linux/drivers/base/node.c

261 lines
6.5 KiB
C
Raw Normal View History

/*
* drivers/base/node.c - basic Node class support
*/
#include <linux/sysdev.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/node.h>
#include <linux/hugetlb.h>
#include <linux/cpumask.h>
#include <linux/topology.h>
#include <linux/nodemask.h>
[PATCH] node hotplug: register cpu: remove node struct With Goto-san's patch, we can add new pgdat/node at runtime. I'm now considering node-hot-add with cpu + memory on ACPI. I found acpi container, which describes node, could evaluate cpu before memory. This means cpu-hot-add occurs before memory hot add. In most part, cpu-hot-add doesn't depend on node hot add. But register_cpu(), which creates symbolic link from node to cpu, requires that node should be onlined before register_cpu(). When a node is onlined, its pgdat should be there. This patch-set holds off creating symbolic link from node to cpu until node is onlined. This removes node arguments from register_cpu(). Now, register_cpu() requires 'struct node' as its argument. But the array of struct node is now unified in driver/base/node.c now (By Goto's node hotplug patch). We can get struct node in generic way. So, this argument is not necessary now. This patch also guarantees add cpu under node only when node is onlined. It is necessary for node-hot-add vs. cpu-hot-add patch following this. Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard to its 'struct node *root' argument. This patch removes it. Also modify callers of register_cpu()/unregister_cpu, whose args are changed by register-cpu-remove-node-struct patch. [Brice.Goglin@ens-lyon.org: fix it] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Brice Goglin <Brice.Goglin@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:41 +00:00
#include <linux/cpu.h>
static struct sysdev_class node_class = {
set_kset_name("node"),
};
static ssize_t node_read_cpumap(struct sys_device * dev, char * buf)
{
struct node *node_dev = to_node(dev);
cpumask_t mask = node_to_cpumask(node_dev->sysdev.id);
int len;
/* 2004/06/03: buf currently PAGE_SIZE, need > 1 char per 4 bits. */
BUILD_BUG_ON(MAX_NUMNODES/4 > PAGE_SIZE/2);
len = cpumask_scnprintf(buf, PAGE_SIZE-1, mask);
len += sprintf(buf + len, "\n");
return len;
}
static SYSDEV_ATTR(cpumap, S_IRUGO, node_read_cpumap, NULL);
#define K(x) ((x) << (PAGE_SHIFT - 10))
static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
{
int n;
int nid = dev->id;
struct sysinfo i;
struct page_state ps;
unsigned long inactive;
unsigned long active;
unsigned long free;
si_meminfo_node(&i, nid);
get_page_state_node(&ps, nid);
__get_zone_counts(&active, &inactive, &free, NODE_DATA(nid));
/* Check for negative values in these approximate counters */
if ((long)ps.nr_dirty < 0)
ps.nr_dirty = 0;
if ((long)ps.nr_writeback < 0)
ps.nr_writeback = 0;
n = sprintf(buf, "\n"
"Node %d MemTotal: %8lu kB\n"
"Node %d MemFree: %8lu kB\n"
"Node %d MemUsed: %8lu kB\n"
"Node %d Active: %8lu kB\n"
"Node %d Inactive: %8lu kB\n"
"Node %d HighTotal: %8lu kB\n"
"Node %d HighFree: %8lu kB\n"
"Node %d LowTotal: %8lu kB\n"
"Node %d LowFree: %8lu kB\n"
"Node %d Dirty: %8lu kB\n"
"Node %d Writeback: %8lu kB\n"
"Node %d FilePages: %8lu kB\n"
"Node %d Mapped: %8lu kB\n"
"Node %d AnonPages: %8lu kB\n"
"Node %d PageTables: %8lu kB\n"
"Node %d Slab: %8lu kB\n",
nid, K(i.totalram),
nid, K(i.freeram),
nid, K(i.totalram - i.freeram),
nid, K(active),
nid, K(inactive),
nid, K(i.totalhigh),
nid, K(i.freehigh),
nid, K(i.totalram - i.totalhigh),
nid, K(i.freeram - i.freehigh),
nid, K(ps.nr_dirty),
nid, K(ps.nr_writeback),
