num) + (ret ? 0 : pnum)); ret = 1; goto out; } @@ -3354,16 +3353,16 @@ static int img_rebase(int argc, char **argv) /* If they differ, we need to write to the COW file */ uint64_t written = 0; - while (written < n) { - int pnum; + while (written < n * BDRV_SECTOR_SIZE) { + int64_t pnum; - if (compare_sectors(buf_old + written * 512, - buf_new + written * 512, n - written, &pnum)) + if (compare_buffers(buf_old + written, + buf_new + written, + n * BDRV_SECTOR_SIZE - written, &pnum)) { ret = blk_pwrite(blk, - (sector + written) << BDRV_SECTOR_BITS, - buf_old + written * 512, - pnum << BDRV_SECTOR_BITS, 0); + (sector << BDRV_SECTOR_BITS) + written, + buf_old + written, pnum, 0); if (ret < 0) { error_report("Error while writing to COW image: %s", strerror(-ret)); From 415362873fd3bfba4605ec44b6ae2da91bbb28d3 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:15 -0500 Subject: [PATCH 21/35] qemu-img: Change img_rebase() to be byte-based In the continuing quest to make more things byte-based, change the internal iteration of img_rebase(). We can finally drop the TODO assertion added earlier, now that the entire algorithm is byte-based and no longer has to shift from bytes to sectors. Most of the change is mechanical ('num_sectors' becomes 'size', 'sector' becomes 'offset', 'n' goes from sectors to bytes); some of it is also a cleanup (use of MIN() instead of open-coding, loss of variable 'count' added earlier in commit d6a644bb). Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 84 ++++++++++++++++++++++-------------------------------- 1 file changed, 34 insertions(+), 50 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index c6b6263853..994365c6a4 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -3248,70 +3248,58 @@ static int img_rebase(int argc, char **argv) * the image is the same as the original one at any time. */ if (!unsafe) { - int64_t num_sectors; - int64_t old_backing_num_sectors; - int64_t new_backing_num_sectors = 0; - uint64_t sector; - int n; - int64_t count; + int64_t size; + int64_t old_backing_size; + int64_t new_backing_size = 0; + uint64_t offset; + int64_t n; float local_progress = 0; buf_old = blk_blockalign(blk, IO_BUF_SIZE); buf_new = blk_blockalign(blk, IO_BUF_SIZE); - num_sectors = blk_nb_sectors(blk); - if (num_sectors < 0) { + size = blk_getlength(blk); + if (size < 0) { error_report("Could not get size of '%s': %s", - filename, strerror(-num_sectors)); + filename, strerror(-size)); ret = -1; goto out; } - old_backing_num_sectors = blk_nb_sectors(blk_old_backing); - if (old_backing_num_sectors < 0) { + old_backing_size = blk_getlength(blk_old_backing); + if (old_backing_size < 0) { char backing_name[PATH_MAX]; bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name)); error_report("Could not get size of '%s': %s", - backing_name, strerror(-old_backing_num_sectors)); + backing_name, strerror(-old_backing_size)); ret = -1; goto out; } if (blk_new_backing) { - new_backing_num_sectors = blk_nb_sectors(blk_new_backing); - if (new_backing_num_sectors < 0) { + new_backing_size = blk_getlength(blk_new_backing); + if (new_backing_size < 0) { error_report("Could not get size of '%s': %s", - out_baseimg, strerror(-new_backing_num_sectors)); + out_baseimg, strerror(-new_backing_size)); ret = -1; goto out; } } - if (num_sectors != 0) { - local_progress = (float)100 / - (num_sectors / MIN(num_sectors, IO_BUF_SIZE / 512)); + if (size != 0) { + local_progress = (float)100 / (size / MIN(size, IO_BUF_SIZE)); } - for (sector = 0; sector < num_sectors; sector += n) { - - /* How many sectors can we handle with the next read? */ - if (sector + (IO_BUF_SIZE / 512) <= num_sectors) { - n = (IO_BUF_SIZE / 512); - } else { - n = num_sectors - sector; - } + for (offset = 0; offset < size; offset += n) { + /* How many bytes can we handle with the next read? */ + n = MIN(IO_BUF_SIZE, size - offset); /* If the cluster is allocated, we don't need to take action */ - ret = bdrv_is_allocated(bs, sector << BDRV_SECTOR_BITS, - n << BDRV_SECTOR_BITS, &count); + ret = bdrv_is_allocated(bs, offset, n, &n); if (ret < 0) { error_report("error while reading image metadata: %s", strerror(-ret)); goto out; } - /* TODO relax this once bdrv_is_allocated does not enforce - * sector alignment */ - assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - n = count >> BDRV_SECTOR_BITS; if (ret) { continue; } @@ -3320,30 +3308,28 @@ static int img_rebase(int argc, char **argv) * Read old and new backing file and take into consideration that * backing files may be smaller than the COW image. */ - if (sector >= old_backing_num_sectors) { - memset(buf_old, 0, n * BDRV_SECTOR_SIZE); + if (offset >= old_backing_size) { + memset(buf_old, 0, n); } else { - if (sector + n > old_backing_num_sectors) { - n = old_backing_num_sectors - sector; + if (offset + n > old_backing_size) { + n = old_backing_size - offset; } - ret = blk_pread(blk_old_backing, sector << BDRV_SECTOR_BITS, - buf_old, n << BDRV_SECTOR_BITS); + ret = blk_pread(blk_old_backing, offset, buf_old, n); if (ret < 0) { error_report("error while reading from old backing file"); goto out; } } - if (sector >= new_backing_num_sectors || !blk_new_backing) { - memset(buf_new, 0, n * BDRV_SECTOR_SIZE); + if (offset >= new_backing_size || !blk_new_backing) { + memset(buf_new, 0, n); } else { - if (sector + n > new_backing_num_sectors) { - n = new_backing_num_sectors - sector; + if (offset + n > new_backing_size) { + n = new_backing_size - offset; } - ret = blk_pread(blk_new_backing, sector << BDRV_SECTOR_BITS, - buf_new, n << BDRV_SECTOR_BITS); + ret = blk_pread(blk_new_backing, offset, buf_new, n); if (ret < 0) { error_report("error while reading from new backing file"); goto out; @@ -3353,15 +3339,13 @@ static int img_rebase(int argc, char **argv) /* If they differ, we need to write to the COW file */ uint64_t written = 0; - while (written < n * BDRV_SECTOR_SIZE) { + while (written < n) { int64_t pnum; - if (compare_buffers(buf_old + written, - buf_new + written, - n * BDRV_SECTOR_SIZE - written, &pnum)) + if (compare_buffers(buf_old + written, buf_new + written, + n - written, &pnum)) { - ret = blk_pwrite(blk, - (sector << BDRV_SECTOR_BITS) + written, + ret = blk_pwrite(blk, offset + written, buf_old + written, pnum, 0); if (ret < 0) { error_report("Error while writing to COW image: %s", From 033d9fc203a90f567b16119906cd06f7e65a397c Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:16 -0500 Subject: [PATCH 22/35] qemu-img: Change img_compare() to be byte-based In the continuing quest to make more things byte-based, change the internal iteration of img_compare(). We can finally drop the TODO assertions added earlier, now that the entire algorithm is byte-based and no longer has to shift from bytes to sectors. Most of the change is mechanical ('total_sectors' becomes 'total_size', 'sector_num' becomes 'offset', 'nb_sectors' becomes 'chunk', 'progress_base' goes from sectors to bytes); some of it is also a cleanup (sectors_to_bytes() is now unused, loss of variable 'count' added earlier in commit 51b0a488). Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- qemu-img.c | 132 +++++++++++++++++++++-------------------------------- 1 file changed, 52 insertions(+), 80 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index 994365c6a4..02a6e27beb 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1186,11 +1186,6 @@ static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2, #define IO_BUF_SIZE (2 * 1024 * 1024) -static int64_t sectors_to_bytes(int64_t sectors) -{ - return sectors << BDRV_SECTOR_BITS; -} - /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * @@ -1241,7 +1236,7 @@ static int img_compare(int argc, char **argv) const char *fmt1 = NULL, *fmt2 = NULL, *cache, *filename1, *filename2; BlockBackend *blk1, *blk2; BlockDriverState *bs1, *bs2; - int64_t total_sectors1, total_sectors2; + int64_t total_size1, total_size2; uint8_t *buf1 = NULL, *buf2 = NULL; int64_t pnum1, pnum2; int allocated1, allocated2; @@ -1249,9 +1244,9 @@ static int img_compare(int argc, char **argv) bool progress = false, quiet = false, strict = false; int flags; bool writethrough; - int64_t total_sectors; - int64_t sector_num = 0; - int64_t nb_sectors; + int64_t total_size; + int64_t offset = 0; + int64_t chunk; int c; uint64_t progress_base; bool image_opts = false; @@ -1365,39 +1360,37 @@ static int img_compare(int argc, char **argv) buf1 = blk_blockalign(blk1, IO_BUF_SIZE); buf2 = blk_blockalign(blk2, IO_BUF_SIZE); - total_sectors1 = blk_nb_sectors(blk1); - if (total_sectors1 < 0) { + total_size1 = blk_getlength(blk1); + if (total_size1 < 0) { error_report("Can't get size of %s: %s", - filename1, strerror(-total_sectors1)); + filename1, strerror(-total_size1)); ret = 4; goto out; } - total_sectors2 = blk_nb_sectors(blk2); - if (total_sectors2 < 0) { + total_size2 = blk_getlength(blk2); + if (total_size2 < 0) { error_report("Can't get size of %s: %s", - filename2, strerror(-total_sectors2)); + filename2, strerror(-total_size2)); ret = 4; goto out; } - total_sectors = MIN(total_sectors1, total_sectors2); - progress_base = MAX(total_sectors1, total_sectors2); + total_size = MIN(total_size1, total_size2); + progress_base = MAX(total_size1, total_size2); qemu_progress_print(0, 100); - if (strict && total_sectors1 != total_sectors2) { + if (strict && total_size1 != total_size2) { ret = 1; qprintf(quiet, "Strict mode: Image size mismatch!\n"); goto out; } - while (sector_num < total_sectors) { + while (offset < total_size) { int status1, status2; - status1 = bdrv_block_status_above(bs1, NULL, - sector_num * BDRV_SECTOR_SIZE, - (total_sectors1 - sector_num) * - BDRV_SECTOR_SIZE, - &pnum1, NULL, NULL); + status1 = bdrv_block_status_above(bs1, NULL, offset, + total_size1 - offset, &pnum1, NULL, + NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -1405,30 +1398,24 @@ static int img_compare(int argc, char **argv) } allocated1 = status1 & BDRV_BLOCK_ALLOCATED; - status2 = bdrv_block_status_above(bs2, NULL, - sector_num * BDRV_SECTOR_SIZE, - (total_sectors2 - sector_num) * - BDRV_SECTOR_SIZE, - &pnum2, NULL, NULL); + status2 = bdrv_block_status_above(bs2, NULL, offset, + total_size2 - offset, &pnum2, NULL, + NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); goto out; } allocated2 = status2 & BDRV_BLOCK_ALLOCATED; - /* TODO: Relax this once comparison is byte-based, and we no longer - * have to worry about sector alignment */ - assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); assert(pnum1 && pnum2); - nb_sectors = MIN(pnum1, pnum2) >> BDRV_SECTOR_BITS; + chunk = MIN(pnum1, pnum2); if (strict) { if (status1 != status2) { ret = 1; qprintf(quiet, "Strict mode: Offset %" PRId64 - " block status mismatch!\n", - sectors_to_bytes(sector_num)); + " block status mismatch!\n", offset); goto out; } } @@ -1438,59 +1425,54 @@ static int img_compare(int argc, char **argv) if (allocated1) { int64_t pnum; - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, - nb_sectors << BDRV_SECTOR_BITS); - if (ret < 0) { - error_report("Error while reading offset %" PRId64 " of %s:" - " %s", sectors_to_bytes(sector_num), filename1, - strerror(-ret)); - ret = 4; - goto out; - } - ret = blk_pread(blk2, sector_num << BDRV_SECTOR_BITS, buf2, - nb_sectors << BDRV_SECTOR_BITS); + chunk = MIN(chunk, IO_BUF_SIZE); + ret = blk_pread(blk1, offset, buf1, chunk); if (ret < 0) { error_report("Error while reading offset %" PRId64 - " of %s: %s", sectors_to_bytes(sector_num), - filename2, strerror(-ret)); + " of %s: %s", + offset, filename1, strerror(-ret)); ret = 4; goto out; } - ret = compare_buffers(buf1, buf2, - nb_sectors * BDRV_SECTOR_SIZE, &pnum); - if (ret || pnum != nb_sectors * BDRV_SECTOR_SIZE) { + ret = blk_pread(blk2, offset, buf2, chunk); + if (ret < 0) { + error_report("Error while reading offset %" PRId64 + " of %s: %s", + offset, filename2, strerror(-ret)); + ret = 4; + goto out; + } + ret = compare_buffers(buf1, buf2, chunk, &pnum); + if (ret || pnum != chunk) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(sector_num) + (ret ? 0 : pnum)); + offset + (ret ? 0 : pnum)); ret = 1; goto out; } } } else { - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); + chunk = MIN(chunk, IO_BUF_SIZE); if (allocated1) { - ret = check_empty_sectors(blk1, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + ret = check_empty_sectors(blk1, offset, chunk, filename1, buf1, quiet); } else { - ret = check_empty_sectors(blk2, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + ret = check_empty_sectors(blk2, offset, chunk, filename2, buf1, quiet); } if (ret) { goto out; } } - sector_num += nb_sectors; - qemu_progress_print(((float) nb_sectors / progress_base)*100, 100); + offset += chunk; + qemu_progress_print(((float) chunk / progress_base) * 100, 100); } - if (total_sectors1 != total_sectors2) { + if (total_size1 != total_size2) { BlockBackend *blk_over; const char *filename_over; qprintf(quiet, "Warning: Image size mismatch!