[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH V5 08/12] NUMA: set guest numa nodes memory policy
From: |
Wanlong Gao |
Subject: |
[Qemu-devel] [PATCH V5 08/12] NUMA: set guest numa nodes memory policy |
Date: |
Wed, 17 Jul 2013 17:29:29 +0800 |
Set the guest numa nodes memory policies using the mbind(2)
system call node by node.
After this patch, we are able to set guest nodes memory policies
through the QEMU options, this arms to solve the guest cross
nodes memory access performance issue.
And as you all know, if PCI-passthrough is used,
direct-attached-device uses DMA transfer between device and qemu process.
All pages of the guest will be pinned by get_user_pages().
KVM_ASSIGN_PCI_DEVICE ioctl
kvm_vm_ioctl_assign_device()
=>kvm_assign_device()
=> kvm_iommu_map_memslots()
=> kvm_iommu_map_pages()
=> kvm_pin_pages()
So, with direct-attached-device, all guest page's page count will be +1 and
any page migration will not work. AutoNUMA won't too.
So, we should set the guest nodes memory allocation policies before
the pages are really mapped.
Signed-off-by: Andre Przywara <address@hidden>
Signed-off-by: Wanlong Gao <address@hidden>
---
numa.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 86 insertions(+)
diff --git a/numa.c b/numa.c
index 736acbb..24c886b 100644
--- a/numa.c
+++ b/numa.c
@@ -28,6 +28,16 @@
#include "qapi-visit.h"
#include "qapi/opts-visitor.h"
#include "qapi/dealloc-visitor.h"
+#include "exec/memory.h"
+
+#ifdef CONFIG_NUMA
+#include <numa.h>
+#include <numaif.h>
+#ifndef MPOL_F_RELATIVE_NODES
+#define MPOL_F_RELATIVE_NODES (1 << 14)
+#define MPOL_F_STATIC_NODES (1 << 15)
+#endif
+#endif
QemuOptsList qemu_numa_opts = {
.name = "numa",
@@ -279,6 +289,75 @@ void set_numa_nodes(void)
}
}
+#ifdef CONFIG_NUMA
+static int node_parse_bind_mode(unsigned int nodeid)
+{
+ int bind_mode;
+
+ switch (numa_info[nodeid].flags & NODE_HOST_POLICY_MASK) {
+ case NODE_HOST_BIND:
+ bind_mode = MPOL_BIND;
+ break;
+ case NODE_HOST_INTERLEAVE:
+ bind_mode = MPOL_INTERLEAVE;
+ break;
+ case NODE_HOST_PREFERRED:
+ bind_mode = MPOL_PREFERRED;
+ break;
+ default:
+ bind_mode = MPOL_DEFAULT;
+ return bind_mode;
+ }
+
+ bind_mode |= (numa_info[nodeid].flags & NODE_HOST_RELATIVE) ?
+ MPOL_F_RELATIVE_NODES : MPOL_F_STATIC_NODES;
+
+ return bind_mode;
+}
+#endif
+
+static int set_node_mem_policy(unsigned int nodeid)
+{
+#ifdef CONFIG_NUMA
+ void *ram_ptr;
+ RAMBlock *block;
+ ram_addr_t len, ram_offset = 0;
+ int bind_mode;
+ int i;
+
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+ if (!strcmp(block->mr->name, "pc.ram")) {
+ break;
+ }
+ }
+
+ if (block->host == NULL)
+ return -1;
+
+ ram_ptr = block->host;
+ for (i = 0; i < nodeid; i++) {
+ len = numa_info[i].node_mem;
+ ram_offset += len;
+ }
+
+ len = numa_info[i].node_mem;
+ bind_mode = node_parse_bind_mode(i);
+
+ /* This is a workaround for a long standing bug in Linux'
+ * mbind implementation, which cuts off the last specified
+ * node. To stay compatible should this bug be fixed, we
+ * specify one more node and zero this one out.
+ */
+ clear_bit(numa_num_configured_nodes() + 1, numa_info[i].host_mem);
+ if (mbind(ram_ptr + ram_offset, len, bind_mode,
+ numa_info[i].host_mem, numa_num_configured_nodes() + 1, 0)) {
+ perror("mbind");
+ return -1;
+ }
+#endif
+ return 0;
+}
+
void set_numa_modes(void)
{
CPUState *cpu;
@@ -291,4 +370,11 @@ void set_numa_modes(void)
}
}
}
+
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (set_node_mem_policy(i) == -1) {
+ fprintf(stderr,
+ "qemu: can't set host memory policy for node%d\n", i);
+ }
+ }
}
--
1.8.3.2.634.g7a3187e
- [Qemu-devel] [PATCH V5 05/12] NUMA: Add Linux libnuma detection, (continued)
- [Qemu-devel] [PATCH V5 05/12] NUMA: Add Linux libnuma detection, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 07/12] NUMA: split out the common range parser, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 02/12] NUMA: split -numa option, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 06/12] NUMA: parse guest numa nodes memory policy, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 04/12] NUMA: Add numa_info structure to contain numa nodes info, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 08/12] NUMA: set guest numa nodes memory policy,
Wanlong Gao <=
- [Qemu-devel] [PATCH V5 09/12] NUMA: add qmp command set-mem-policy to set memory policy for NUMA node, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 12/12] NUMA: convert hmp command info_numa to use qmp command query_numa, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 10/12] NUMA: add hmp command set-mem-policy, Wanlong Gao, 2013/07/17
- [Qemu-devel] [PATCH V5 11/12] NUMA: add qmp command query-numa, Wanlong Gao, 2013/07/17