3bfe57165b
When there are more nodes than available memory 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.
We introduce numa_auto_assign_ram() function in MachineClass
to keep compatibility between machine type versions.
The legacy function is used with pseries-2.9, pc-q35-2.9 and
pc-i440fx-2.9 (and previous), the new one with all others.
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 <lvivier@redhat.com>
Message-Id: <20170502162955.1610-2-lvivier@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
[ehabkost: s/ram_size/size/ at numa_default_auto_assign_ram()]
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
46 lines
1.4 KiB
C
46 lines
1.4 KiB
C
#ifndef SYSEMU_NUMA_H
|
|
#define SYSEMU_NUMA_H
|
|
|
|
#include "qemu/bitmap.h"
|
|
#include "qemu/option.h"
|
|
#include "sysemu/sysemu.h"
|
|
#include "sysemu/hostmem.h"
|
|
#include "hw/boards.h"
|
|
|
|
extern int nb_numa_nodes; /* Number of NUMA nodes */
|
|
extern bool have_numa_distance;
|
|
|
|
struct numa_addr_range {
|
|
ram_addr_t mem_start;
|
|
ram_addr_t mem_end;
|
|
QLIST_ENTRY(numa_addr_range) entry;
|
|
};
|
|
|
|
struct node_info {
|
|
uint64_t node_mem;
|
|
unsigned long *node_cpu;
|
|
struct HostMemoryBackend *node_memdev;
|
|
bool present;
|
|
QLIST_HEAD(, numa_addr_range) addr; /* List to store address ranges */
|
|
uint8_t distance[MAX_NODES];
|
|
};
|
|
|
|
extern NodeInfo numa_info[MAX_NODES];
|
|
void parse_numa_opts(MachineClass *mc);
|
|
void numa_post_machine_init(void);
|
|
void query_numa_node_mem(uint64_t node_mem[]);
|
|
extern QemuOptsList qemu_numa_opts;
|
|
void numa_set_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node);
|
|
void numa_unset_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node);
|
|
uint32_t numa_get_node(ram_addr_t addr, Error **errp);
|
|
void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
|
|
int nb_nodes, ram_addr_t size);
|
|
void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
|
|
int nb_nodes, ram_addr_t size);
|
|
|
|
|
|
/* on success returns node index in numa_info,
|
|
* on failure returns nb_numa_nodes */
|
|
int numa_get_node_for_cpu(int idx);
|
|
#endif
|