From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:54223) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bS9Lc-0008K4-UK for qemu-devel@nongnu.org; Tue, 26 Jul 2016 16:53:05 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bS9Lb-0004yy-VR for qemu-devel@nongnu.org; Tue, 26 Jul 2016 16:53:04 -0400 From: Jeff Cody Date: Tue, 26 Jul 2016 16:52:53 -0400 Message-Id: <1469566373-9953-3-git-send-email-jcody@redhat.com> In-Reply-To: <1469566373-9953-1-git-send-email-jcody@redhat.com> References: <1469566373-9953-1-git-send-email-jcody@redhat.com> Subject: [Qemu-devel] [PULL 2/2] mirror: double performance of the bulk stage if the disc is full List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-block@nongnu.org Cc: peter.maydell@linaro.org, jcody@redhat.com, qemu-devel@nongnu.org From: Vladimir Sementsov-Ogievskiy Mirror can do up to 16 in-flight requests, but actually on full copy (the whole source disk is non-zero) in-flight is always 1. This happens as the request is not limited in size: the data occupies maximum available capacity of s->buf. The patch limits the size of the request to some artificial constant (1 Mb here), which is not that big or small. This effectively enables back parallelism in mirror code as it was designed. The result is important: the time to migrate 10 Gb disk is reduced from ~350 sec to 170 sec. Signed-off-by: Vladimir Sementsov-Ogievskiy Signed-off-by: Denis V. Lunev Reviewed-by: Max Reitz Reviewed-by: Jeff Cody Message-id: 1468516741-82174-1-git-send-email-vsementsov@virtuozzo.com CC: Stefan Hajnoczi CC: Fam Zheng CC: Kevin Wolf CC: Max Reitz CC: Jeff Cody CC: Eric Blake Signed-off-by: Jeff Cody --- block/mirror.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index 69a1a7c..d6034f5 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -23,7 +23,9 @@ #define SLICE_TIME 100000000ULL /* ns */ #define MAX_IN_FLIGHT 16 -#define DEFAULT_MIRROR_BUF_SIZE (10 << 20) +#define MAX_IO_SECTORS ((1 << 20) >> BDRV_SECTOR_BITS) /* 1 Mb */ +#define DEFAULT_MIRROR_BUF_SIZE \ + (MAX_IN_FLIGHT * MAX_IO_SECTORS * BDRV_SECTOR_SIZE) /* The mirroring buffer is a list of granularity-sized chunks. * Free chunks are organized in a list. @@ -325,6 +327,8 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) int64_t end = s->bdev_length / BDRV_SECTOR_SIZE; 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_sectors = MAX((s->buf_size >> BDRV_SECTOR_BITS) / MAX_IN_FLIGHT, + MAX_IO_SECTORS); sector_num = hbitmap_iter_next(&s->hbi); if (sector_num < 0) { @@ -388,7 +392,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) nb_chunks * sectors_per_chunk, &io_sectors, &file); if (ret < 0) { - io_sectors = nb_chunks * sectors_per_chunk; + io_sectors = MIN(nb_chunks * sectors_per_chunk, max_io_sectors); + } else if (ret & BDRV_BLOCK_DATA) { + io_sectors = MIN(io_sectors, max_io_sectors); } io_sectors -= io_sectors % sectors_per_chunk; -- 1.9.3