nid, K(node_page_state(nid, NR_FILE_PAGES)),
nid, K(node_page_state(nid, NR_FILE_MAPPED)),
nid, K(node_page_state(nid, NR_ANON_PAGES)),
nid, K(node_page_state(nid, NR_PAGETABLE)),
nid, K(node_page_state(nid, NR_SLAB)));
n += hugetlb_report_node_meminfo(nid, buf + n);
return n;
}
#undef K
static SYSDEV_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL);
static ssize_t node_read_numastat(struct sys_device * dev, char * buf)
{
unsigned long numa_hit, numa_miss, interleave_hit, numa_foreign;
unsigned long local_node, other_node;
int i, cpu;
pg_data_t *pg = NODE_DATA(dev->id);
numa_hit = 0;
numa_miss = 0;
interleave_hit = 0;
numa_foreign = 0;
local_node = 0;
other_node = 0;
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *z = &pg->node_zones[i];
for_each_online_cpu(cpu) {
[PATCH] node local per-cpu-pages This patch modifies the way pagesets in struct zone are managed. Each zone has a per-cpu array of pagesets. So any particular CPU has some memory in each zone structure which belongs to itself. Even if that CPU is not local to that zone. So the patch relocates the pagesets for each cpu to the node that is nearest to the cpu instead of allocating the pagesets in the (possibly remote) target zone. This means that the operations to manage pages on remote zone can be done with information available locally. We play a macro trick so that non-NUMA pmachines avoid the additional pointer chase on the page allocator fastpath. AIM7 benchmark on a 32 CPU SGI Altix w/o patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.68 100 484.6769 12.01 1.97 Fri Mar 25 11:01:42 2005 100 27140.46 89 271.4046 21.44 148.71 Fri Mar 25 11:02:04 2005 200 30792.02 82 153.9601 37.80 296.72 Fri Mar 25 11:02:42 2005 300 32209.27 81 107.3642 54.21 451.34 Fri Mar 25 11:03:37 2005 400 34962.83 78 87.4071 66.59 588.97 Fri Mar 25 11:04:44 2005 500 31676.92 75 63.3538 91.87 742.71 Fri Mar 25 11:06:16 2005 600 36032.69 73 60.0545 96.91 885.44 Fri Mar 25 11:07:54 2005 700 35540.43 77 50.7720 114.63 1024.28 Fri Mar 25 11:09:49 2005 800 33906.70 74 42.3834 137.32 1181.65 Fri Mar 25 11:12:06 2005 900 34120.67 73 37.9119 153.51 1325.26 Fri Mar 25 11:14:41 2005 1000 34802.37 74 34.8024 167.23 1465.26 Fri Mar 25 11:17:28 2005 with slab API changes and pageset patch: Tasks jobs/min jti jobs/min/task real cpu 1 485.00 100 485.0000 12.00 1.96 Fri Mar 25 11:46:18 2005 100 28000.96 89 280.0096 20.79 150.45 Fri Mar 25 11:46:39 2005 200 32285.80 79 161.4290 36.05 293.37 Fri Mar 25 11:47:16 2005 300 40424.15 84 134.7472 43.19 438.42 Fri Mar 25 11:47:59 2005 400 39155.01 79 97.8875 59.46 590.05 Fri Mar 25 11:48:59 2005 500 37881.25 82 75.7625 76.82 730.19 Fri Mar 25 11:50:16 2005 600 39083.14 78 65.1386 89.35 872.79 Fri Mar 25 11:51:46 2005 700 38627.83 77 55.1826 105.47 1022.46 Fri Mar 25 11:53:32 2005 800 39631.94 78 49.5399 117.48 1169.94 Fri Mar 25 11:55:30 2005 900 36903.70 79 41.0041 141.94 1310.78 Fri Mar 25 11:57:53 2005 1000 36201.23 77 36.2012 160.77 1458.31 Fri Mar 25 12:00:34 2005 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Shobhit Dayal <shobhit@calsoftinc.com> Signed-off-by: Shai Fultheim <Shai@Scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 00:14:47 +00:00
struct per_cpu_pageset *ps = zone_pcp(z,cpu);
numa_hit += ps->numa_hit;
numa_miss += ps->numa_miss;
numa_foreign += ps->numa_foreign;
interleave_hit += ps->interleave_hit;
local_node += ps->local_node;
other_node += ps->other_node;
}
}
return sprintf(buf,
"numa_hit %lu\n"
"numa_miss %lu\n"
"numa_foreign %lu\n"
"interleave_hit %lu\n"
"local_node %lu\n"
"other_node %lu\n",
numa_hit,
