linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@linux.intel.com>
To: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org, dan.j.williams@intel.com,
	Dave Hansen <dave.hansen@linux.intel.com>,
	keith.busch@intel.com
Subject: [PATCH 1/4] node: Define and export memory migration path
Date: Wed, 16 Oct 2019 15:11:49 -0700	[thread overview]
Message-ID: <20191016221149.74AE222C@viggo.jf.intel.com> (raw)
In-Reply-To: <20191016221148.F9CCD155@viggo.jf.intel.com>


From: Keith Busch <keith.busch@intel.com>

Prepare for the kernel to auto-migrate pages to other memory nodes
with a user defined node migration table. This allows creating single
migration target for each NUMA node to enable the kernel to do NUMA
page migrations instead of simply reclaiming colder pages. A node
with no target is a "terminal node", so reclaim acts normally there.
The migration target does not fundamentally _need_ to be a single node,
but this implementation starts there to limit complexity.

If you consider the migration path as a graph, cycles (loops) in the
graph are disallowed.  This avoids wasting resources by constantly
migrating (A->B, B->A, A->B ...).  The expectation is that cycles will
never be allowed, and this rule is enforced if the user tries to make
such a cycle.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
---

 b/drivers/base/node.c  |   73 +++++++++++++++++++++++++++++++++++++++++++++++++
 b/include/linux/node.h |    6 ++++
 2 files changed, 79 insertions(+)

diff -puN drivers/base/node.c~0003-node-Define-and-export-memory-migration-path drivers/base/node.c
--- a/drivers/base/node.c~0003-node-Define-and-export-memory-migration-path	2019-10-16 15:06:55.895952599 -0700
+++ b/drivers/base/node.c	2019-10-16 15:06:55.902952599 -0700
@@ -101,6 +101,10 @@ static const struct attribute_group *nod
 	NULL,
 };
 
+#define TERMINAL_NODE -1
+static int node_migration[MAX_NUMNODES] = {[0 ...  MAX_NUMNODES - 1] = TERMINAL_NODE};
+static DEFINE_SPINLOCK(node_migration_lock);
+
 static void node_remove_accesses(struct node *node)
 {
 	struct node_access_nodes *c, *cnext;
@@ -530,6 +534,74 @@ static ssize_t node_read_distance(struct
 }
 static DEVICE_ATTR(distance, S_IRUGO, node_read_distance, NULL);
 
+static ssize_t migration_path_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	return sprintf(buf, "%d\n", node_migration[dev->id]);
+}
+
+static ssize_t migration_path_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	int i, err, nid = dev->id;
+	nodemask_t visited = NODE_MASK_NONE;
+	long next;
+
+	err = kstrtol(buf, 0, &next);
+	if (err)
+		return -EINVAL;
+
+	if (next < 0) {
+		spin_lock(&node_migration_lock);
+		WRITE_ONCE(node_migration[nid], TERMINAL_NODE);
+		spin_unlock(&node_migration_lock);
+		return count;
+	}
+	if (next >= MAX_NUMNODES || !node_online(next))
+		return -EINVAL;
+
+	/*
+	 * Follow the entire migration path from 'nid' through the point where
+	 * we hit a TERMINAL_NODE.
+	 *
+	 * Don't allow loops migration cycles in the path.
+	 */
+	node_set(nid, visited);
+	spin_lock(&node_migration_lock);
+	for (i = next; node_migration[i] != TERMINAL_NODE;
+	     i = node_migration[i]) {
+		/* Fail if we have visited this node already */
+		if (node_test_and_set(i, visited)) {
+			spin_unlock(&node_migration_lock);
+			return -EINVAL;
+		}
+	}
+	WRITE_ONCE(node_migration[nid], next);
+	spin_unlock(&node_migration_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(migration_path);
+
+/**
+ * next_migration_node() - Get the next node in the migration path
+ * @current_node: The starting node to lookup the next node
+ *
+ * @returns: node id for next memory node in the migration path hierarchy from
+ * 	     @current_node; -1 if @current_node is terminal or its migration
+ * 	     node is not online.
+ */
+int next_migration_node(int current_node)
+{
+	int nid = READ_ONCE(node_migration[current_node]);
+
+	if (nid >= 0 && node_online(nid))
+		return nid;
+	return TERMINAL_NODE;
+}
+
 static struct attribute *node_dev_attrs[] = {
 	&dev_attr_cpumap.attr,
 	&dev_attr_cpulist.attr,
@@ -537,6 +609,7 @@ static struct attribute *node_dev_attrs[
 	&dev_attr_numastat.attr,
 	&dev_attr_distance.attr,
 	&dev_attr_vmstat.attr,
+	&dev_attr_migration_path.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(node_dev);
diff -puN include/linux/node.h~0003-node-Define-and-export-memory-migration-path include/linux/node.h
--- a/include/linux/node.h~0003-node-Define-and-export-memory-migration-path	2019-10-16 15:06:55.898952599 -0700
+++ b/include/linux/node.h	2019-10-16 15:06:55.902952599 -0700
@@ -134,6 +134,7 @@ static inline int register_one_node(int
 	return error;
 }
 
