linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>, Rik van Riel <riel@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
	Ingo Molnar <mingo@kernel.org>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Linux-MM <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>, Mel Gorman <mgorman@suse.de>
Subject: [PATCH 52/63] sched: numa: add debugging
Date: Fri, 27 Sep 2013 14:27:37 +0100	[thread overview]
Message-ID: <1380288468-5551-53-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1380288468-5551-1-git-send-email-mgorman@suse.de>

From: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-5giqjcqnc93a89q01ymtjxpr@git.kernel.org
---
 include/linux/sched.h |  6 ++++++
 kernel/sched/debug.c  | 60 +++++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/fair.c   |  5 ++++-
 3 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 31d1740..11b873f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1357,6 +1357,7 @@ struct task_struct {
 	unsigned long *numa_faults_buffer;
 
 	int numa_preferred_nid;
+	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
 	struct rcu_head rcu;
@@ -2581,6 +2582,11 @@ static inline unsigned int task_cpu(const struct task_struct *p)
 	return task_thread_info(p)->cpu;
 }
 
+static inline int task_node(const struct task_struct *p)
+{
+	return cpu_to_node(task_cpu(p));
+}
+
 extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
 
 #else
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e076bdd..49ab782 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
+#include <linux/mempolicy.h>
 
 #include "sched.h"
 
@@ -137,6 +138,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+#endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
 #endif
@@ -159,7 +163,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, p) {
-		if (!p->on_rq || task_cpu(p) != rq_cpu)
+		if (task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);
@@ -345,7 +349,7 @@ static void sched_debug_header(struct seq_file *m)
 	cpu_clk = local_clock();
 	local_irq_restore(flags);
 
-	SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
@@ -488,6 +492,56 @@ static int __init init_sched_debug_procfs(void)
 
 __initcall(init_sched_debug_procfs);
 
+#define __P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+
+static void sched_show_numa(struct task_struct *p, struct seq_file *m)
+{
+#ifdef CONFIG_NUMA_BALANCING
+	struct mempolicy *pol;
+	int node, i;
+
+	if (p->mm)
+		P(mm->numa_scan_seq);
+
+	task_lock(p);
+	pol = p->mempolicy;
+	if (pol && !(pol->flags & MPOL_F_MORON))
+		pol = NULL;
+	mpol_get(pol);
+	task_unlock(p);
+
+	SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
+
+	for_each_online_node(node) {
+		for (i = 0; i < 2; i++) {
+			unsigned long nr_faults = -1;
+			int cpu_current, home_node;
+
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
+
+			cpu_current = !i ? (task_node(p) == node) :
+				(pol && node_isset(node, pol->v.nodes));
+
+			home_node = (p->numa_preferred_nid == node);
+
+			SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+				i, node, cpu_current, home_node, nr_faults);
+		}
+	}
+
+	mpol_put(pol);
+#endif
+}
+
 void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 {
 	unsigned long nr_switches;
@@ -591,6 +645,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		SEQ_printf(m, "%-45s:%21Ld\n",
 			   "clock-delta", (long long)(t1-t0));
 	}
+
+	sched_show_numa(p, m);
 }
 
 void proc_sched_set_task(struct task_struct *p)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 86511a5..cd1b862 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1137,7 +1137,7 @@ static int task_numa_migrate(struct task_struct *p)
 		.p = p,
 
 		.src_cpu = task_cpu(p),
-		.src_nid = cpu_to_node(task_cpu(p)),
+		.src_nid = task_node(p),
 
 		.imbalance_pct = 112,
 
@@ -1515,6 +1515,9 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (p->numa_migrate_retry && time_after(jiffies, p->numa_migrate_retry))
 		numa_migrate_preferred(p);
 
+	if (migrated)
+		p->numa_pages_migrated += pages;
+
 	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
 }
 