\n"); - if (total_sectors1 > total_sectors2) { + if (total_size1 > total_size2) { blk_over = blk1; filename_over = filename1; } else { @@ -1498,14 +1480,10 @@ static int img_compare(int argc, char **argv) filename_over = filename2; } - while (sector_num < progress_base) { - int64_t count; - - ret = bdrv_block_status_above(blk_bs(blk_over), NULL, - sector_num * BDRV_SECTOR_SIZE, - (progress_base - sector_num) * - BDRV_SECTOR_SIZE, - &count, NULL, NULL); + while (offset < progress_base) { + ret = bdrv_block_status_above(blk_bs(blk_over), NULL, offset, + progress_base - offset, &chunk, + NULL, NULL); if (ret < 0) { ret = 3; error_report("Sector allocation test failed for %s", @@ -1513,22 +1491,16 @@ static int img_compare(int argc, char **argv) goto out; } - /* TODO relax this once bdrv_block_status_above does not enforce - * sector alignment */ - assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - nb_sectors = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = check_empty_sectors(blk_over, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + chunk = MIN(chunk, IO_BUF_SIZE); + ret = check_empty_sectors(blk_over, offset, chunk, filename_over, buf1, quiet); if (ret) { goto out; } } - sector_num += nb_sectors; - qemu_progress_print(((float) nb_sectors / progress_base)*100, 100); + offset += chunk; + qemu_progress_print(((float) chunk / progress_base) * 100, 100); } } From efa6e2ed643c770153eeacace410c06f15360cd9 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:17 -0500 Subject: [PATCH 23/35] block: Align block status requests Any device that has request_alignment greater than 512 should be unable to report status at a finer granularity; it may also be simpler for such devices to be guaranteed that the block layer has rounded things out to the granularity boundary (the way the block layer already rounds all other I/O out). Besides, getting the code correct for super-sector alignment also benefits us for the fact that our public interface now has byte granularity, even though none of our drivers have byte-level callbacks. Add an assertion in blkdebug that proves that the block layer never requests status of unaligned sections, similar to what it does on other requests (while still keeping the generic helper in place for when future patches add a throttle driver). Note that iotest 177 already covers this (it would fail if you use just the blkdebug.c hunk without the io.c changes). Meanwhile, we can drop assertions in callers that no longer have to pass in sector-aligned addresses. There is a mid-function scope added for 'count' and 'longret', for a couple of reasons: first, an upcoming patch will add an 'if' statement that checks whether a driver has an old- or new-style callback, and can conveniently use the same scope for less indentation churn at that time. Second, since we are trying to get rid of sector-based computations, wrapping things in a scope makes it easier to group and see what will be deleted in a final cleanup patch once all drivers have been converted to the new-style callback. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/blkdebug.c | 13 ++++++- block/io.c | 71 +++++++++++++++++++++++++-------------- include/block/block_int.h | 3 +- 3 files changed, 59 insertions(+), 28 deletions(-) diff --git a/block/blkdebug.c b/block/blkdebug.c index dfdf9b91aa..e21669979d 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -627,6 +627,17 @@ static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs, return bdrv_co_pdiscard(bs->file->bs, offset, bytes); } +static int64_t coroutine_fn blkdebug_co_get_block_status( + BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, + BlockDriverState **file) +{ + assert(QEMU_IS_ALIGNED(sector_num | nb_sectors, + DIV_ROUND_UP(bs->bl.request_alignment, + BDRV_SECTOR_SIZE))); + return bdrv_co_get_block_status_from_file(bs, sector_num, nb_sectors, + pnum, file); +} + static void blkdebug_close(BlockDriverState *bs) { BDRVBlkdebugState *s = bs->opaque; @@ -896,7 +907,7 @@ static BlockDriver bdrv_blkdebug = { .bdrv_co_flush_to_disk = blkdebug_co_flush, .bdrv_co_pwrite_zeroes = blkdebug_co_pwrite_zeroes, .bdrv_co_pdiscard = blkdebug_co_pdiscard, - .bdrv_co_get_block_status = bdrv_co_get_block_status_from_file, + .bdrv_co_get_block_status = blkdebug_co_get_block_status, .bdrv_debug_event = blkdebug_debug_event, .bdrv_debug_breakpoint = blkdebug_debug_breakpoint, diff --git a/block/io.c b/block/io.c index e64b1cb294..d2cb20d872 100644 --- a/block/io.c +++ b/block/io.c @@ -1839,10 +1839,11 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, { int64_t total_size; int64_t n; /* bytes */ - int64_t ret; + int ret; int64_t local_map = 0; BlockDriverState *local_file = NULL; - int count; /* sectors */ + int64_t aligned_offset, aligned_bytes; + uint32_t align; assert(pnum); *pnum = 0; @@ -1881,35 +1882,58 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, } bdrv_inc_in_flight(bs); + + /* Round out to request_alignment boundaries */ + /* TODO: until we have a byte-based driver callback, we also have to + * round out to sectors, even if that is bigger than request_alignment */ + align = MAX(bs->bl.request_alignment, BDRV_SECTOR_SIZE); + aligned_offset = QEMU_ALIGN_DOWN(offset, align); + aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset; + + { + int count; /* sectors */ + int64_t longret; + + assert(QEMU_IS_ALIGNED(aligned_offset | aligned_bytes, + BDRV_SECTOR_SIZE)); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + longret = bs->drv->bdrv_co_get_block_status( + bs, aligned_offset >> BDRV_SECTOR_BITS, + MIN(INT_MAX, aligned_bytes) >> BDRV_SECTOR_BITS, &count, + &local_file); + if (longret < 0) { + assert(INT_MIN <= longret); + ret = longret; + goto out; + } + if (longret & BDRV_BLOCK_OFFSET_VALID) { + local_map = longret & BDRV_BLOCK_OFFSET_MASK; + } + ret = longret & ~BDRV_BLOCK_OFFSET_MASK; + *pnum = count * BDRV_SECTOR_SIZE; + } + /* - * TODO: Rather than require aligned offsets, we could instead - * round to the driver's request_alignment here, then touch up - * count afterwards back to the caller's expectations. + * The driver's result must be a multiple of request_alignment. + * Clamp pnum and adjust map to original request. */ - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - /* - * The contract allows us to return pnum smaller than bytes, even - * if the next query would see the same status; we truncate the - * request to avoid