From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37766) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1XDCgT-0000GD-Nk for qemu-devel@nongnu.org; Fri, 01 Aug 2014 09:15:51 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1XDCgO-0000S3-8L for qemu-devel@nongnu.org; Fri, 01 Aug 2014 09:15:45 -0400 Received: from mail-we0-x236.google.com ([2a00:1450:400c:c03::236]:45947) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1XDCgN-0000QT-Vv for qemu-devel@nongnu.org; Fri, 01 Aug 2014 09:15:40 -0400 Received: by mail-we0-f182.google.com with SMTP id k48so4292679wev.13 for ; Fri, 01 Aug 2014 06:15:37 -0700 (PDT) Date: Fri, 1 Aug 2014 14:15:32 +0100 From: Stefan Hajnoczi Message-ID: <20140801131532.GA11091@stefanha-thinkpad.redhat.com> References: <1404738953-13221-1-git-send-email-stefanha@redhat.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="x+6KMIRAuhnl3hBn" Content-Disposition: inline In-Reply-To: <1404738953-13221-1-git-send-email-stefanha@redhat.com> Subject: Re: [Qemu-devel] [PATCH v3 0/2] coroutine: dynamically scale pool size List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: Kevin Wolf , ming.lei@canonical.com, qemu-devel@nongnu.org, Markus Armbruster , Paolo Bonzini , =?iso-8859-1?Q?Llu=EDs?= Vilanova --x+6KMIRAuhnl3hBn Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jul 07, 2014 at 03:15:51PM +0200, Stefan Hajnoczi wrote: > v3: > * Use COROUTINE_POOL_RESERVATION constant in block.c [Lluis] >=20 > v2: > * Assert that callers never reduce pool below default size [eblake] >=20 > The coroutine pool reuses exited coroutines to make qemu_coroutine_create= () > cheap. The size of the pool is capped to prevent it from hogging memory = after > a period of high coroutine activity. Previously the max size was hardcod= ed to > 64 but this doesn't scale with guest size. >=20 > A guest with lots of disks can do more parallel I/O and therefore require= s a > larger coroutine pool size. This series tries to solve the problem by sc= aling > pool size according to the number of drives. >=20 > Ming has confirmed that this patch series, together with his block plug/u= nplug > series, solves the dataplane performance regression in QEMU 2.1. >=20 > Stefan Hajnoczi (2): > coroutine: make pool size dynamic > block: bump coroutine pool size for drives >=20 > block.c | 6 ++++++ > include/block/coroutine.h | 11 +++++++++++ > qemu-coroutine.c | 26 +++++++++++++++++++++++--- > 3 files changed, 40 insertions(+), 3 deletions(-) Thanks, applied to my block-next tree: https://github.com/stefanha/qemu/commits/block Stefan --x+6KMIRAuhnl3hBn Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQEcBAEBAgAGBQJT25L0AAoJEJykq7OBq3PICRYH/jArJWhOH9WzIuIthtGDZu52 QPv7tMsXkzpAfwGszF/CFnm3JhUke2ZVFyRo/qJ4gDWaUt1QS2d4GGkR1AMiuWoe 8xTUG3/bv16tsZD+hom93VQLEXy92CzCmhzII9rNJNjTYGUvGNoJOgmZXcEQWlaX DIjRUIl885tBQxGanGEWwK/23dHWj9wH4fmq6rE0WdQ7PdTbfi9ooFv9DMQSlnCK z+DhilkQ7vxNfFGq6+XybditaOmSp/hGVqXTgCwHQqvq8LbYb5/MIbnNnUpgQ4AL 5Y0YB/HUWNjzZ18gLCqbzkgiPeetThi/vOTRoAS9k6gsZkVloW6OFNf6wk3l1KE= =zDkk -----END PGP SIGNATURE----- --x+6KMIRAuhnl3hBn--