This patch add a new api PR_NUMA_BALANCING in prctl.
A large number of page faults will cause performance loss when numa balancing
is performing. Thus those processes which care about worst-case performance
need numa balancing disabled. Others, on the contrary, allow a temporary
performance loss in exchange for higher average performance, so enable numa
balancing is better for them.
Numa balancing can only be controlled globally by /proc/sys/kernel/numa_balancing.
Due to the above case, we want to disable/enable numa_balancing per-process
instead.
Add numa_balancing under mm_struct. Then use it in task_tick_numa.
Set per-process numa balancing:
prctl(PR_NUMA_BALANCING, PR_SET_NUMAB_DISABLE); //disable
prctl(PR_NUMA_BALANCING, PR_SET_NUMAB_ENABLE); //enable
prctl(PR_NUMA_BALANCING, PR_SET_NUMAB_DEFAULT); //follow global
Get numa_balancing state:
prctl(PR_NUMA_BALANCING, PR_GET_NUMAB, &ret);
cat /proc/<pid>/status | grep NumaB_enabled
Signed-off-by: Gang Li <ligang.bdlg@xxxxxxxxxxxxx>
---
Documentation/filesystems/proc.rst | 2 ++
fs/proc/task_mmu.c | 25 ++++++++++++++++++++
include/linux/mm_types.h | 3 +++
include/linux/sched/numa_balancing.h | 6 +++++
include/uapi/linux/prctl.h | 7 ++++++
kernel/fork.c | 3 +++
kernel/sched/fair.c | 6 +++--
kernel/sys.c | 35 ++++++++++++++++++++++++++++
8 files changed, 85 insertions(+), 2 deletions(-)
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 8d7f141c6fc7..fc44723a821a 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -192,6 +192,7 @@ read the file /proc/PID/status::
VmLib: 1412 kB
VmPTE: 20 kb
VmSwap: 0 kB
+ NumaB_enabled: default
HugetlbPages: 0 kB
CoreDumping: 0
THP_enabled: 1
@@ -273,6 +274,7 @@ It's slow but very precise.
VmPTE size of page table entries
VmSwap amount of swap used by anonymous private data
(shmem swap usage is not included)
+ NumaB_enabled numa balancing state, set by prctl(PR_NUMA_BALANCING, ...)
HugetlbPages size of hugetlb memory portions
CoreDumping process's memory is currently being dumped
(killing the process may lead to a corrupted core)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ad667dbc96f5..5f340f1c926e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -19,6 +19,7 @@
#include <linux/shmem_fs.h>
#include <linux/uaccess.h>
#include <linux/pkeys.h>
+#include <linux/sched/numa_balancing.h>
#include <asm/elf.h>
#include <asm/tlb.h>
@@ -31,10 +32,16 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
{
unsigned long text, lib, swap, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
+#ifdef CONFIG_NUMA_BALANCING
+ int numab_enabled;
+#endif
anon = get_mm_counter(mm, MM_ANONPAGES);
file = get_mm_counter(mm, MM_FILEPAGES);
shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+#ifdef CONFIG_NUMA_BALANCING
+ numab_enabled = mm->numab_enabled;
+#endif
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -75,6 +82,24 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
" kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8);
SEQ_PUT_DEC(" kB\nVmSwap:\t", swap);
seq_puts(m, " kB\n");
+#ifdef CONFIG_NUMA_BALANCING
+ seq_puts(m, "NumaB_enabled:\t");
+ switch (mm->numab_enabled) {
+ case NUMAB_DEFAULT:
+ seq_puts(m, "default");
+ break;
+ case NUMAB_DISABLED:
+ seq_puts(m, "disabled");
+ break;
+ case NUMAB_ENABLED:
+ seq_puts(m, "enabled");
+ break;
+ default:
+ seq_puts(m, "unknown");
+ break;
+ }
+ seq_putc(m, '\n');
+#endif
hugetlb_report_usage(m, mm);
}
#undef SEQ_PUT_DEC
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bb8c6f5f19bc..3f827b3c0e75 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -612,6 +612,9 @@ struct mm_struct {
