[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1600204258-13683-1-git-send-email-vijayb@linux.microsoft.com>
Date: Tue, 15 Sep 2020 14:10:57 -0700
From: Vijay Balakrishna <vijayb@...ux.microsoft.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Oleg Nesterov <oleg@...hat.com>,
Song Liu <songliubraving@...com>,
Andrea Arcangeli <aarcange@...hat.com>,
Pavel Tatashin <pasha.tatashin@...een.com>,
Vijay Balakrishna <vijayb@...ux.microsoft.com>,
Michal Hocko <mhocko@...e.com>,
Allen Pais <apais@...rosoft.com>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: [v2 1/2] mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged
When memory is hotplug added or removed the min_free_kbytes must be
recalculated based on what is expected by khugepaged. Currently
after hotplug, min_free_kbytes will be set to a lower default and higher
default set when THP enabled is lost. This leaves the system with small
min_free_kbytes which isn't suitable for systems especially with network
intensive loads. Typical failure symptoms include HW WATCHDOG reset,
soft lockup hang notices, NETDEVICE WATCHDOG timeouts, and OOM process
kills.
Fixes: f000565adb77 ("thp: set recommended min free kbytes")
Signed-off-by: Vijay Balakrishna <vijayb@...ux.microsoft.com>
Cc: stable@...r.kernel.org
Reviewed-by: Pavel Tatashin <pasha.tatashin@...een.com>
---
include/linux/khugepaged.h | 5 +++++
mm/khugepaged.c | 13 +++++++++++--
mm/memory_hotplug.c | 3 +++
3 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index bc45ea1efbf7..c941b7377321 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm);
extern void __khugepaged_exit(struct mm_struct *mm);
extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
unsigned long vm_flags);
+extern void khugepaged_min_free_kbytes_update(void);
#ifdef CONFIG_SHMEM
extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
#else
@@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
unsigned long addr)
{
}
+
+static inline void khugepaged_min_free_kbytes_update(void)
+{
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_KHUGEPAGED_H */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index cfa0dba5fd3b..4f7107476a6f 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -56,6 +56,9 @@ enum scan_result {
#define CREATE_TRACE_POINTS
#include <trace/events/huge_memory.h>
+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
@@ -2292,8 +2295,6 @@ static void set_recommended_min_free_kbytes(void)
int start_stop_khugepaged(void)
{
- static struct task_struct *khugepaged_thread __read_mostly;
- static DEFINE_MUTEX(khugepaged_mutex);
int err = 0;
mutex_lock(&khugepaged_mutex);
@@ -2320,3 +2321,11 @@ int start_stop_khugepaged(void)
mutex_unlock(&khugepaged_mutex);
return err;
}
+
+void khugepaged_min_free_kbytes_update(void)
+{
+ mutex_lock(&khugepaged_mutex);
+ if (khugepaged_enabled() && khugepaged_thread)
+ set_recommended_min_free_kbytes();
+ mutex_unlock(&khugepaged_mutex);
+}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e9d5ab5d3ca0..3e19272c1fad 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -36,6 +36,7 @@
#include <linux/memblock.h>
#include <linux/compaction.h>
#include <linux/rmap.h>
+#include <linux/khugepaged.h>
#include <asm/tlbflush.h>
@@ -857,6 +858,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
zone_pcp_update(zone);
init_per_zone_wmark_min();
+ khugepaged_min_free_kbytes_update();
kswapd_run(nid);
kcompactd_run(nid);
@@ -1600,6 +1602,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
pgdat_resize_unlock(zone->zone_pgdat, &flags);
init_per_zone_wmark_min();
+ khugepaged_min_free_kbytes_update();
if (!populated_zone(zone)) {
zone_pcp_reset(zone);
--
2.28.0
Powered by blists - more mailing lists