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 47/50] sched: numa: add debugging
Date: Tue, 10 Sep 2013 10:32:27 +0100 [thread overview]
Message-ID: <1378805550-29949-48-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1378805550-29949-1-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 46fb36a..ac08eb6 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;
@@ -2577,6 +2578,11 @@ 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 4653f71..80906fa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1138,7 +1138,7 @@ 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,
@@ -1510,6 +1510,9 @@ 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>
next prev parent reply other threads:[~2013-09-10 9:33 UTC|newest]
Thread overview: 182+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-10 9:31 [PATCH 0/50] Basic scheduler support for automatic NUMA balancing V7 Mel Gorman
2013-09-10 9:31 ` [PATCH 01/50] sched: monolithic code dump of what is being pushed upstream Mel Gorman
2013-09-11 0:58 ` Joonsoo Kim
2013-09-11 3:11 ` Hillf Danton
2013-09-13 8:11 ` Mel Gorman
2013-09-10 9:31 ` [PATCH 02/50] mm: numa: Document automatic NUMA balancing sysctls Mel Gorman
2013-09-10 9:31 ` [PATCH 03/50] sched, numa: Comment fixlets Mel Gorman
2013-09-10 9:31 ` [PATCH 04/50] mm: numa: Do not account for a hinting fault if we raced Mel Gorman
2013-09-10 9:31 ` [PATCH 05/50] mm: Wait for THP migrations to complete during NUMA hinting faults Mel Gorman
2013-09-10 9:31 ` [PATCH 06/50] mm: Prevent parallel splits during THP migration Mel Gorman
2013-09-10 9:31 ` [PATCH 07/50] mm: Account for a THP NUMA hinting update as one PTE update Mel Gorman
2013-09-16 12:36 ` Peter Zijlstra
2013-09-16 13:39 ` Rik van Riel
2013-09-16 14:54 ` Peter Zijlstra
2013-09-16 16:11 ` Mel Gorman
2013-09-16 16:37 ` Peter Zijlstra
2013-09-10 9:31 ` [PATCH 08/50] mm: numa: Sanitize task_numa_fault() callsites Mel Gorman
2013-09-10 9:31 ` [PATCH 09/50] mm: numa: Do not migrate or account for hinting faults on the zero page Mel Gorman
2013-09-10 9:31 ` [PATCH 10/50] sched: numa: Mitigate chance that same task always updates PTEs Mel Gorman
2013-09-10 9:31 ` [PATCH 11/50] sched: numa: Continue PTE scanning even if migrate rate limited Mel Gorman
2013-09-10 9:31 ` [PATCH 12/50] Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node" Mel Gorman
2013-09-10 9:31 ` [PATCH 13/50] sched: numa: Initialise numa_next_scan properly Mel Gorman
2013-09-10 9:31 ` [PATCH 14/50] sched: Set the scan rate proportional to the memory usage of the task being scanned Mel Gorman
2013-09-16 15:18 ` Peter Zijlstra
2013-09-16 15:40 ` Mel Gorman
2013-09-10 9:31 ` [PATCH 15/50] sched: numa: Correct adjustment of numa_scan_period Mel Gorman
2013-09-10 9:31 ` [PATCH 16/50] mm: Only flush TLBs if a transhuge PMD is modified for NUMA pte scanning Mel Gorman
2013-09-10 9:31 ` [PATCH 17/50] mm: Do not flush TLB during protection change if !pte_present && !migration_entry Mel Gorman
2013-09-16 16:35 ` Peter Zijlstra
2013-09-17 17:00 ` Mel Gorman
2013-09-10 9:31 ` [PATCH 18/50] sched: numa: Slow scan rate if no NUMA hinting faults are being recorded Mel Gorman
2013-09-10 9:31 ` [PATCH 19/50] sched: Track NUMA hinting faults on per-node basis Mel Gorman
2013-09-10 9:32 ` [PATCH 20/50] sched: Select a preferred node with the most numa hinting faults Mel Gorman
2013-09-10 9:32 ` [PATCH 21/50] sched: Update NUMA hinting faults once per scan Mel Gorman
2013-09-10 9:32 ` [PATCH 22/50] sched: Favour moving tasks towards the preferred node Mel Gorman
