[PATCH 07/33] autonuma: mm_autonuma and task_autonuma data structures

[Andrea Arcangeli <aarcange@redhat.com>]

Define the two data structures that collect the per-process (in the
mm) and per-thread (in the task_struct) statistical information that
are the input of the CPU follow memory algorithms in the NUMA
scheduler.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---
 include/linux/autonuma_types.h |  107 ++++++++++++++++++++++++++++++++++++++++
 1 files changed, 107 insertions(+), 0 deletions(-)
 create mode 100644 include/linux/autonuma_types.h

diff --git a/include/linux/autonuma_types.h b/include/linux/autonuma_types.h
new file mode 100644
index 0000000..9673ce8
--- /dev/null
+++ b/include/linux/autonuma_types.h
@@ -0,0 +1,107 @@
+#ifndef _LINUX_AUTONUMA_TYPES_H
+#define _LINUX_AUTONUMA_TYPES_H
+
+#ifdef CONFIG_AUTONUMA
+
+#include <linux/numa.h>
+
+
+/*
+ * Per-mm (per-process) structure that contains the NUMA memory
+ * placement statistics generated by the knuma scan daemon. This
+ * structure is dynamically allocated only if AutoNUMA is possible on
+ * this system. They are linked togehter in a list headed within the
+ * knumad_scan structure.
+ */
+struct mm_autonuma {
+	/* link for knuma_scand's list of mm structures to scan */
+	struct list_head mm_node;
+	/* Pointer to associated mm structure */
+	struct mm_struct *mm;
+
+	/*
+	 * Zeroed from here during allocation, check
+	 * mm_autonuma_reset() if you alter the below.
+	 */
+
+	/*
+	 * Pass counter for this mm. This exist only to be able to
+	 * tell when it's time to apply the exponential backoff on the
+	 * task_autonuma statistics.
+	 */
+	unsigned long mm_numa_fault_pass;
+	/* Total number of pages that will trigger NUMA faults for this mm */
+	unsigned long mm_numa_fault_tot;
+	/* Number of pages that will trigger NUMA faults for each [nid] */
+	unsigned long mm_numa_fault[0];
+	/* do not add more variables here, the above array size is dynamic */
+};
+
+extern int alloc_mm_autonuma(struct mm_struct *mm);
+extern void free_mm_autonuma(struct mm_struct *mm);
+extern void __init mm_autonuma_init(void);
+
+/*
+ * Per-task (thread) structure that contains the NUMA memory placement
+ * statistics generated by the knuma scan daemon. This structure is
+ * dynamically allocated only if AutoNUMA is possible on this
+ * system. They are linked togehter in a list headed within the
+ * knumad_scan structure.
+ */
+struct task_autonuma {
+	/* node id the CPU scheduler should try to stick with (-1 if none) */
+	int task_selected_nid;
+
+	/*
+	 * Zeroed from here during allocation, check
+	 * mm_autonuma_reset() if you alter the below.
+	 */
+
+	/*
+	 * Pass counter for this task. When the pass counter is found
+	 * out of sync with the mm_numa_fault_pass we know it's time
+	 * to apply the exponential backoff on the task_autonuma
+	 * statistics, and then we synchronize it with
+	 * mm_numa_fault_pass. This pass counter is needed because in
+	 * knuma_scand we work on the mm and we've no visibility on
+	 * the task_autonuma. Furthermore it would be detrimental to
+	 * apply exponential backoff to all task_autonuma associated
+	 * to a certain mm_autonuma (potentially zeroing out the trail
+	 * of statistical data in task_autonuma) if the task is idle
+	 * for a long period of time (i.e. several knuma_scand passes).
+	 */
+	unsigned long task_numa_fault_pass;
+	/* Total number of eligible pages that triggered NUMA faults */
+	unsigned long task_numa_fault_tot;
+	/* Number of pages that triggered NUMA faults for each [nid] */
+	unsigned long task_numa_fault[0];
+	/* do not add more variables here, the above array size is dynamic */
+};
+
+extern int alloc_task_autonuma(struct task_struct *tsk,
+			       struct task_struct *orig,
+			       int node);
+extern void __init task_autonuma_init(void);
+extern void free_task_autonuma(struct task_struct *tsk);
+
+#else /* CONFIG_AUTONUMA */
+
+static inline int alloc_mm_autonuma(struct mm_struct *mm)
+{
+	return 0;
+}
+static inline void free_mm_autonuma(struct mm_struct *mm) {}
+static inline void mm_autonuma_init(void) {}
+
+static inline int alloc_task_autonuma(struct task_struct *tsk,
+				      struct task_struct *orig,
+				      int node)
+{
+	return 0;
+}
+static inline void task_autonuma_init(void) {}
+static inline void free_task_autonuma(struct task_struct *tsk) {}
+
+#endif /* CONFIG_AUTONUMA */
+
+#endif /* _LINUX_AUTONUMA_TYPES_H */

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