-- 
1.8.1.4

--
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>

  parent reply	other threads:[~2013-09-27 13:28 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-09-27 13:26 [PATCH 0/63] Basic scheduler support for automatic NUMA balancing V8 Mel Gorman
2013-09-27 13:26 ` [PATCH 01/63] sched: monolithic code dump of what is being pushed upstream Mel Gorman
2013-09-27 13:26 ` [PATCH 02/63] mm: numa: Document automatic NUMA balancing sysctls Mel Gorman
2013-09-27 13:26 ` [PATCH 03/63] sched, numa: Comment fixlets Mel Gorman
2013-09-27 13:26 ` [PATCH 04/63] mm: numa: Do not account for a hinting fault if we raced Mel Gorman
2013-09-27 13:26 ` [PATCH 05/63] mm: Wait for THP migrations to complete during NUMA hinting faults Mel Gorman
2013-09-27 13:26 ` [PATCH 06/63] mm: Prevent parallel splits during THP migration Mel Gorman
2013-09-27 13:26 ` [PATCH 07/63] mm: Account for a THP NUMA hinting update as one PTE update Mel Gorman
2013-09-27 13:26 ` [PATCH 08/63] mm: Do not flush TLB during protection change if !pte_present && !migration_entry Mel Gorman
2013-09-27 13:26 ` [PATCH 09/63] mm: Only flush TLBs if a transhuge PMD is modified for NUMA pte scanning Mel Gorman
2013-09-27 13:26 ` [PATCH 10/63] mm: numa: Sanitize task_numa_fault() callsites Mel Gorman
2013-09-27 13:26 ` [PATCH 11/63] mm: Close races between THP migration and PMD numa clearing Mel Gorman
2013-09-30  8:52   ` Mel Gorman
2013-09-30 14:10     ` Rik van Riel
2013-09-30 15:18       ` Mel Gorman
2013-09-27 13:26 ` [PATCH 12/63] mm: numa: Do not migrate or account for hinting faults on the zero page Mel Gorman
2013-09-27 13:26 ` [PATCH 13/63] sched: numa: Mitigate chance that same task always updates PTEs Mel Gorman
2013-09-27 13:26 ` [PATCH 14/63] sched: numa: Continue PTE scanning even if migrate rate limited Mel Gorman
2013-09-27 13:27 ` [PATCH 15/63] Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node" Mel Gorman
2013-09-27 13:27 ` [PATCH 16/63] sched: numa: Initialise numa_next_scan properly Mel Gorman
2013-09-27 13:27 ` [PATCH 17/63] sched: Set the scan rate proportional to the memory usage of the task being scanned Mel Gorman
2013-09-27 13:27 ` [PATCH 18/63] sched: numa: Slow scan rate if no NUMA hinting faults are being recorded Mel Gorman
2013-09-27 13:27 ` [PATCH 19/63] sched: Track NUMA hinting faults on per-node basis Mel Gorman
2013-09-27 13:27 ` [PATCH 20/63] sched: Select a preferred node with the most numa hinting faults Mel Gorman
2013-09-27 13:27 ` [PATCH 21/63] sched: Update NUMA hinting faults once per scan Mel Gorman
2013-09-27 13:27 ` [PATCH 22/63] sched: Favour moving tasks towards the preferred node Mel Gorman
2013-09-27 13:27 ` [PATCH 23/63] sched: Resist moving tasks towards nodes with fewer hinting faults Mel Gorman
2013-09-27 13:27 ` [PATCH 24/63] sched: Reschedule task on preferred NUMA node once selected Mel Gorman
2013-09-27 13:27 ` [PATCH 25/63] sched: Add infrastructure for split shared/private accounting of NUMA hinting faults Mel Gorman
2013-09-27 13:27 ` [PATCH 26/63] sched: Check current->mm before allocating NUMA faults Mel Gorman
2013-09-27 13:27 ` [PATCH 27/63] mm: numa: Scan pages with elevated page_mapcount Mel Gorman
2013-09-27 13:27 ` [PATCH 28/63] sched: Remove check that skips small VMAs Mel Gorman
2013-09-27 13:27 ` [PATCH 29/63] sched: Set preferred NUMA node based on number of private faults Mel Gorman
2013-09-29  2:05   ` Figo.zhang
2013-09-27 13:27 ` [PATCH 30/63] sched: Do not migrate memory immediately after switching node Mel Gorman
2013-09-27 13:27 ` [PATCH 31/63] mm: numa: only unmap migrate-on-fault VMAs Mel Gorman
2013-09-27 13:27 ` [PATCH 32/63] sched: Avoid overloading CPUs on a preferred NUMA node Mel Gorman