2013-09-10 9:32 ` [PATCH 23/50] sched: Resist moving tasks towards nodes with fewer hinting faults Mel Gorman
2013-09-10 9:32 ` [PATCH 24/50] sched: Reschedule task on preferred NUMA node once selected Mel Gorman
2013-09-10 9:32 ` [PATCH 25/50] sched: Add infrastructure for split shared/private accounting of NUMA hinting faults Mel Gorman
2013-09-10 9:32 ` [PATCH 26/50] sched: Check current->mm before allocating NUMA faults Mel Gorman
2013-09-10 9:32 ` [PATCH 27/50] mm: numa: Scan pages with elevated page_mapcount Mel Gorman
2013-09-12 2:10 ` Hillf Danton
2013-09-13 8:11 ` Mel Gorman
2013-09-10 9:32 ` [PATCH 28/50] sched: Remove check that skips small VMAs Mel Gorman
2013-09-10 9:32 ` [PATCH 29/50] sched: Set preferred NUMA node based on number of private faults Mel Gorman
2013-09-10 9:32 ` [PATCH 30/50] sched: Do not migrate memory immediately after switching node Mel Gorman
2013-09-10 9:32 ` [PATCH 31/50] sched: Avoid overloading CPUs on a preferred NUMA node Mel Gorman
2013-09-10 9:32 ` [PATCH 32/50] sched: Retry migration of tasks to CPU on a preferred node Mel Gorman
2013-09-10 9:32 ` [PATCH 33/50] sched: numa: increment numa_migrate_seq when task runs in correct location Mel Gorman
2013-09-10 9:32 ` [PATCH 34/50] sched: numa: Do not trap hinting faults for shared libraries Mel Gorman
2013-09-17 2:02 ` 答复: " 张天飞
2013-09-17 8:05 ` ????: " Mel Gorman
2013-09-17 8:22 ` Figo.zhang
2013-09-10 9:32 ` [PATCH 35/50] mm: numa: Only trap pmd hinting faults if we would otherwise trap PTE faults Mel Gorman
2013-09-10 9:32 ` [PATCH 36/50] stop_machine: Introduce stop_two_cpus() Mel Gorman
2013-09-10 9:32 ` [PATCH 37/50] sched: Introduce migrate_swap() Mel Gorman
2013-09-17 14:30 ` [PATCH] hotplug: Optimize {get,put}_online_cpus() Peter Zijlstra
2013-09-17 16:20 ` Mel Gorman
2013-09-17 16:45 ` Peter Zijlstra
2013-09-18 15:49 ` Peter Zijlstra
2013-09-19 14:32 ` Peter Zijlstra
2013-09-21 16:34 ` Oleg Nesterov
2013-09-21 19:13 ` Oleg Nesterov
2013-09-23 9:29 ` Peter Zijlstra
2013-09-23 17:32 ` Oleg Nesterov
2013-09-24 20:24 ` Peter Zijlstra
2013-09-24 21:02 ` Peter Zijlstra
2013-09-25 15:55 ` Oleg Nesterov
2013-09-25 16:59 ` Paul E. McKenney
2013-09-25 17:43 ` Peter Zijlstra
2013-09-25 17:50 ` Oleg Nesterov
2013-09-25 18:40 ` Peter Zijlstra
2013-09-25 21:22 ` Paul E. McKenney
2013-09-26 11:10 ` Peter Zijlstra
[not found] ` <20130926155321.GA4342@redhat.com>
2013-09-26 16:13 ` Peter Zijlstra
2013-09-26 16:14 ` Oleg Nesterov
2013-09-26 16:40 ` Peter Zijlstra
2013-09-26 16:58 ` Oleg Nesterov
2013-09-26 17:50 ` Peter Zijlstra
2013-09-27 18:15 ` Oleg Nesterov
2013-09-27 20:41 ` Peter Zijlstra
2013-09-28 12:48 ` Oleg Nesterov
2013-09-28 14:47 ` Peter Zijlstra
2013-09-28 16:31 ` Oleg Nesterov
2013-09-30 20:11 ` Rafael J. Wysocki
2013-10-01 17:11 ` Srivatsa S. Bhat
2013-10-01 17:36 ` Peter Zijlstra
2013-10-01 17:45 ` Oleg Nesterov
2013-10-01 17:56 ` Peter Zijlstra
2013-10-01 18:07 ` Oleg Nesterov
2013-10-01 19:05 ` Paul E. McKenney
2013-10-02 12:16 ` Oleg Nesterov
2013-10-02 9:08 ` Peter Zijlstra
2013-10-02 12:13 ` Oleg Nesterov
2013-10-02 12:25 ` Peter Zijlstra
2013-10-02 13:31 ` Peter Zijlstra
2013-10-02 14:00 ` Oleg Nesterov
2013-10-02 15:17 ` Peter Zijlstra
2013-10-02 16:31 ` Oleg Nesterov
2013-10-02 17:52 ` Paul E. McKenney
2013-10-01 19:03 ` Srivatsa S. Bhat
2013-10-01 18:14 ` Srivatsa S. Bhat
2013-10-01 18:56 ` Srivatsa S. Bhat
2013-10-02 10:14 ` Srivatsa S. Bhat
2013-09-28 20:46 ` Paul E. McKenney
2013-10-01 3:56 ` Paul E. McKenney
2013-10-01 14:14 ` Oleg Nesterov
2013-10-01 14:45 ` Paul E. McKenney
2013-10-01 14:48 ` Peter Zijlstra
2013-10-01 15:24 ` Paul E. McKenney
