Skip to contentSkip to conversation

Add a sysctl for numa_balancing.

PATCH In review Andi Kleen 4 participants 4 messages Apr 24, 2013 – Apr 29, 2013

Subsystems (5)
lore
Share & tools
lore

Andi Kleen

author
#0 lore raw

PATCH 1/1 Add a sysctl for numa_balancing.

From: Andi Kleen <[email protected]>

As discussed earlier, this adds a working sysctl to enable/disable automatic numa memory balancing at runtime.

This was possible earlier through debugfs, but only with special debugging options set. Also fix the boot message.

---
 Documentation/sysctl/kernel.txt |   10 ++++++++++
 include/linux/sched/sysctl.h    |    4 ++++
 kernel/sched/core.c             |   24 +++++++++++++++++++++++-
 kernel/sysctl.c                 |   11 +++++++++++
 mm/mempolicy.c                  |    2 +-
 5 files changed, 49 insertions(+), 2 deletions(-)
Documentation/sysctl/kernel.txt +10 -0
index ccd4258..17a7004 100644
@@ -354,6 +354,16 @@ utilize.
 
 ==============================================================
 
+numa_balancing
+
+Enables/disables automatic page fault based NUMA memory
+balancing. Memory is moved automatically to nodes
+that access it often.
+
+TBD someone document the other numa_balancing tunables
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease
include/linux/sched/sysctl.h +4 -0
index bf8086b..e228a1b 100644
@@ -101,4 +101,8 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+extern int sched_numa_balancing(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */
kernel/sched/core.c +23 -1
index 67d0465..679be74 100644
@@ -1614,7 +1614,29 @@ void set_numabalancing_state(bool enabled)
 	numabalancing_enabled = enabled;
 }
 #endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sched_numa_balancing(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = numabalancing_enabled;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_numabalancing_state(state);
+	return err;
+}
+#endif
+#endif
 
 /*
  * fork()/clone()-time setup:
kernel/sysctl.c +11 -0
index afc1dc6..94164ac 100644
@@ -393,6 +393,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sched_numa_balancing,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+
+
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
mm/mempolicy.c +1 -1
index 7431001..7eee646 100644
@@ -2531,7 +2531,7 @@ static void __init check_numabalancing_enable(void)
 
 	if (nr_node_ids > 1 && !numabalancing_override) {
 		printk(KERN_INFO "Enabling automatic NUMA balancing. "
-			"Configure with numa_balancing= or sysctl");
+			"Configure with numa_balancing= or the kernel.numa_balancing sysctl");
 		set_numabalancing_state(numabalancing_default);
 	}
 }
Signature · 1 line
1.7.7.6
#1 lore raw
Quoted 7 lines · Andi Kleen

From: Andi Kleen <[email protected]>

As discussed earlier, this adds a working sysctl to enable/disable automatic numa memory balancing at runtime.

This was possible earlier through debugfs, but only with special debugging options set. Also fix the boot message.

One offline question.

If I configure uma to fake numa, is there benefit or downside?

Quoted 106 lines
---
  Documentation/sysctl/kernel.txt |   10 ++++++++++
  include/linux/sched/sysctl.h    |    4 ++++
  kernel/sched/core.c             |   24 +++++++++++++++++++++++-
  kernel/sysctl.c                 |   11 +++++++++++
  mm/mempolicy.c                  |    2 +-
  5 files changed, 49 insertions(+), 2 deletions(-)
Documentation/sysctl/kernel.txt +10 -0
index ccd4258..17a7004 100644
@@ -354,6 +354,16 @@ utilize.
 
  ==============================================================
 
+numa_balancing
+
+Enables/disables automatic page fault based NUMA memory
+balancing. Memory is moved automatically to nodes
+that access it often.
+
+TBD someone document the other numa_balancing tunables
+
+==============================================================
+
  osrelease, ostype & version:
 
  # cat osrelease
include/linux/sched/sysctl.h +4 -0
index bf8086b..e228a1b 100644
@@ -101,4 +101,8 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
  		void __user *buffer, size_t *lenp,
  		loff_t *ppos);
 
+extern int sched_numa_balancing(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
  #endif /* _SCHED_SYSCTL_H */
kernel/sched/core.c +23 -1
index 67d0465..679be74 100644
@@ -1614,7 +1614,29 @@ void set_numabalancing_state(bool enabled)
  	numabalancing_enabled = enabled;
  }
  #endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sched_numa_balancing(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = numabalancing_enabled;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_numabalancing_state(state);
+	return err;
+}
+#endif
+#endif
 
