From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:49033) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cpvWV-0002jw-RR for qemu-devel@nongnu.org; Mon, 20 Mar 2017 07:30:52 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cpvWS-0004d9-1m for qemu-devel@nongnu.org; Mon, 20 Mar 2017 07:30:51 -0400 Date: Mon, 20 Mar 2017 11:30:42 +0000 From: "Daniel P. Berrange" Message-ID: <20170320113042.GG3792@redhat.com> Reply-To: "Daniel P. Berrange" References: <20170320112426.4030-1-lvivier@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <20170320112426.4030-1-lvivier@redhat.com> Subject: Re: [Qemu-devel] [PATCH] numa, spapr: align default numa node memory size to 256MB List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Laurent Vivier Cc: Eduardo Habkost , Thomas Huth , qemu-ppc@nongnu.org, qemu-devel@nongnu.org, David Gibson On Mon, Mar 20, 2017 at 12:24:26PM +0100, Laurent Vivier wrote: > Since commit 224245b ("spapr: Add LMB DR connectors"), NUMA node > memory size must be aligned to 256MB (SPAPR_MEMORY_BLOCK_SIZE). That commit only enabled the feature for the pseries-2.5 machine type several releases back now... > But when "-numa" option is provided without "mem" parameter, > the memory is equally divided between nodes, but 8MB aligned. > This can be not valid for pseries. > > In that case we can have: > $ ./ppc64-softmmu/qemu-system-ppc64 -m 4G -numa node -numa node -numa node > qemu-system-ppc64: Node 0 memory size 0x55000000 is not aligned to 256 MiB > > With this patch, we have: > (qemu) info numa > 3 nodes > node 0 cpus: 0 > node 0 size: 1280 MB > node 1 cpus: > node 1 size: 1280 MB > node 2 cpus: > node 2 size: 1536 MB > > Signed-off-by: Laurent Vivier > --- > dtc | 2 +- > numa.c | 14 +++++++++----- > 2 files changed, 10 insertions(+), 6 deletions(-) > > diff --git a/dtc b/dtc > index 558cd81..fa8bc7f 160000 > --- a/dtc > +++ b/dtc > @@ -1 +1 @@ > -Subproject commit 558cd81bdd432769b59bff01240c44f82cfb1a9d > +Subproject commit fa8bc7f928ac25f23532afc8beb2073efc8fb063 This looks unrelated > diff --git a/numa.c b/numa.c > index e01cb54..a911284 100644 > --- a/numa.c > +++ b/numa.c > @@ -337,15 +337,19 @@ void parse_numa_opts(MachineClass *mc) > } > if (i == nb_numa_nodes) { > uint64_t usedmem = 0; > - > - /* On Linux, each node's border has to be 8MB aligned, > - * the final node gets the rest. > - */ > +#if defined(TARGET_PPC64) > + /* pseries requests each node's border has to be 256 MB aligned */ > + const uint64_t numa_mem_align_mask = ~((1 << 28UL) - 1); > +#else but here you're forcing 256 MB alignement for all machine types. This is surely breaking machine ABI compat for anyone who previously used -numa with QEMU and upgrades to new QEMU expecting the same ABI. Regards, Daniel -- |: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :| |: http://libvirt.org -o- http://virt-manager.org :| |: http://entangle-photo.org -o- http://search.cpan.org/~danberr/ :|