overflowing the driver's 32-bit interface. - */ - bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); - ret = bs->drv->bdrv_co_get_block_status(bs, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &count, - &local_file); - if (ret < 0) { - goto out; + assert(QEMU_IS_ALIGNED(*pnum, align) && align > offset - aligned_offset); + *pnum -= offset - aligned_offset; + if (*pnum > bytes) { + *pnum = bytes; } if (ret & BDRV_BLOCK_OFFSET_VALID) { - local_map = ret & BDRV_BLOCK_OFFSET_MASK; + local_map += offset - aligned_offset; } - *pnum = count * BDRV_SECTOR_SIZE; if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); ret = bdrv_co_block_status(local_file, want_zero, local_map, *pnum, pnum, &local_map, &local_file); - assert(ret < 0 || - QEMU_IS_ALIGNED(*pnum | local_map, BDRV_SECTOR_SIZE)); goto out; } @@ -1968,11 +1992,6 @@ early_out: if (map) { *map = local_map; } - if (ret >= 0) { - ret &= ~BDRV_BLOCK_OFFSET_MASK; - } else { - assert(INT_MIN <= ret); - } return ret; } diff --git a/include/block/block_int.h b/include/block/block_int.h index 246eee2e82..a5482775ec 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -207,7 +207,8 @@ struct BlockDriver { * according to the current layer, and should not set * BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. The block - * layer guarantees non-NULL pnum and file. + * layer guarantees input aligned to request_alignment, as well as + * non-NULL pnum and file. */ int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, From 88e63df21490a43f430820c66b043018db96b1d4 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:18 -0500 Subject: [PATCH 24/35] block: Reduce bdrv_aligned_preadv() rounding Now that bdrv_is_allocated accepts non-aligned inputs, we can remove the TODO added in commit d6a644bb. Signed-off-by: Eric Blake Reviewed-by: John Snow Signed-off-by: Kevin Wolf --- block/io.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/block/io.c b/block/io.c index d2cb20d872..3d5ef2cabe 100644 --- a/block/io.c +++ b/block/io.c @@ -1124,18 +1124,14 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, } if (flags & BDRV_REQ_COPY_ON_READ) { - /* TODO: Simplify further once bdrv_is_allocated no longer - * requires sector alignment */ - int64_t start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); - int64_t end = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE); int64_t pnum; - ret = bdrv_is_allocated(bs, start, end - start, &pnum); + ret = bdrv_is_allocated(bs, offset, bytes, &pnum); if (ret < 0) { goto out; } - if (!ret || pnum != end - start) { + if (!ret || pnum != bytes) { ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov); goto out; } From 8cbf74b23cafd1bcee5fdef769f8e94ace43935f Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:19 -0500 Subject: [PATCH 25/35] qcow2: Reduce is_zero() rounding Now that bdrv_is_allocated accepts non-aligned inputs, we can remove the TODO added in earlier refactoring. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- block/qcow2.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index 29d0a50955..fbf9464d3a 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2976,22 +2976,16 @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { int64_t nr; int res; - int64_t start; - - /* TODO: Widening to sector boundaries should only be needed as - * long as we can't query finer granularity. */ - start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); - bytes = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE) - start; /* Clamp to image length, before checking status of underlying sectors */ - if (start + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { - bytes = bs->total_sectors * BDRV_SECTOR_SIZE - start; + if (offset + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { + bytes = bs->total_sectors * BDRV_SECTOR_SIZE - offset; } if (!bytes) { return true; } - res = bdrv_block_status_above(bs, NULL, start, bytes, &nr, NULL, NULL); + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; } From f0a9c18f9e72ab66d3c57c5c3a43137deb534076 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Wed, 11 Oct 2017 22:47:20 -0500 Subject: [PATCH 26/35] qemu-io: Relax 'alloc' now that block-status doesn't assert Previously, the alloc command required that input parameters be sector-aligned and clamped to 32 bits, because the underlying bdrv_is_allocated used a 32-bit parameter and asserted aligned inputs. But now that we have fixed block status to report a 64-bit bytes value, and to properly round requests on behalf of guests, we can pass any values, and can use qemu-io to add coverage that our rounding is correct regardless of the guest alignment constraints. Update iotest 177 to intentionally probe block status at unaligned boundaries as well as with a bytes value that does not map to 32-bit sectors, which also required tweaking the image prep to leave an unallocated portion to the image under test. Signed-off-by: Eric Blake Signed-off-by: Kevin Wolf --- qemu-io-cmds.c | 13 ------------- tests/qemu-iotests/177 | 12 ++++++++++-- tests/qemu-iotests/177.out | 19 ++++++++++++++----- 3 files changed, 24 insertions(+), 20 deletions(-) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index 3727fb43f3..de8e3de726 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -1769,10 +1769,6 @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) if (offset < 0) { print_cvtnum_err(offset, argv[1]); return 0; - } else if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { - printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", - offset); - return 0; } if (argc == 3) { @@ -1780,19 +1776,10 @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) if (count < 0) { print_cvtnum_err(count, argv[2]); return 0; - } else if (count > INT_MAX * BDRV_SECTOR_SIZE) { - printf("length argument cannot exceed %llu, given %s\n", - INT_MAX * BDRV_SECTOR_SIZE, argv[2]); - return 0; } } else { count = BDRV_SECTOR_SIZE; } - if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { - printf("%" PRId64 " is not a sector-aligned value for 'count'\n", - count); - return 0; - } remaining = count; sum_alloc = 0; diff --git a/tests/qemu-iotests/177 b/tests/qemu-iotests/177 index f8ed8fb86b..28990977f1 100755 --- a/tests/qemu-iotests/177 +++ b/tests/qemu-iotests/177 @@ -51,7 +51,7 @@ echo "== setting up files ==" TEST_IMG="$TEST_IMG.base" _make_test_img $size $QEMU_IO -c "write -P 11 0 $size" "$TEST_IMG.base" | _filter_qemu_io _make_test_img -b "$TEST_IMG.base" -$QEMU_IO -c "write -P 22 0 $size" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "write -P 22 0 110M" "$TEST_IMG" | _filter_qemu_io # Limited to 64k max-transfer echo @@ -81,6 +81,13 @@ limits=align=512,opt-write-zero=15M,max-write-zero=15M,opt-discard=15M,max-disca $QEMU_IO -c "open -o $options,$limits blkdebug::$TEST_IMG" \ -c "discard 80000001 30M" | _filter_qemu_io +echo +echo "== block status smaller than alignment ==" +limits=align=4k +$QEMU_IO -c "open -o $options,$limits blkdebug::$TEST_IMG" \ + -c "alloc 1 1" -c "alloc 0x6dffff0 1000" -c "alloc 127m 5P" \ + -c map | _filter_qemu_io + echo echo "== verify image content ==" @@ -103,7 +110,8 @@ function verify_io() echo read -P 0 32M 32M echo read -P 22 64M 13M echo read -P $discarded 77M 29M - echo read -P 22 106M 22M + echo read -P 22 106M 4M + echo read -P 11 110M 18M } verify_io | $QEMU_IO -r "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/177.out b/tests/qemu-iotests/177.out index 43a777836c..f788b55e20 100644 --- a/tests/qemu-iotests/177.out +++ b/tests/qemu-iotests/177.out @@ -5,8 +5,8 @@ Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 wrote 134217728/134217728 bytes at offset 0 128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base -wrote 134217728/134217728 bytes at offset 0 -128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 115343360/115343360 bytes at offset 0 +110 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) == constrained alignment and max-transfer == wrote 131072/131072 bytes at offset 1000 @@ -26,6 +26,13 @@ wrote 33554432/33554432 bytes at offset 33554432 discard 31457280/31457280 bytes at offset 80000001 30 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +== block status smaller than alignment == +1/1 bytes allocated at offset 1 bytes +16/1000 bytes allocated at offset 110 MiB +0/1048576 bytes allocated at offset 127 MiB +110 MiB (0x6e00000) bytes allocated at offset 0 bytes (0x0) +18 MiB (0x1200000) bytes not allocated at offset 110 MiB (0x6e00000) + == verify image content == read 1000/1000 bytes at offset 0 1000 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -43,12 +50,14 @@ read 13631488/13631488 bytes at offset 67108864 13 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 30408704/30408704 bytes at offset 80740352 29 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -read 23068672/23068672 bytes at offset 111149056 -22 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 4194304/4194304 bytes at offset 111149056 +4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 18874368/18874368 bytes at offset 115343360 +18 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Offset Length File 0 0x800000 TEST_DIR/t.IMGFMT 0x900000 0x2400000 TEST_DIR/t.IMGFMT 0x3c00000 0x1100000 TEST_DIR/t.IMGFMT -0x6a00000 0x1600000 TEST_DIR/t.IMGFMT +0x6a00000 0x400000 TEST_DIR/t.IMGFMT No errors were found on the image. *** done From 67e56472a503f94a3950bad85a57fb99706cf1d8 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Thu, 26 Oct 2017 09:59:47 +0200 Subject: [PATCH 27/35] qemu-img.1: Image invalidation on qemu-img commit qemu-img commit invalidates all images between base and top. This should be mentioned in the man page. Suggested-by: Ping Li Signed-off-by: Max Reitz Reviewed-by: Jeff Cody Signed-off-by: Kevin Wolf --- qemu-img.texi | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/qemu-img.texi b/qemu-img.texi index ee5c5940d3..fdcf120f36 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -274,11 +274,10 @@ If the backing chain of the given image file @var{filename} has more than one layer, the backing file into which the changes will be committed may be specified as @var{base} (which has to be part of @var{filename}'s backing chain). If @var{base} is not specified, the immediate backing file of the top -image (which is @var{filename}) will be used. For reasons of consistency, -explicitly specifying @var{base} will always imply @code{-d} (since emptying an -image after committing to an indirect backing file would lead to different data -being read from the image due to content in the intermediate backing chain -overruling the commit target). +image (which is @var{filename}) will be used. Note that after a commit operation +all images between @var{base} and the top image will be invalid and may return +garbage data when read. For this reason, @code{-b} implies @code{-d} (so that +the top image stays valid). @item compare [-f @var{fmt}] [-F @var{fmt}] [-T @var{src_cache}] [-p] [-s] [-q] @var{filename1} @var{filename2} From a35f87f50d4bb5d7255b30e5bb9dddb6f3a6938f Mon Sep 17 00:00:00 2001 From: Alberto Garcia Date: Mon, 9 Oct 2017 17:38:56 +0200 Subject: [PATCH 28/35] qcow2: Use BDRV_SECTOR_BITS instead of its literal value BDRV_SECTOR_BITS is defined to be 9 in block.h (and BDRV_SECTOR_SIZE is calculated from that), but there are still a couple of places where we are using the literal value instead of the macro. Signed-off-by: Alberto Garcia Message-id: 20171009153856.20387-1-berto@igalia.com Signed-off-by: Max Reitz --- block/qcow2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index fbf9464d3a..f77b490cc6 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -1139,7 +1139,7 @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, s->cluster_bits = header.cluster_bits; s->cluster_size = 1 << s->cluster_bits; - s->cluster_sectors = 1 << (s->cluster_bits - 9); + s->cluster_sectors = 1 << (s->cluster_bits - BDRV_SECTOR_BITS); /* Initialise version 3 header fields */ if (header.version == 2) { @@ -1636,7 +1636,7 @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs, bytes = MIN(INT_MAX, nb_sectors * BDRV_SECTOR_SIZE); qemu_co_mutex_lock(&s->lock); - ret = qcow2_get_cluster_offset(bs, sector_num << 9, &bytes, + ret = qcow2_get_cluster_offset(bs, sector_num << BDRV_SECTOR_BITS, &bytes, &cluster_offset); qemu_co_mutex_unlock(&s->lock); if (ret < 0) { From f700ceae8ab57a5c8973932c14f9abba1f99e5a8 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Fri, 29 Sep 2017 19:08:43 +0200 Subject: [PATCH 29/35] iotests: Add test for dataplane mirroring Signed-off-by: Max Reitz Message-id: 20170929170843.3711-1-mreitz@redhat.com Reviewed-by: Eric Blake Signed-off-by: Max Reitz --- tests/qemu-iotests/127 | 97 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/127.out | 14 ++++++ tests/qemu-iotests/group | 1 + 3 files changed, 112 insertions(+) create mode 100755 tests/qemu-iotests/127 create mode 100644 tests/qemu-iotests/127.out diff --git a/tests/qemu-iotests/127 b/tests/qemu-iotests/127 new file mode 100755 index 0000000000..9e0d7d3be8 --- /dev/null +++ b/tests/qemu-iotests/127 @@ -0,0 +1,97 @@ +#!