  /*
   * fork()/clone()-time setup:
kernel/sysctl.c +11 -0
index afc1dc6..94164ac 100644
@@ -393,6 +393,17 @@ static struct ctl_table kern_table[] = {
  		.mode		= 0644,
  		.proc_handler	= proc_dointvec,
  	},
+	{
+		.procname	= "numa_balancing",
+		.data		= NULL, /* filled in by handler */
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sched_numa_balancing,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+
+
  #endif /* CONFIG_NUMA_BALANCING */
  #endif /* CONFIG_SCHED_DEBUG */
  	{
mm/mempolicy.c +0 -0
index 7431001..7eee646 100644

mm/mempolicy.c static void __init check_numabalancing_enable(void) · line 2537

Quoted 8 lines
mm/mempolicy.c +1 -1
@@ -2531,7 +2531,7 @@ static void __init check_numabalancing_enable(void)
 
  	if (nr_node_ids > 1 && !numabalancing_override) {
  		printk(KERN_INFO "Enabling automatic NUMA balancing. "
-			"Configure with numa_balancing= or sysctl");
+			"Configure with numa_balancing= or the kernel.numa_balancing sysctl");
  		set_numabalancing_state(numabalancing_default);
  	}
  }

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

reviewer Acked-by on v1 1/1
#2 lore raw
In reply to Andi Kleen
Quoted 9 lines · Andi Kleen

From: Andi Kleen <[email protected]>

As discussed earlier, this adds a working sysctl to enable/disable automatic numa memory balancing at runtime.

This was possible earlier through debugfs, but only with special debugging options set. Also fix the boot message.

Would you like to merge the following patch with it to remove the TBD?

---8<---
mm: numa: Document remaining automatic NUMA balancing sysctls

---
 Documentation/sysctl/kernel.txt | 62 +++++++++++++++++++++++++++++++++++++----
 1 file changed, 57 insertions(+), 5 deletions(-)
Documentation/sysctl/kernel.txt +57 -5
index 17a7004..4d56060 100644
@@ -356,11 +356,63 @@ utilize.
 
 numa_balancing
 
-Enables/disables automatic page fault based NUMA memory
-balancing. Memory is moved automatically to nodes
-that access it often.
-
-TBD someone document the other numa_balancing tunables
+Enables/disables automatic NUMA memory balancing. On NUMA machines, there
+is a performance penalty if remote memory is accessed by a CPU. When this
+feature is enabled the kernel samples what task thread is accessing memory
+by periodically unmapping pages and later trapping a page fault. At the
+time of the page fault, it is determined if the data being accessed should
+be migrated to a local memory node.
+
+The unmapping of pages and trapping faults incur additional overhead that
+ideally is offset by improved memory locality but there is no universal
+guarantee. If the target workload is already bound to NUMA nodes then this
+feature should be disabled. Otherwise, if the system overhead from the
+feature is too high then the rate the kernel samples for NUMA hinting
+faults may be controlled by the numa_balancing_scan_period_min_ms,
+numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset,
+numa_balancing_scan_period_max_ms and numa_balancing_scan_size_mb sysctls.
+
+==============================================================
+
+numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms,
+numa_balancing_scan_period_max_ms, numa_balancing_scan_period_reset,
+numa_balancing_scan_size_mb
+
+Automatic NUMA balancing scans tasks address space and unmaps pages to
+detect if pages are properly placed or if the data should be migrated to a
+memory node local to where the task is running.  Every "scan delay" the task
+scans the next "scan size" number of pages in its address space. When the
+end of the address space is reached the scanner restarts from the beginning.
+
+In combination, the "scan delay" and "scan size" determine the scan rate.
+When "scan delay" decreases, the scan rate increases.  The scan delay and
+hence the scan rate of every task is adaptive and depends on historical
+behaviour. If pages are properly placed then the scan delay increases,
+otherwise the scan delay decreases.  The "scan size" is not adaptive but
+the higher the "scan size", the higher the scan rate.
+
+Higher scan rates incur higher system overhead as page faults must be
+trapped and potentially data must be migrated. However, the higher the scan
+rate, the more quickly a tasks memory is migrated to a local node if the
+workload pattern changes and minimises performance impact due to remote
+memory accesses. These sysctls control the thresholds for scan delays and
+the number of pages scanned.
+
+numa_balancing_scan_period_min_ms is the minimum delay in milliseconds
+between scans. It effectively controls the maximum scanning rate for
+each task.
+
+numa_balancing_scan_delay_ms is the starting "scan delay" used for a task
+when it initially forks.
+
+numa_balancing_scan_period_max_ms is the maximum delay between scans. It
+effectively controls the minimum scanning rate for each task.
+
+numa_balancing_scan_size_mb is how many megabytes worth of pages are
+scanned for a given scan.
+
+numa_balancing_scan_period_reset is a blunt instrument that controls how
+often a tasks scan delay is reset to detect sudden changes in task behaviour.
 
 ==============================================================
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Acked-by Acked-by
#3 lore raw
Quoted 6 lines · Mel Gorman
Quoted 5 lines · Andi Kleen

From: Andi Kleen <[email protected]>

As discussed earlier, this adds a working sysctl to enable/disable automatic numa memory balancing at runtime.

Quoted 7 lines
Quoted 4 lines

This was possible earlier through debugfs, but only with special debugging options set. Also fix the boot message.

Quoted 6 lines

Would you like to merge the following patch with it to remove the TBD?

---8<---
mm: numa: Document remaining automatic NUMA balancing sysctls

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>