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
+
+ /* Controls whether NUMA balancing is active for this mm. */
+ int numab_enabled;
#endif
/*
* An operation with batched TLB flushing is going on. Anything
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 3988762efe15..35a1c79925ea 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -16,6 +16,12 @@
#define TNF_MIGRATE_FAIL 0x10
#ifdef CONFIG_NUMA_BALANCING
+enum {
+ NUMAB_DISABLED,
+ NUMAB_ENABLED,
+ NUMAB_DEFAULT
+};
+DECLARE_STATIC_KEY_FALSE(sched_numa_balancing);
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index bb73e9a0b24f..525f174a56f5 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -272,4 +272,11 @@ struct prctl_mm_map {
# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1
# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2
+/* Set/get enabled per-process numa_balancing */
+#define PR_NUMA_BALANCING 63
+# define PR_SET_NUMAB_DISABLED NUMAB_DISABLED
+# define PR_SET_NUMAB_ENABLED NUMAB_ENABLED
+# define PR_SET_NUMAB_DEFAULT NUMAB_DEFAULT
+# define PR_GET_NUMAB 3
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 01af6129aa38..d028822d551f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1110,6 +1110,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+ mm->numab_enabled = NUMAB_DEFAULT;
#endif
mm_init_uprobes_state(mm);
hugetlb_count_init(mm);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6e476f6d9435..1245be1223c8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11169,8 +11169,10 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
entity_tick(cfs_rq, se, queued);
}
- if (static_branch_unlikely(&sched_numa_balancing))
- task_tick_numa(rq, curr);
+ if (curr->mm && (curr->mm->numab_enabled == NUMAB_ENABLED \
+ || (static_branch_unlikely(&sched_numa_balancing) \
+ && curr->mm->numab_enabled == NUMAB_DEFAULT)))
+ task_tick_numa(rq, curr);
update_misfit_status(curr, rq);
update_overutilized_status(task_rq(curr));
diff --git a/kernel/sys.c b/kernel/sys.c
index 8fdac0d90504..de3112e537b8 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -58,6 +58,7 @@
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
+#include <linux/sched/numa_balancing.h>
#include <linux/rcupdate.h>
#include <linux/uidgid.h>
#include <linux/cred.h>
@@ -2081,6 +2082,23 @@ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr,
return 0;
}
+#ifdef CONFIG_NUMA_BALANCING
+static int prctl_pid_numa_balancing_write(int numa_balancing)
+{
+ if (numa_balancing != PR_SET_NUMAB_DEFAULT \
+ && numa_balancing != PR_SET_NUMAB_DISABLED \
+ && numa_balancing != PR_SET_NUMAB_ENABLED)
+ return -EINVAL;
+ current->mm->numab_enabled = numa_balancing;
+ return 0;
+}
+
+static int prctl_pid_numa_balancing_read(void)
+{
+ return current->mm->numab_enabled;
+}
+#endif
+
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
@@ -2525,6 +2543,23 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = set_syscall_user_dispatch(arg2, arg3, arg4,
(char __user *) arg5);
break;
+#ifdef CONFIG_NUMA_BALANCING
+ case PR_NUMA_BALANCING:
+ switch (arg2) {
+ case PR_SET_NUMAB_DEFAULT:
+ case PR_SET_NUMAB_DISABLED:
+ case PR_SET_NUMAB_ENABLED:
+ error = prctl_pid_numa_balancing_write((int)arg2);
+ break;
+ case PR_GET_NUMAB:
+ error = put_user(prctl_pid_numa_balancing_read(), (int __user *)arg3);
+ break;
+ default:
+ error = -EINVAL;
+ break;
+ }
+ break;
+#endif
#ifdef CONFIG_SCHED_CORE
case PR_SCHED_CORE:
error = sched_core_share_pid(arg2, arg3, arg4, arg5);
--
2.20.1