/bin/bash +# +# Test case for mirroring with dataplane +# +# Copyright (C) 2017 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . +# + +# creator +owner=mreitz@redhat.com + +seq=$(basename $0) +echo "QA output created by $seq" + +here=$PWD +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_qemu + _cleanup_test_img + _rm_test_img "$TEST_IMG.overlay0" + _rm_test_img "$TEST_IMG.overlay1" +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and qemu instance handling +. ./common.rc +. ./common.filter +. ./common.qemu + +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux + +IMG_SIZE=64K + +_make_test_img $IMG_SIZE +TEST_IMG="$TEST_IMG.overlay0" _make_test_img -b "$TEST_IMG" $IMG_SIZE +TEST_IMG="$TEST_IMG.overlay1" _make_test_img -b "$TEST_IMG" $IMG_SIZE + +# So that we actually have something to mirror and the job does not return +# immediately (which may be bad because then we cannot know whether the +# 'return' or the 'BLOCK_JOB_READY' comes first). +$QEMU_IO -c 'write 0 42' "$TEST_IMG.overlay0" | _filter_qemu_io + +# We cannot use virtio-blk here because that does not actually set the attached +# BB's AioContext in qtest mode +_launch_qemu \ + -object iothread,id=iothr \ + -blockdev node-name=source,driver=$IMGFMT,file.driver=file,file.filename="$TEST_IMG.overlay0" \ + -device virtio-scsi,id=scsi-bus,iothread=iothr \ + -device scsi-hd,bus=scsi-bus.0,drive=source + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'qmp_capabilities' }" \ + 'return' + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'drive-mirror', + 'arguments': { + 'job-id': 'mirror', + 'device': 'source', + 'target': '$TEST_IMG.overlay1', + 'mode': 'existing', + 'sync': 'top' + } }" \ + 'BLOCK_JOB_READY' + +# The backing BDS should be assigned the overlay's AioContext +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'mirror' } }" \ + 'BLOCK_JOB_COMPLETED' + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'quit' }" \ + 'return' + +wait=yes _cleanup_qemu + +# success, all done +echo '*** done' +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/127.out b/tests/qemu-iotests/127.out new file mode 100644 index 0000000000..543d075005 --- /dev/null +++ b/tests/qemu-iotests/127.out @@ -0,0 +1,14 @@ +QA output created by 127 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536 +Formatting 'TEST_DIR/t.IMGFMT.overlay0', fmt=IMGFMT size=65536 backing_file=TEST_DIR/t.IMGFMT +Formatting 'TEST_DIR/t.IMGFMT.overlay1', fmt=IMGFMT size=65536 backing_file=TEST_DIR/t.IMGFMT +wrote 42/42 bytes at offset 0 +42 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index 83da427c0a..24e5ad1b79 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -133,6 +133,7 @@ 124 rw auto backing 125 rw auto 126 rw auto backing +127 rw auto backing quick 128 rw auto quick 129 rw auto quick 130 rw auto quick From 44673a0b59d1fafd1abfdf35a1ac924b856c6ad5 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 18:34:55 +0200 Subject: [PATCH 30/35] iotests: Pull _filter_actual_image_size from 67/87 Tests 067 and 087 filter the actual image size because it depends on the host filesystem (and is not part of the respective test). Since this is generally true, we should have a common filter function for this, so let's pull out the sed line from both tests into such a function. Signed-off-by: Max Reitz Message-id: 20171009163456.485-2-mreitz@redhat.com Reviewed-by: Eric Blake Reviewed-by: Jeff Cody Signed-off-by: Max Reitz --- tests/qemu-iotests/067 | 2 +- tests/qemu-iotests/087 | 2 +- tests/qemu-iotests/common.filter | 6 ++++++ 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/067 b/tests/qemu-iotests/067 index ee9595f0da..9d561ef786 100755 --- a/tests/qemu-iotests/067 +++ b/tests/qemu-iotests/067 @@ -56,7 +56,7 @@ _filter_qmp_events() function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp | _filter_qemu \ - | sed -e 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' \ + | _filter_actual_image_size \ | _filter_generated_node_ids | _filter_qmp_events } diff --git a/tests/qemu-iotests/087 b/tests/qemu-iotests/087 index f8e4903f4f..27ab6c5151 100755 --- a/tests/qemu-iotests/087 +++ b/tests/qemu-iotests/087 @@ -46,7 +46,7 @@ function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp \ | _filter_qemu | _filter_imgfmt \ - | sed -e 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' + | _filter_actual_image_size } size=128M diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index 227b37e941..873ca6b104 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -105,6 +105,12 @@ _filter_block_job_len() sed -e 's/, "len": [0-9]\+,/, "len": LEN,/g' } +# replace actual image size (depends on the host filesystem) +_filter_actual_image_size() +{ + sed -s 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' +} + # replace driver-specific options in the "Formatting..." line _filter_img_create() { From b66df843b442924745d196bd0a05f0639b808164 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 18:34:56 +0200 Subject: [PATCH 31/35] iotests: Filter actual image size in 184 and 191 Whenever the actual image size is not part of the test, it should be filtered as it depends on the host filesystem. Signed-off-by: Max Reitz Message-id: 20171009163456.485-3-mreitz@redhat.com Reviewed-by: Eric Blake Reviewed-by: Jeff Cody Signed-off-by: Max Reitz --- tests/qemu-iotests/184 | 3 ++- tests/qemu-iotests/184.out | 6 ++--- tests/qemu-iotests/191 | 4 ++-- tests/qemu-iotests/191.out | 46 +++++++++++++++++++------------------- 4 files changed, 30 insertions(+), 29 deletions(-) diff --git a/tests/qemu-iotests/184 b/tests/qemu-iotests/184 index 704f38f936..ee96c99af3 100755 --- a/tests/qemu-iotests/184 +++ b/tests/qemu-iotests/184 @@ -51,7 +51,8 @@ function do_run_qemu() function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp\ - | _filter_qemu_io | _filter_generated_node_ids + | _filter_qemu_io | _filter_generated_node_ids \ + | _filter_actual_image_size } _make_test_img 64M diff --git a/tests/qemu-iotests/184.out b/tests/qemu-iotests/184.out index 0aed1a2220..4dc7984a85 100644 --- a/tests/qemu-iotests/184.out +++ b/tests/qemu-iotests/184.out @@ -32,7 +32,7 @@ Testing: "filename": "json:{\"throttle-group\": \"group0\", \"driver\": \"throttle\", \"file\": {\"driver\": \"qcow2\", \"file\": {\"driver\": \"file\", \"filename\": \"TEST_DIR/t.qcow2\"}}}", "cluster-size": 