2013-10-01 15:34 ` Oleg Nesterov
2013-10-01 15:00 ` Oleg Nesterov
2013-09-29 13:56 ` Oleg Nesterov
2013-10-01 15:38 ` Paul E. McKenney
2013-10-01 15:40 ` Oleg Nesterov
2013-10-01 20:40 ` Paul E. McKenney
2013-09-23 14:50 ` Steven Rostedt
2013-09-23 14:54 ` Peter Zijlstra
2013-09-23 15:13 ` Steven Rostedt
2013-09-23 15:22 ` Peter Zijlstra
2013-09-23 15:59 ` Steven Rostedt
2013-09-23 16:02 ` Peter Zijlstra
2013-09-23 15:50 ` Paul E. McKenney
2013-09-23 16:01 ` Peter Zijlstra
2013-09-23 17:04 ` Paul E. McKenney
2013-09-23 17:30 ` Peter Zijlstra
2013-09-23 17:50 ` Oleg Nesterov
2013-09-24 12:38 ` Peter Zijlstra
2013-09-24 14:42 ` Paul E. McKenney
2013-09-24 16:09 ` Peter Zijlstra
2013-09-24 16:31 ` Oleg Nesterov
2013-09-24 21:09 ` Paul E. McKenney
2013-09-24 16:03 ` Oleg Nesterov
2013-09-24 16:43 ` Steven Rostedt
2013-09-24 17:06 ` Oleg Nesterov
2013-09-24 17:47 ` Paul E. McKenney
2013-09-24 18:00 ` Oleg Nesterov
2013-09-24 20:35 ` Peter Zijlstra
2013-09-25 15:16 ` Oleg Nesterov
2013-09-25 15:35 ` Peter Zijlstra
2013-09-25 16:33 ` Oleg Nesterov
2013-09-24 16:49 ` Paul E. McKenney
2013-09-24 16:54 ` Peter Zijlstra
2013-09-24 17:02 ` Oleg Nesterov
2013-09-24 16:51 ` Peter Zijlstra
2013-09-24 16:39 ` Steven Rostedt
2013-09-29 18:36 ` [RFC] introduce synchronize_sched_{enter,exit}() Oleg Nesterov
2013-09-29 20:01 ` Paul E. McKenney
2013-09-30 12:42 ` Oleg Nesterov
2013-09-29 21:34 ` Steven Rostedt
2013-09-30 13:03 ` Oleg Nesterov
2013-09-30 12:59 ` Peter Zijlstra
2013-09-30 14:24 ` Peter Zijlstra
2013-09-30 15:06 ` Peter Zijlstra
2013-09-30 16:58 ` Oleg Nesterov
2013-09-30 16:38 ` Oleg Nesterov
2013-10-02 14:41 ` Peter Zijlstra
2013-10-03 7:04 ` Ingo Molnar
2013-10-03 7:43 ` Peter Zijlstra
2013-09-17 14:32 ` [PATCH 37/50] sched: Introduce migrate_swap() Peter Zijlstra
2013-09-10 9:32 ` [PATCH 38/50] sched: numa: Use a system-wide search to find swap/migration candidates Mel Gorman
2013-09-10 9:32 ` [PATCH 39/50] sched: numa: Favor placing a task on the preferred node Mel Gorman
2013-09-10 9:32 ` [PATCH 40/50] mm: numa: Change page last {nid,pid} into {cpu,pid} Mel Gorman
2013-09-10 9:32 ` [PATCH 41/50] sched: numa: Use {cpu, pid} to create task groups for shared faults Mel Gorman
2013-09-12 12:42 ` Hillf Danton
2013-09-12 14:40 ` Mel Gorman
2013-09-12 12:45 ` Hillf Danton
2013-09-10 9:32 ` [PATCH 42/50] sched: numa: Report a NUMA task group ID Mel Gorman
2013-09-10 9:32 ` [PATCH 43/50] mm: numa: Do not group on RO pages Mel Gorman
2013-09-10 9:32 ` [PATCH 44/50] sched: numa: stay on the same node if CLONE_VM Mel Gorman
2013-09-10 9:32 ` [PATCH 45/50] sched: numa: use group fault statistics in numa placement Mel Gorman
2013-09-10 9:32 ` [PATCH 46/50] sched: numa: Prevent parallel updates to group stats during placement Mel Gorman
2013-09-20 9:55 ` Peter Zijlstra
2013-09-20 12:31 ` Mel Gorman
2013-09-20 12:36 ` Peter Zijlstra
2013-09-20 13:31 ` Mel Gorman
2013-09-10 9:32 ` Mel Gorman [this message]
2013-09-10 9:32 ` [PATCH 48/50] sched: numa: Decide whether to favour task or group weights based on swap candidate relationships Mel Gorman
2013-09-10 9:32 ` [PATCH 49/50] sched: numa: fix task or group comparison Mel Gorman
2013-09-10 9:32 ` [PATCH 50/50] sched: numa: Avoid migrating tasks that are placed on their preferred node Mel Gorman
2013-09-11 2:03 ` [PATCH 0/50] Basic scheduler support for automatic NUMA balancing V7 Rik van Riel
2013-09-14 2:57 ` Bob Liu
2013-09-30 10:30 ` Mel Gorman
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=1378805550-29949-48-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).