From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34846) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YH79s-0004Ke-Tk for qemu-devel@nongnu.org; Fri, 30 Jan 2015 03:42:37 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1YH79r-0002a2-Ks for qemu-devel@nongnu.org; Fri, 30 Jan 2015 03:42:32 -0500 Received: from mailhub.sw.ru ([195.214.232.25]:24183 helo=relay.sw.ru) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YH79r-0002YA-6s for qemu-devel@nongnu.org; Fri, 30 Jan 2015 03:42:31 -0500 From: "Denis V. Lunev" Date: Fri, 30 Jan 2015 11:42:17 +0300 Message-Id: <1422607337-25335-8-git-send-email-den@openvz.org> In-Reply-To: <1422607337-25335-1-git-send-email-den@openvz.org> References: <1422607337-25335-1-git-send-email-den@openvz.org> Subject: [Qemu-devel] [PATCH 7/7] block/raw-posix: set max_write_zeroes to INT_MAX for regular files List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Kevin Wolf , Fam Zheng , Peter Lieven , qemu-devel@nongnu.org, Stefan Hajnoczi , "Denis V. Lunev" fallocate() works fine and could handle properly with arbitrary size requests. There is no sense to reduce the amount of space to fallocate. The bigger is the size, the better is the performance as the amount of journal updates is reduced. The patch changes behavior for both generic filesystem and XFS codepaths, which are different in handle_aiocb_write_zeroes. The implementation of fallocate and xfsctl(XFS_IOC_ZERO_RANGE) for XFS are exactly the same thus the change is fine for both ways. Signed-off-by: Denis V. Lunev Reviewed-by: Max Reitz CC: Kevin Wolf CC: Stefan Hajnoczi CC: Peter Lieven CC: Fam Zheng --- block/raw-posix.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/block/raw-posix.c b/block/raw-posix.c index 7b42f37..933c778 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -293,6 +293,20 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp) } } +static void raw_probe_max_write_zeroes(BlockDriverState *bs) +{ + BDRVRawState *s = bs->opaque; + struct stat st; + + if (fstat(s->fd, &st) < 0) { + return; /* no problem, keep default value */ + } + if (!S_ISREG(st.st_mode) || !s->discard_zeroes) { + return; + } + bs->bl.max_write_zeroes = INT_MAX; +} + static void raw_parse_flags(int bdrv_flags, int *open_flags) { assert(open_flags != NULL); @@ -600,6 +614,7 @@ static int raw_reopen_prepare(BDRVReopenState *state, /* Fail already reopen_prepare() if we can't get a working O_DIRECT * alignment with the new fd. */ if (raw_s->fd != -1) { + raw_probe_max_write_zeroes(state->bs); raw_probe_alignment(state->bs, raw_s->fd, &local_err); if (local_err) { qemu_close(raw_s->fd); @@ -653,6 +668,8 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) raw_probe_alignment(bs, s->fd, errp); bs->bl.opt_mem_alignment = s->buf_align; + + raw_probe_max_write_zeroes(bs); } static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb) -- 1.9.1