65536, "format": "throttle", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -62,7 +62,7 @@ Testing: "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -100,7 +100,7 @@ Testing: "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index 28bdea8f98..ad785e10b1 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -92,7 +92,7 @@ echo === Check that both top and top2 point to base now === echo _send_qemu_cmd $h "{ 'execute': 'query-named-block-nodes' }" "^}" | - _filter_generated_node_ids + _filter_generated_node_ids | _filter_actual_image_size _send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" wait=1 _cleanup_qemu @@ -140,7 +140,7 @@ echo === Check that both top and top2 point to base now === echo _send_qemu_cmd $h "{ 'execute': 'query-named-block-nodes' }" "^}" | - _filter_generated_node_ids + _filter_generated_node_ids | _filter_actual_image_size _send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" wait=1 _cleanup_qemu diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out index 6157fa520f..73c0ed454c 100644 --- a/tests/qemu-iotests/191.out +++ b/tests/qemu-iotests/191.out @@ -47,7 +47,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -64,7 +64,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -105,7 +105,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -136,7 +136,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -153,7 +153,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -194,7 +194,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -225,7 +225,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -242,7 +242,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.mid", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -283,7 +283,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.mid", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -313,7 +313,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -351,7 +351,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.base", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -450,7 +450,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -467,7 +467,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -508,7 +508,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -540,7 +540,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -557,7 +557,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -576,7 +576,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl3", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -617,7 +617,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl3", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -647,7 +647,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -685,7 +685,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.base", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -716,7 +716,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -733,7 +733,7 @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -774,7 +774,7 @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, From 233521b1999810036f63d060ce021d30a8ce0504 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 17:54:31 +0200 Subject: [PATCH 32/35] qcow2: Emit errp when truncating the image tail bdrv_truncate() has an errp parameter which is always set when an error occurs. Let's use that instead of a plain strerror(). Signed-off-by: Max Reitz Message-id: 20171009155431.14093-1-mreitz@redhat.com Reviewed-by: Pavel Butsykin Reviewed-by: Jeff Cody Signed-off-by: Max Reitz --- block/qcow2.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index f77b490cc6..d3e114bce5 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -3145,12 +3145,13 @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, return last_cluster; } if ((last_cluster + 1) * s->cluster_size < old_file_size) { - ret = bdrv_truncate(bs->file, (last_cluster + 1) * s->cluster_size, - PREALLOC_MODE_OFF, NULL); - if (ret < 0) { - warn_report("Failed to truncate the tail of the image: %s", - strerror(-ret)); - ret = 0; + Error *local_err = NULL; + + bdrv_truncate(bs->file, (last_cluster + 1) * s->cluster_size, + PREALLOC_MODE_OFF, &local_err); + if (local_err) { + warn_reportf_err(local_err, + "Failed to truncate the tail of the image: "); } } } else { From e400ad1e1f0127b4fdabcb1c8de1e99be91788df Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 23:55:31 +0200 Subject: [PATCH 33/35] qcow2: Fix unaligned preallocated truncation A qcow2 image file's length is not required to have a length that is a multiple of the cluster size. However, qcow2_refcount_area() expects an aligned value for its @start_offset parameter, so we need to round @old_file_size up to the next cluster boundary. Reported-by: Ping Li Bug: https://bugzilla.redhat.com/show_bug.cgi?id=1414049 Signed-off-by: Max Reitz Message-id: 20171009215533.12530-2-mreitz@redhat.com Cc: qemu-stable@nongnu.org Reviewed-by: Eric Blake Reviewed-by: Jeff Cody Reviewed-by: Stefan Hajnoczi Signed-off-by: Max Reitz --- block/qcow2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/qcow2.c b/block/qcow2.c index d3e114bce5..1ea763126d 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -3188,6 +3188,7 @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, "Failed to inquire current file length"); return old_file_size; } + old_file_size = ROUND_UP(old_file_size, s->cluster_size); nb_new_data_clusters = DIV_ROUND_UP(offset - old_length, s->cluster_size); From 572b07bea1d1a0f7726fd95c2613c76002a379bc Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 23:55:32 +0200 Subject: [PATCH 34/35] qcow2: Always execute preallocate() in a coroutine Some qcow2 functions (at least perform_cow()) expect s->lock to be taken. Therefore, if we want to make use of them, we should execute preallocate() (as "preallocate_co") in a coroutine so that we can use the qemu_co_mutex_* functions. Signed-off-by: Max Reitz Message-id: 20171009215533.12530-3-mreitz@redhat.com Cc: qemu-stable@nongnu.org Reviewed-by: Eric Blake Reviewed-by: Jeff Cody Reviewed-by: Stefan Hajnoczi Signed-off-by: Max Reitz --- block/qcow2.