+extern int next_migration_node(int current_node);
 extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
@@ -186,6 +187,11 @@ static inline void register_hugetlbfs_wi
 						node_registration_func_t unreg)
 {
 }
+
+static inline int next_migration_node(int current_node)
+{
+	return -1;
+}
 #endif
 
 #define to_node(device) container_of(device, struct node, dev)
_

  reply	other threads:[~2019-10-16 22:14 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-16 22:11 [PATCH 0/4] [RFC] Migrate Pages in lieu of discard Dave Hansen
2019-10-16 22:11 ` Dave Hansen [this message]
2019-10-17 11:12   ` [PATCH 1/4] node: Define and export memory migration path Kirill A. Shutemov
2019-10-17 11:44     ` Kirill A. Shutemov
2019-10-16 22:11 ` [PATCH 2/4] mm/migrate: Defer allocating new page until needed Dave Hansen
2019-10-17 11:27   ` Kirill A. Shutemov
2019-10-16 22:11 ` [PATCH 3/4] mm/vmscan: Attempt to migrate page in lieu of discard Dave Hansen
2019-10-17 17:30   ` Yang Shi
2019-10-18 18:15     ` Dave Hansen
2019-10-18 21:02       ` Yang Shi
2019-10-16 22:11 ` [PATCH 4/4] mm/vmscan: Consider anonymous pages without swap Dave Hansen
2019-10-17  3:45 ` [PATCH 0/4] [RFC] Migrate Pages in lieu of discard Shakeel Butt
2019-10-17 14:26   ` Dave Hansen
2019-10-17 16:58     ` Shakeel Butt
2019-10-17 20:51       ` Dave Hansen
2019-10-17 17:20     ` Yang Shi
2019-10-17 21:05       ` Dave Hansen
2019-10-17 22:58       ` Shakeel Butt
2019-10-18 21:44         ` Yang Shi
2019-10-17 16:01 ` Suleiman Souhlal
2019-10-17 16:32   ` Dave Hansen
2019-10-17 16:39     ` Shakeel Butt
2019-10-18  8:11     ` Suleiman Souhlal
2019-10-18 15:10       ` Dave Hansen
2019-10-18 15:39         ` Suleiman Souhlal
2019-10-18  7:44 ` Michal Hocko
2019-10-18 14:54   ` Dave Hansen
2019-10-18 21:39     ` Yang Shi
2019-10-18 21:55       ` Dan Williams
2019-10-22 13:49     ` Michal Hocko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191016221149.74AE222C@viggo.jf.intel.com \
    --to=dave.hansen@linux.intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=keith.busch@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).