From patchwork Thu Apr 27 10:12:59 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Laurent Vivier X-Patchwork-Id: 755942 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3wDCTP5591z9sNF for ; Thu, 27 Apr 2017 20:13:45 +1000 (AEST) Received: from localhost ([::1]:59763 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1d3gQh-0005ct-3C for incoming@patchwork.ozlabs.org; Thu, 27 Apr 2017 06:13:43 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:55840) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1d3gQ8-0005Zq-0X for qemu-devel@nongnu.org; Thu, 27 Apr 2017 06:13:09 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1d3gQ6-0008Rv-Ls for qemu-devel@nongnu.org; Thu, 27 Apr 2017 06:13:08 -0400 Received: from mx1.redhat.com ([209.132.183.28]:59744) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1d3gQ6-0008R9-D1 for qemu-devel@nongnu.org; Thu, 27 Apr 2017 06:13:06 -0400 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 6C7B861D15; Thu, 27 Apr 2017 10:13:05 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com 6C7B861D15 Authentication-Results: ext-mx10.extmail.prod.ext.phx2.redhat.com; dmarc=none (p=none dis=none) header.from=redhat.com Authentication-Results: ext-mx10.extmail.prod.ext.phx2.redhat.com; spf=pass smtp.mailfrom=lvivier@redhat.com DKIM-Filter: OpenDKIM Filter v2.11.0 mx1.redhat.com 6C7B861D15 Received: from thinkpad.redhat.com (unknown [10.36.118.57]) by smtp.corp.redhat.com (Postfix) with ESMTP id 1C7B689320; Thu, 27 Apr 2017 10:13:03 +0000 (UTC) From: Laurent Vivier To: Eduardo Habkost Date: Thu, 27 Apr 2017 12:12:59 +0200 Message-Id: <20170427101259.13798-3-lvivier@redhat.com> In-Reply-To: <20170427101259.13798-1-lvivier@redhat.com> References: <20170427101259.13798-1-lvivier@redhat.com> X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.39]); Thu, 27 Apr 2017 10:13:05 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PATCH v2 2/2] numa, spapr: equally distribute memory on nodes X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Laurent Vivier , Thomas Huth , qemu-devel@nongnu.org, David Gibson Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" When there are more nodes than memory available to put the minimum allowed memory by node, all the memory is put on the last node. This is because we put (ram_size / nb_numa_nodes) & ~((1 << mc->numa_mem_align_shift) - 1); on each node, and in this case the value is 0. This is particularly true with pseries, as the memory must be aligned to 256MB. To avoid this problem, this patch uses an error diffusion algorithm [1] to distribute equally the memory on nodes. Example: qemu-system-ppc64 -S -nographic -nodefaults -monitor stdio -m 1G -smp 8 \ -numa node -numa node -numa node \ -numa node -numa node -numa node Before: (qemu) info numa 6 nodes node 0 cpus: 0 6 node 0 size: 0 MB node 1 cpus: 1 7 node 1 size: 0 MB node 2 cpus: 2 node 2 size: 0 MB node 3 cpus: 3 node 3 size: 0 MB node 4 cpus: 4 node 4 size: 0 MB node 5 cpus: 5 node 5 size: 1024 MB After: (qemu) info numa 6 nodes node 0 cpus: 0 6 node 0 size: 0 MB node 1 cpus: 1 7 node 1 size: 256 MB node 2 cpus: 2 node 2 size: 0 MB node 3 cpus: 3 node 3 size: 256 MB node 4 cpus: 4 node 4 size: 256 MB node 5 cpus: 5 node 5 size: 256 MB [1] https://en.wikipedia.org/wiki/Error_diffusion Signed-off-by: Laurent Vivier --- hw/ppc/spapr.c | 21 ++++++++++++++++++++- include/hw/ppc/spapr.h | 3 ++- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 80d12d0..be498e2 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -3106,6 +3106,23 @@ static void spapr_pic_print_info(InterruptStatsProvider *obj, ics_pic_print_info(spapr->ics, mon); } +static void spapr_numa_auto_assign_ram(uint64_t *nodes, int nb_nodes, + ram_addr_t size) +{ + int i; + uint64_t usedmem = 0, node_mem; + uint64_t granularity = size / nb_nodes; + uint64_t propagate = 0; + + for (i = 0; i < nb_nodes - 1; i++) { + node_mem = (granularity + propagate) & ~(SPAPR_MEMORY_BLOCK_SIZE - 1); + propagate = granularity + propagate - node_mem; + nodes[i] = node_mem; + usedmem += node_mem; + } + nodes[i] = ram_size - usedmem; +} + static void spapr_machine_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -3162,7 +3179,8 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) * SPAPR_MEMORY_BLOCK_SIZE (256M) since that's the granularity * in which LMBs are represented and hot-added */ - mc->numa_mem_align_shift = 28; + mc->numa_mem_align_shift = SPAPR_MEMORY_BLOCK_SIZE_SHIFT; + mc->numa_auto_assign_ram = spapr_numa_auto_assign_ram; } static const TypeInfo spapr_machine_info = { @@ -3242,6 +3260,7 @@ static void spapr_machine_2_9_class_options(MachineClass *mc) { spapr_machine_2_10_class_options(mc); SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_2_9); + mc->numa_auto_assign_ram = NULL; } DEFINE_SPAPR_MACHINE(2_9, "2.9", false); diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 5802f88..8f4a588 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -653,7 +653,8 @@ int spapr_rtc_import_offset(sPAPRRTCState *rtc, int64_t legacy_offset); int spapr_rng_populate_dt(void *fdt); -#define SPAPR_MEMORY_BLOCK_SIZE (1 << 28) /* 256MB */ +#define SPAPR_MEMORY_BLOCK_SIZE_SHIFT 28 /* 256MB */ +#define SPAPR_MEMORY_BLOCK_SIZE (1 << SPAPR_MEMORY_BLOCK_SIZE_SHIFT) /* * This defines the maximum number of DIMM slots we can have for sPAPR