From c8bb23cbdbe32f5c326365e0a82e1b0e68cdcd8a Mon Sep 17 00:00:00 2001 From: Anton Nefedov Date: Thu, 16 May 2019 17:27:49 +0300 Subject: qcow2: skip writing zero buffers to empty COW areas If COW areas of the newly allocated clusters are zeroes on the backing image, efficient bdrv_write_zeroes(flags=BDRV_REQ_NO_FALLBACK) can be used on the whole cluster instead of writing explicit zero buffers later in perform_cow(). iotest 060: write to the discarded cluster does not trigger COW anymore. Use a backing image instead. Signed-off-by: Anton Nefedov Message-id: 20190516142749.81019-2-anton.nefedov@virtuozzo.com Reviewed-by: Vladimir Sementsov-Ogievskiy Reviewed-by: Alberto Garcia Signed-off-by: Max Reitz --- block/qcow2-cluster.c | 2 +- block/qcow2.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++ block/qcow2.h | 6 ++++ block/trace-events | 1 + 4 files changed, 93 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 4a92990..cf892f3 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -831,7 +831,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) assert(start->offset + start->nb_bytes <= end->offset); assert(!m->data_qiov || m->data_qiov->size == data_bytes); - if (start->nb_bytes == 0 && end->nb_bytes == 0) { + if ((start->nb_bytes == 0 && end->nb_bytes == 0) || m->skip_cow) { return 0; } diff --git a/block/qcow2.c b/block/qcow2.c index dea765b..f2cb131 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2103,6 +2103,11 @@ static bool merge_cow(uint64_t offset, unsigned bytes, continue; } + /* If COW regions are handled already, skip this too */ + if (m->skip_cow) { + continue; + } + /* The data (middle) region must be immediately after the * start region */ if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) { @@ -2128,6 +2133,80 @@ static bool merge_cow(uint64_t offset, unsigned bytes, return false; } +static bool is_unallocated(BlockDriverState *bs, int64_t offset, int64_t bytes) +{ + int64_t nr; + return !bytes || + (!bdrv_is_allocated_above(bs, NULL, offset, bytes, &nr) && nr == bytes); +} + +static bool is_zero_cow(BlockDriverState *bs, QCowL2Meta *m) +{ + /* + * This check is designed for optimization shortcut so it must be + * efficient. + * Instead of is_zero(), use is_unallocated() as it is faster (but not + * as accurate and can result in false negatives). + */ + return is_unallocated(bs, m->offset + m->cow_start.offset, + m->cow_start.nb_bytes) && + is_unallocated(bs, m->offset + m->cow_end.offset, + m->cow_end.nb_bytes); +} + +static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta) +{ + BDRVQcow2State *s = bs->opaque; + QCowL2Meta *m; + + if (!(s->data_file->bs->supported_zero_flags & BDRV_REQ_NO_FALLBACK)) { + return 0; + } + + if (bs->encrypted) { + return 0; + } + + for (m = l2meta; m != NULL; m = m->next) { + int ret; + + if (!m->cow_start.nb_bytes && !m->cow_end.nb_bytes) { + continue; + } + + if (!is_zero_cow(bs, m)) { + continue; + } + + /* + * instead of writing zero COW buffers, + * efficiently zero out the whole clusters + */ + + ret = qcow2_pre_write_overlap_check(bs, 0, m->alloc_offset, + m->nb_clusters * s->cluster_size, + true); + if (ret < 0) { + return ret; + } + + BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_SPACE); + ret = bdrv_co_pwrite_zeroes(s->data_file, m->alloc_offset, + m->nb_clusters * s->cluster_size, + BDRV_REQ_NO_FALLBACK); + if (ret < 0) { + if (ret != -ENOTSUP && ret != -EAGAIN) { + return ret; + } + continue; + } + + trace_qcow2_skip_cow(qemu_coroutine_self(), m->offset, m->nb_clusters); + m->skip_cow = true; + } + return 0; +} + static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) @@ -2207,6 +2286,12 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes); } + /* Try to efficiently initialize the physical space with zeroes */ + ret = handle_alloc_space(bs, l2meta); + if (ret < 0) { + goto out_unlocked; + } + /* If we need to do COW, check if it's possible to merge the * writing of the guest data together with that of the COW regions. * If it's not possible (or not necessary) then write the diff --git a/block/qcow2.h b/block/qcow2.h index e873ae5..567375e 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -405,6 +405,12 @@ typedef struct QCowL2Meta */ Qcow2COWRegion cow_end; + /* + * Indicates that COW regions are already handled and do not require + * any more processing. + */ + bool skip_cow; + /** * The I/O vector with the data from the actual guest write request. * If non-NULL, this is meant to be merged together with the data diff --git a/block/trace-events b/block/trace-events index 79ccd8d..1e0653c 100644 --- a/block/trace-events +++ b/block/trace-events @@ -68,6 +68,7 @@ qcow2_writev_done_part(void *co, int cur_bytes) "co %p cur_bytes %d" qcow2_writev_data(void *co, uint64_t offset) "co %p offset 0x%" PRIx64 qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" +qcow2_skip_cow(void *co, uint64_t offset, int nb_clusters) "co %p offset 0x%" PRIx64 " nb_clusters %d" # qcow2-cluster.c qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d" -- cgit v1.1