numa_miss,
numa_foreign,
interleave_hit,
local_node,
other_node);
}
static SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
static ssize_t node_read_distance(struct sys_device * dev, char * buf)
{
int nid = dev->id;
int len = 0;
int i;
/* buf currently PAGE_SIZE, need ~4 chars per node */
BUILD_BUG_ON(MAX_NUMNODES*4 > PAGE_SIZE/2);
for_each_online_node(i)
len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
len += sprintf(buf + len, "\n");
return len;
}
static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL);
/*
* register_node - Setup a driverfs device for a node.
* @num - Node number to use when creating the device.
*
* Initialize and register the node device.
*/
int register_node(struct node *node, int num, struct node *parent)
{
int error;
node->sysdev.id = num;
node->sysdev.cls = &node_class;
error = sysdev_register(&node->sysdev);
if (!error){
sysdev_create_file(&node->sysdev, &attr_cpumap);
sysdev_create_file(&node->sysdev, &attr_meminfo);
sysdev_create_file(&node->sysdev, &attr_numastat);
sysdev_create_file(&node->sysdev, &attr_distance);
}
return error;
}
/**
* unregister_node - unregister a node device
* @node: node going away
*
* Unregisters a node device @node. All the devices on the node must be
* unregistered before calling this function.
*/
void unregister_node(struct node *node)
{
sysdev_remove_file(&node->sysdev, &attr_cpumap);
sysdev_remove_file(&node->sysdev, &attr_meminfo);
sysdev_remove_file(&node->sysdev, &attr_numastat);
sysdev_remove_file(&node->sysdev, &attr_distance);
sysdev_unregister(&node->sysdev);
}
struct node node_devices[MAX_NUMNODES];
[PATCH] node hotplug: register cpu: remove node struct With Goto-san's patch, we can add new pgdat/node at runtime. I'm now considering node-hot-add with cpu + memory on ACPI. I found acpi container, which describes node, could evaluate cpu before memory. This means cpu-hot-add occurs before memory hot add. In most part, cpu-hot-add doesn't depend on node hot add. But register_cpu(), which creates symbolic link from node to cpu, requires that node should be onlined before register_cpu(). When a node is onlined, its pgdat should be there. This patch-set holds off creating symbolic link from node to cpu until node is onlined. This removes node arguments from register_cpu(). Now, register_cpu() requires 'struct node' as its argument. But the array of struct node is now unified in driver/base/node.c now (By Goto's node hotplug patch). We can get struct node in generic way. So, this argument is not necessary now. This patch also guarantees add cpu under node only when node is onlined. It is necessary for node-hot-add vs. cpu-hot-add patch following this. Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard to its 'struct node *root' argument. This patch removes it. Also modify callers of register_cpu()/unregister_cpu, whose args are changed by register-cpu-remove-node-struct patch. [Brice.Goglin@ens-lyon.org: fix it] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Brice Goglin <Brice.Goglin@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:41 +00:00
/*
* register cpu under node
*/
int register_cpu_under_node(unsigned int cpu, unsigned int nid)
{
if (node_online(nid)) {
struct sys_device *obj = get_cpu_sysdev(cpu);
if (!obj)
return 0;
return sysfs_create_link(&node_devices[nid].sysdev.kobj,
&obj->kobj,
kobject_name(&obj->kobj));
}
return 0;
}
int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
{
if (node_online(nid)) {
struct sys_device *obj = get_cpu_sysdev(cpu);
if (obj)
sysfs_remove_link(&node_devices[nid].sysdev.kobj,