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index 1ea763126d..92cb9f9bfa 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2460,6 +2460,14 @@ static int qcow2_set_up_encryption(BlockDriverState *bs, const char *encryptfmt, } +typedef struct PreallocCo { + BlockDriverState *bs; + uint64_t offset; + uint64_t new_length; + + int ret; +} PreallocCo; + /** * Preallocates metadata structures for data clusters between @offset (in the * guest disk) and @new_length (which is thus generally the new guest disk @@ -2467,9 +2475,12 @@ static int qcow2_set_up_encryption(BlockDriverState *bs, const char *encryptfmt, * * Returns: 0 on success, -errno on failure. */ -static int preallocate(BlockDriverState *bs, - uint64_t offset, uint64_t new_length) +static void coroutine_fn preallocate_co(void *opaque) { + PreallocCo *params = opaque; + BlockDriverState *bs = params->bs; + uint64_t offset = params->offset; + uint64_t new_length = params->new_length; BDRVQcow2State *s = bs->opaque; uint64_t bytes; uint64_t host_offset = 0; @@ -2477,9 +2488,7 @@ static int preallocate(BlockDriverState *bs, int ret; QCowL2Meta *meta; - if (qemu_in_coroutine()) { - qemu_co_mutex_lock(&s->lock); - } + qemu_co_mutex_lock(&s->lock); assert(offset <= new_length); bytes = new_length - offset; @@ -2533,10 +2542,28 @@ static int preallocate(BlockDriverState *bs, ret = 0; done: + qemu_co_mutex_unlock(&s->lock); + params->ret = ret; +} + +static int preallocate(BlockDriverState *bs, + uint64_t offset, uint64_t new_length) +{ + PreallocCo params = { + .bs = bs, + .offset = offset, + .new_length = new_length, + .ret = -EINPROGRESS, + }; + if (qemu_in_coroutine()) { - qemu_co_mutex_unlock(&s->lock); + preallocate_co(¶ms); + } else { + Coroutine *co = qemu_coroutine_create(preallocate_co, ¶ms); + bdrv_coroutine_enter(bs, co); + BDRV_POLL_WHILE(bs, params.ret == -EINPROGRESS); } - return ret; + return params.ret; } /* qcow2_refcount_metadata_size: From 4c112a397c2f61038914fa315a7896ce6d645d18 Mon Sep 17 00:00:00 2001 From: Max Reitz Date: Mon, 9 Oct 2017 23:55:33 +0200 Subject: [PATCH 35/35] iotests: Add cluster_size=64k to 125 Apparently it would be a good idea to test that, too. Signed-off-by: Max Reitz Message-id: 20171009215533.12530-4-mreitz@redhat.com Reviewed-by: Eric Blake Reviewed-by: Jeff Cody Reviewed-by: Stefan Hajnoczi Signed-off-by: Max Reitz --- tests/qemu-iotests/125 | 7 +- tests/qemu-iotests/125.out | 480 +++++++++++++++++++++++++++++++++---- 2 files changed, 437 insertions(+), 50 deletions(-) diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125 index 9424313e82..c20c71570c 100755 --- a/tests/qemu-iotests/125 +++ b/tests/qemu-iotests/125 @@ -69,13 +69,15 @@ fi # in B CREATION_SIZE=$((2 * 1024 * 1024 - 48 * 1024)) +# 512 is the actual test -- but it's good to test 64k as well, just to be sure. +for cluster_size in 512 64k; do # in kB for GROWTH_SIZE in 16 48 80; do for create_mode in off metadata falloc full; do for growth_mode in off metadata falloc full; do - echo "--- growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---" + echo "--- cluster_size=$cluster_size growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---" - IMGOPTS="preallocation=$create_mode,cluster_size=512" _make_test_img ${CREATION_SIZE} + IMGOPTS="preallocation=$create_mode,cluster_size=$cluster_size" _make_test_img ${CREATION_SIZE} $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K host_size_0=$(get_image_size_on_host) @@ -123,6 +125,7 @@ for GROWTH_SIZE in 16 48 80; do done done done +done # success, all done echo '*** done' diff --git a/tests/qemu-iotests/125.out b/tests/qemu-iotests/125.out index 3f4d6e31a6..596905f533 100644 --- a/tests/qemu-iotests/125.out +++ b/tests/qemu-iotests/125.out @@ -1,5 +1,5 @@ QA output created by 125 ---- growth_size=16 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -7,7 +7,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -15,7 +15,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -23,7 +23,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -31,7 +31,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -39,7 +39,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -47,7 +47,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -55,7 +55,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -63,7 +63,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -71,7 +71,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -79,7 +79,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -87,7 +87,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -95,7 +95,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -103,7 +103,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -111,7 +111,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -119,7 +119,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -127,7 +127,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -135,7 +135,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -143,7 +143,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -151,7 +151,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -159,7 +159,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -167,7 +167,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -175,7 +175,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -183,7 +183,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -191,7 +191,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -199,7 +199,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -207,7 +207,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -215,7 +215,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -223,7 +223,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -231,7 +231,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -239,7 +239,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -247,7 +247,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -255,7 +255,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -263,7 +263,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -271,7 +271,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -279,7 +279,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -287,7 +287,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -295,7 +295,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -303,7 +303,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -311,7 +311,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -319,7 +319,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -327,7 +327,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -335,7 +335,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -343,7 +343,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -351,7 +351,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -359,7 +359,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -367,7 +367,7 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -375,7 +375,391 @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0