From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:48284) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cDokr-0002n5-CD for qemu-devel@nongnu.org; Mon, 05 Dec 2016 03:36:10 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cDokn-0000I6-CI for qemu-devel@nongnu.org; Mon, 05 Dec 2016 03:36:09 -0500 From: zhanghailiang Date: Mon, 5 Dec 2016 16:35:03 +0800 Message-ID: <1480926904-17596-6-git-send-email-zhang.zhanghailiang@huawei.com> In-Reply-To: <1480926904-17596-1-git-send-email-zhang.zhanghailiang@huawei.com> References: <1480926904-17596-1-git-send-email-zhang.zhanghailiang@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Subject: [Qemu-devel] [PATCH RFC v2 5/6] replication: Implement block replication for shared disk case List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org, qemu-block@nongnu.org Cc: stefanha@redhat.com, kwolf@redhat.com, mreitz@redhat.com, pbonzini@redhat.com, wency@cn.fujitsu.com, xiecl.fnst@cn.fujitsu.com, zhanghailiang , Zhang Chen Just as the scenario of non-shared disk block replication, we are going to implement block replication from many basic blocks that are already in QEMU. The architecture is: virtio-blk || .---------- / || | Secondary / || '---------- / || virtio-blk / || | | || replication(5) | NBD --------> NBD (2) | | client || server ---> hidden disk <-- active disk(4) | ^ || | | replication(1) || | | | || | | +-----------------' || | (3) |drive-backup sync=none || | --------. | +-----------------+ || | Primary | | | || backing | --------' | | || | V | | +-------------------------------------------+ | | shared disk | <----------+ +-------------------------------------------+ 1) Primary writes will read original data and forward it to Secondary QEMU. 2) The hidden-disk is created automatically. It buffers the original content that is modified by the primary VM. It should also be an empty disk, and the driver supports bdrv_make_empty() and backing file. 3) Primary write requests will be written to Shared disk. 4) Secondary write requests will be buffered in the active disk and it will overwrite the existing sector content in the buffer. Signed-off-by: zhanghailiang Signed-off-by: Wen Congyang Signed-off-by: Zhang Chen --- block/replication.c | 48 ++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 42 insertions(+), 6 deletions(-) diff --git a/block/replication.c b/block/replication.c index 6574cc2..f416ca5 100644 --- a/block/replication.c +++ b/block/replication.c @@ -233,7 +233,7 @@ static coroutine_fn int replication_co_readv(BlockDriverState *bs, QEMUIOVector *qiov) { BDRVReplicationState *s = bs->opaque; - BdrvChild *child = s->secondary_disk; + BdrvChild *child = s->is_shared_disk ? s->primary_disk : s->secondary_disk; BlockJob *job = NULL; CowRequest req; int ret; @@ -415,7 +415,12 @@ static void backup_job_completed(void *opaque, int ret) s->error = -EIO; } - backup_job_cleanup(bs); + if (s->mode == REPLICATION_MODE_PRIMARY) { + s->replication_state = BLOCK_REPLICATION_DONE; + s->error = 0; + } else { + backup_job_cleanup(bs); + } } static bool check_top_bs(BlockDriverState *top_bs, BlockDriverState *bs) @@ -467,6 +472,19 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, switch (s->mode) { case REPLICATION_MODE_PRIMARY: + if (s->is_shared_disk) { + job = backup_job_create(NULL, s->primary_disk->bs, bs, 0, + MIRROR_SYNC_MODE_NONE, NULL, false, BLOCKDEV_ON_ERROR_REPORT, + BLOCKDEV_ON_ERROR_REPORT, BLOCK_JOB_INTERNAL, + backup_job_completed, bs, NULL, &local_err); + if (local_err) { + error_propagate(errp, local_err); + backup_job_cleanup(bs); + aio_context_release(aio_context); + return; + } + block_job_start(job); + } break; case REPLICATION_MODE_SECONDARY: s->active_disk = bs->file; @@ -485,7 +503,8 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, } s->secondary_disk = s->hidden_disk->bs->backing; - if (!s->secondary_disk->bs || !bdrv_has_blk(s->secondary_disk->bs)) { + if (!s->secondary_disk->bs || + (!s->is_shared_disk && !bdrv_has_blk(s->secondary_disk->bs))) { error_setg(errp, "The secondary disk doesn't have block backend"); aio_context_release(aio_context); return; @@ -580,11 +599,24 @@ static void replication_do_checkpoint(ReplicationState *rs, Error **errp) switch (s->mode) { case REPLICATION_MODE_PRIMARY: + if (s->is_shared_disk) { + if (!s->primary_disk->bs->job) { + error_setg(errp, "Primary backup job was cancelled" + " unexpectedly"); + break; + } + + backup_do_checkpoint(s->primary_disk->bs->job, &local_err); + if (local_err) { + error_propagate(errp, local_err); + } + } break; case REPLICATION_MODE_SECONDARY: if (!s->is_shared_disk) { if (!s->secondary_disk->bs->job) { - error_setg(errp, "Backup job was cancelled unexpectedly"); + error_setg(errp, "Secondary backup job was cancelled" + " unexpectedly"); break; } backup_do_checkpoint(s->secondary_disk->bs->job, &local_err); @@ -663,8 +695,12 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp) switch (s->mode) { case REPLICATION_MODE_PRIMARY: - s->replication_state = BLOCK_REPLICATION_DONE; - s->error = 0; + if (s->is_shared_disk && s->primary_disk->bs->job) { + block_job_cancel(s->primary_disk->bs->job); + } else { + s->replication_state = BLOCK_REPLICATION_DONE; + s->error = 0; + } break; case REPLICATION_MODE_SECONDARY: /* -- 1.8.3.1