From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:44835) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Voz7x-0001qg-WD for qemu-devel@nongnu.org; Fri, 06 Dec 2013 12:23:52 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Voz7r-0001uf-V0 for qemu-devel@nongnu.org; Fri, 06 Dec 2013 12:23:45 -0500 Received: from mx1.redhat.com ([209.132.183.28]:55964) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Voz7r-0001uX-NL for qemu-devel@nongnu.org; Fri, 06 Dec 2013 12:23:39 -0500 Received: from int-mx10.intmail.prod.int.phx2.redhat.com (int-mx10.intmail.prod.int.phx2.redhat.com [10.5.11.23]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id rB6HNcfg017051 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Fri, 6 Dec 2013 12:23:38 -0500 From: Kevin Wolf Date: Fri, 6 Dec 2013 18:22:55 +0100 Message-Id: <1386350580-5666-15-git-send-email-kwolf@redhat.com> In-Reply-To: <1386350580-5666-1-git-send-email-kwolf@redhat.com> References: <1386350580-5666-1-git-send-email-kwolf@redhat.com> Subject: [Qemu-devel] [RFC PATCH 14/19] block: Generalise and optimise COR serialisation List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: kwolf@redhat.com, pbonzini@redhat.com, armbru@redhat.com, stefanha@redhat.com Change the API so that specific requests can be marked serialising. Only these requests are checked for overlaps then. This means that during a Copy on Read operation, not all requests overlapping other requests are serialised any more, but only those that actually overlap with the specific COR request. Also remove COR from function and variable names because this functionality can be useful in other contexts. Signed-off-by: Kevin Wolf --- block.c | 40 +++++++++++++++++++++++++--------------- include/block/block_int.h | 5 +++-- 2 files changed, 28 insertions(+), 17 deletions(-) diff --git a/block.c b/block.c index 0b1f08a..53c19a8 100644 --- a/block.c +++ b/block.c @@ -2005,6 +2005,10 @@ int bdrv_commit_all(void) */ static void tracked_request_end(BdrvTrackedRequest *req) { + if (req->serialising) { + req->bs->serialising_in_flight--; + } + QLIST_REMOVE(req, list); qemu_co_queue_restart_all(&req->wait_queue); } @@ -2023,6 +2027,7 @@ static void tracked_request_begin(BdrvTrackedRequest *req, .bytes = bytes, .is_write = is_write, .co = qemu_coroutine_self(), + .serialising = false, }; qemu_co_queue_init(&req->wait_queue); @@ -2030,6 +2035,14 @@ static void tracked_request_begin(BdrvTrackedRequest *req, QLIST_INSERT_HEAD(&bs->tracked_requests, req, list); } +static void mark_request_serialising(BdrvTrackedRequest *req) +{ + if (!req->serialising) { + req->bs->serialising_in_flight++; + req->serialising = true; + } +} + /** * Round a region to cluster boundaries */ @@ -2082,26 +2095,31 @@ static bool tracked_request_overlaps(BdrvTrackedRequest *req, return true; } -static void coroutine_fn wait_for_overlapping_requests(BlockDriverState *bs, - BdrvTrackedRequest *self, int64_t offset, unsigned int bytes) +static void coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self) { + BlockDriverState *bs = self->bs; BdrvTrackedRequest *req; int64_t cluster_offset; unsigned int cluster_bytes; bool retry; + if (!bs->serialising_in_flight) { + return; + } + /* If we touch the same cluster it counts as an overlap. This guarantees * that allocating writes will be serialized and not race with each other * for the same cluster. For example, in copy-on-read it ensures that the * CoR read and write operations are atomic and guest writes cannot * interleave between them. */ - round_bytes_to_clusters(bs, offset, bytes, &cluster_offset, &cluster_bytes); + round_bytes_to_clusters(bs, self->offset, self->bytes, + &cluster_offset, &cluster_bytes); do { retry = false; QLIST_FOREACH(req, &bs->tracked_requests, list) { - if (req == self) { + if (req == self || (!req->serialising && !self->serialising)) { continue; } if (tracked_request_overlaps(req, cluster_offset, cluster_bytes)) { @@ -2676,12 +2694,10 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, /* Handle Copy on Read and associated serialisation */ if (flags & BDRV_REQ_COPY_ON_READ) { - bs->copy_on_read_in_flight++; + mark_request_serialising(req); } - if (bs->copy_on_read_in_flight) { - wait_for_overlapping_requests(bs, req, offset, bytes); - } + wait_serialising_requests(req); if (flags & BDRV_REQ_COPY_ON_READ) { int pnum; @@ -2729,10 +2745,6 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, } out: - if (flags & BDRV_REQ_COPY_ON_READ) { - bs->copy_on_read_in_flight--; - } - return ret; } @@ -2886,9 +2898,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0); assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0); - if (bs->copy_on_read_in_flight) { - wait_for_overlapping_requests(bs, req, offset, bytes); - } + wait_serialising_requests(req); ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req); diff --git a/include/block/block_int.h b/include/block/block_int.h index ec4f121..6ba058a 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -59,6 +59,7 @@ typedef struct BdrvTrackedRequest { int64_t offset; unsigned int bytes; bool is_write; + bool serialising; QLIST_ENTRY(BdrvTrackedRequest) list; Coroutine *co; /* owner, used for deadlock detection */ CoQueue wait_queue; /* coroutines blocked on this request */ @@ -273,8 +274,8 @@ struct BlockDriverState { /* Callback before write request is processed */ NotifierWithReturnList before_write_notifiers; - /* number of in-flight copy-on-read requests */ - unsigned int copy_on_read_in_flight; + /* number of in-flight serialising requests */ + unsigned int serialising_in_flight; /* I/O throttling */ ThrottleState throttle_state; -- 1.8.1.4