From: Li Zhijian <lizhijian@fujitsu.com>
To: Andrew Morton <akpm@linux-foundation.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
rafael@kernel.org, linux-mm@kvack.org
Cc: ying.huang@intel.com, y-goto@fujitsu.com,
linux-kernel@vger.kernel.org, Li Zhijian <lizhijian@fujitsu.com>,
kernel test robot <lkp@intel.com>
Subject: [PATCH v2] mm/vmstat: Move pgdemote_* to per-node stats
Date: Fri, 3 Nov 2023 11:14:50 +0800 [thread overview]
Message-ID: <20231103031450.1456523-1-lizhijian@fujitsu.com> (raw)
Demotion will migrate pages across nodes. Previously, only the global
demotion statistics were accounted for. Changed them to per-node
statistics, making it easier to observe where demotion occurs on each
node.
This will help to identify which nodes are under pressure.
This patch also make pgdemote_* behind CONFIG_NUMA_BALANCING, since
demotion is not available for !CONFIG_NUMA_BALANCING
With this patch, here is a sample where node0 node1 are DRAM,
node3 is PMEM:
Global stats:
$ grep demote /proc/vmstat
pgdemote_kswapd 254288
pgdemote_direct 113497
pgdemote_khugepaged 0
Per-node stats:
$ grep demote /sys/devices/system/node/node0/vmstat # demotion source
pgdemote_kswapd 68454
pgdemote_direct 83431
pgdemote_khugepaged 0
$ grep demote /sys/devices/system/node/node1/vmstat # demotion source
pgdemote_kswapd 185834
pgdemote_direct 30066
pgdemote_khugepaged 0
$ grep demote /sys/devices/system/node/node3/vmstat # demotion target
pgdemote_kswapd 0
pgdemote_direct 0
pgdemote_khugepaged 0
Reported-by: kernel test robot <lkp@intel.com> # compling errors
Closes: https://lore.kernel.org/oe-kbuild-all/202311030137.Vu2ki6zm-lkp@intel.com/
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
V2: split it as a separate patch from previous patch set.
account them to the source node instead destination and add Acked-by # Huang, Ying
---
include/linux/mmzone.h | 4 ++++
include/linux/vm_event_item.h | 3 ---
mm/vmscan.c | 12 ++++++++----
mm/vmstat.c | 6 +++---
4 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4106fbc5b4b3..ad0309eea850 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,6 +206,10 @@ enum node_stat_item {
#ifdef CONFIG_NUMA_BALANCING
PGPROMOTE_SUCCESS, /* promote successfully */
PGPROMOTE_CANDIDATE, /* candidate pages to promote */
+ /* PGDEMOTE_*: pages demoted */
+ PGDEMOTE_KSWAPD,
+ PGDEMOTE_DIRECT,
+ PGDEMOTE_KHUGEPAGED,
#endif
NR_VM_NODE_STAT_ITEMS
};
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8abfa1240040..d1b847502f09 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
PGSTEAL_KSWAPD,
PGSTEAL_DIRECT,
PGSTEAL_KHUGEPAGED,
- PGDEMOTE_KSWAPD,
- PGDEMOTE_DIRECT,
- PGDEMOTE_KHUGEPAGED,
PGSCAN_KSWAPD,
PGSCAN_DIRECT,
PGSCAN_KHUGEPAGED,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6f13394b112e..cc70dcefc60a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1110,12 +1110,14 @@ void drop_slab(void)
static int reclaimer_offset(void)
{
+#ifdef CONFIG_NUMA_BALANCING
BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
- BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
- PGSCAN_DIRECT - PGSCAN_KSWAPD);
BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
+#endif
+ BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
+ PGSCAN_DIRECT - PGSCAN_KSWAPD);
BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);
@@ -1677,8 +1679,10 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
migrate_pages(demote_folios, alloc_demote_folio, NULL,
(unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
&nr_succeeded);
-
- __count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
+#ifdef CONFIG_NUMA_BALANCING
+ mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(),
+ nr_succeeded);
+#endif
return nr_succeeded;
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 00e81e99c6ee..f141c48c39e4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1244,6 +1244,9 @@ const char * const vmstat_text[] = {
#ifdef CONFIG_NUMA_BALANCING
"pgpromote_success",
"pgpromote_candidate",
+ "pgdemote_kswapd",
+ "pgdemote_direct",
+ "pgdemote_khugepaged",
#endif
/* enum writeback_stat_item counters */
@@ -1275,9 +1278,6 @@ const char * const vmstat_text[] = {
"pgsteal_kswapd",
"pgsteal_direct",
"pgsteal_khugepaged",
- "pgdemote_kswapd",
- "pgdemote_direct",
- "pgdemote_khugepaged",
"pgscan_kswapd",
"pgscan_direct",
"pgscan_khugepaged",
--
2.29.2
next reply other threads:[~2023-11-03 3:15 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-03 3:14 Li Zhijian [this message]
2023-12-28 3:52 ` Zhijian Li (Fujitsu)
2023-12-28 18:22 ` Andrew Morton
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=20231103031450.1456523-1-lizhijian@fujitsu.com \
--to=lizhijian@fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lkp@intel.com \
--cc=rafael@kernel.org \
--cc=y-goto@fujitsu.com \
--cc=ying.huang@intel.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