2013-09-27 13:27 ` [PATCH 33/63] sched: Retry migration of tasks to CPU on a preferred node Mel Gorman
2013-09-27 13:27 ` [PATCH 34/63] sched: numa: increment numa_migrate_seq when task runs in correct location Mel Gorman
2013-09-27 13:27 ` [PATCH 35/63] sched: numa: Do not trap hinting faults for shared libraries Mel Gorman
2013-09-27 13:27 ` [PATCH 36/63] mm: numa: Only trap pmd hinting faults if we would otherwise trap PTE faults Mel Gorman
2013-09-27 13:27 ` [PATCH 37/63] stop_machine: Introduce stop_two_cpus() Mel Gorman
2013-09-27 13:27 ` [PATCH 38/63] sched: Introduce migrate_swap() Mel Gorman
2013-09-27 13:27 ` [PATCH 39/63] sched: numa: Use a system-wide search to find swap/migration candidates Mel Gorman
2013-09-27 13:27 ` [PATCH 40/63] sched: numa: Favor placing a task on the preferred node Mel Gorman
2013-09-27 13:27 ` [PATCH 41/63] sched: numa: fix placement of workloads spread across multiple nodes Mel Gorman
2013-09-27 13:27 ` [PATCH 42/63] mm: numa: Change page last {nid,pid} into {cpu,pid} Mel Gorman
2013-09-27 13:27 ` [PATCH 43/63] sched: numa: Use {cpu, pid} to create task groups for shared faults Mel Gorman
2013-09-27 13:27 ` [PATCH 44/63] sched: numa: Report a NUMA task group ID Mel Gorman
2013-09-27 13:27 ` [PATCH 45/63] mm: numa: copy cpupid on page migration Mel Gorman
2013-09-27 13:27 ` [PATCH 46/63] mm: numa: Do not group on RO pages Mel Gorman
2013-09-27 13:27 ` [PATCH 47/63] mm: numa: Do not batch handle PMD pages Mel Gorman
2013-09-27 13:27 ` [PATCH 48/63] sched: numa: stay on the same node if CLONE_VM Mel Gorman
2013-09-27 13:27 ` [PATCH 49/63] sched: numa: use group fault statistics in numa placement Mel Gorman
2013-09-27 13:27 ` [PATCH 50/63] sched: numa: call task_numa_free from do_execve Mel Gorman
2013-09-27 13:27 ` [PATCH 51/63] sched: numa: Prevent parallel updates to group stats during placement Mel Gorman
2013-09-27 13:27 ` Mel Gorman [this message]
2013-09-27 13:27 ` [PATCH 53/63] sched: numa: Decide whether to favour task or group weights based on swap candidate relationships Mel Gorman
2013-09-27 13:27 ` [PATCH 54/63] sched: numa: fix task or group comparison Mel Gorman
2013-09-27 13:27 ` [PATCH 55/63] sched: numa: Avoid migrating tasks that are placed on their preferred node Mel Gorman
2013-09-27 13:27 ` [PATCH 56/63] sched: numa: be more careful about joining numa groups Mel Gorman
2013-09-27 13:27 ` [PATCH 57/63] sched: numa: Take false sharing into account when adapting scan rate Mel Gorman
2013-09-27 13:27 ` [PATCH 58/63] sched: numa: adjust scan rate in task_numa_placement Mel Gorman
2013-09-27 13:27 ` [PATCH 59/63] sched: numa: Remove the numa_balancing_scan_period_reset sysctl Mel Gorman
2013-09-27 13:27 ` [PATCH 60/63] mm: numa: revert temporarily disabling of NUMA migration Mel Gorman
2013-09-27 13:27 ` [PATCH 61/63] sched: numa: skip some page migrations after a shared fault Mel Gorman
2013-09-27 13:27 ` [PATCH 62/63] sched: numa: use unsigned longs for numa group fault stats Mel Gorman
2013-09-27 13:27 ` [PATCH 63/63] sched: numa: periodically retry task_numa_migrate Mel Gorman
2013-10-07 10:28 [PATCH 0/63] Basic scheduler support for automatic NUMA balancing V9 Mel Gorman
2013-10-07 10:29 ` [PATCH 52/63] sched: numa: add debugging Mel Gorman
2013-10-07 19:13   ` Rik van Riel

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=1380288468-5551-53-git-send-email-mgorman@suse.de \
    --to=mgorman@suse.de \
    --cc=a.p.zijlstra@chello.nl \
    --cc=aarcange@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@kernel.org \
    --cc=riel@redhat.com \
    --cc=srikar@linux.vnet.ibm.com \
    /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).