kobject_name(&obj->kobj));
}
return 0;
}
int register_one_node(int nid)
{
int error = 0;
[PATCH] node hotplug: register cpu: remove node struct With Goto-san's patch, we can add new pgdat/node at runtime. I'm now considering node-hot-add with cpu + memory on ACPI. I found acpi container, which describes node, could evaluate cpu before memory. This means cpu-hot-add occurs before memory hot add. In most part, cpu-hot-add doesn't depend on node hot add. But register_cpu(), which creates symbolic link from node to cpu, requires that node should be onlined before register_cpu(). When a node is onlined, its pgdat should be there. This patch-set holds off creating symbolic link from node to cpu until node is onlined. This removes node arguments from register_cpu(). Now, register_cpu() requires 'struct node' as its argument. But the array of struct node is now unified in driver/base/node.c now (By Goto's node hotplug patch). We can get struct node in generic way. So, this argument is not necessary now. This patch also guarantees add cpu under node only when node is onlined. It is necessary for node-hot-add vs. cpu-hot-add patch following this. Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard to its 'struct node *root' argument. This patch removes it. Also modify callers of register_cpu()/unregister_cpu, whose args are changed by register-cpu-remove-node-struct patch. [Brice.Goglin@ens-lyon.org: fix it] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Brice Goglin <Brice.Goglin@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:41 +00:00
int cpu;
if (node_online(nid)) {
int p_node = parent_node(nid);
struct node *parent = NULL;
if (p_node != nid)
parent = &node_devices[p_node];
error = register_node(&node_devices[nid], nid, parent);
[PATCH] node hotplug: register cpu: remove node struct With Goto-san's patch, we can add new pgdat/node at runtime. I'm now considering node-hot-add with cpu + memory on ACPI. I found acpi container, which describes node, could evaluate cpu before memory. This means cpu-hot-add occurs before memory hot add. In most part, cpu-hot-add doesn't depend on node hot add. But register_cpu(), which creates symbolic link from node to cpu, requires that node should be onlined before register_cpu(). When a node is onlined, its pgdat should be there. This patch-set holds off creating symbolic link from node to cpu until node is onlined. This removes node arguments from register_cpu(). Now, register_cpu() requires 'struct node' as its argument. But the array of struct node is now unified in driver/base/node.c now (By Goto's node hotplug patch). We can get struct node in generic way. So, this argument is not necessary now. This patch also guarantees add cpu under node only when node is onlined. It is necessary for node-hot-add vs. cpu-hot-add patch following this. Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard to its 'struct node *root' argument. This patch removes it. Also modify callers of register_cpu()/unregister_cpu, whose args are changed by register-cpu-remove-node-struct patch. [Brice.Goglin@ens-lyon.org: fix it] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Brice Goglin <Brice.Goglin@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 09:53:41 +00:00
/* link cpu under this node */
for_each_present_cpu(cpu) {
if (cpu_to_node(cpu) == nid)
register_cpu_under_node(cpu, nid);
}
}
return error;
}
void unregister_one_node(int nid)
{
unregister_node(&node_devices[nid]);
}
static int __init register_node_type(void)
{
return sysdev_class_register(&node_class);
}
postcore_initcall(register_node_type);