From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:54841) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dDYs1-0004Nm-Ca for qemu-devel@nongnu.org; Wed, 24 May 2017 12:10:46 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1dDYrx-0001ko-Ad for qemu-devel@nongnu.org; Wed, 24 May 2017 12:10:45 -0400 Received: from [62.254.189.133] (port=38662 helo=centos.localdomain) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dDYrw-0001dZ-Up for qemu-devel@nongnu.org; Wed, 24 May 2017 12:10:41 -0400 From: Felipe Franciosi Date: Wed, 24 May 2017 17:09:59 +0100 Message-Id: <1495642203-12702-1-git-send-email-felipe@nutanix.com> Subject: [Qemu-devel] [PATCH 0/4] migration: autoconverge counter fixes List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Xu , Juan Quintela , "Jason J. Herne" , amit Shah , "Dr. David Alan Gilbert" Cc: Malcolm Crossley , "qemu-devel@nongnu.org" , Felipe Franciosi As discussed in the ML [1], there are some issues around the way ram.c accounts for transferred data and dirty pages for the auto convergence calculations. The patches in these series fix that by: - Keeping bytes_xfer_prev zeroed until it's used - Ensure bytes_xfer_* counters are accounted for the same period as dirty_pages_* counters - Start throttling in a consistent manner [1] http://lists.nongnu.org/archive/html/qemu-devel/2017-05/msg05524.html Felipe Franciosi (4): migration: keep bytes_xfer_prev init'd to zero migration: set dirty_pages_rate before autoconverge logic migration: set bytes_xfer_* outside of autoconverge logic migration: use dirty_rate_high_cnt more aggressively migration/ram.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) -- 1.9.5