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 <[email protected]>
Cc: [email protected]
Reviewed-by: Pavel Tatashin <[email protected]>
---
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
On Tue 15-09-20 14:10:57, Vijay Balakrishna wrote:
> 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.
This changelog still doesn't explain the underlying problem IMO. It
sounds it is papering over some other problem. I do agree that the
current behavior is non intuitive and surprising. Justifying the change
by that inconsistency is likely much better than arguing with soft
lockups and OOMs which shouldn't be a result of this inconsistency.
> Fixes: f000565adb77 ("thp: set recommended min free kbytes")
>
> Signed-off-by: Vijay Balakrishna <[email protected]>
> Cc: [email protected]
> Reviewed-by: Pavel Tatashin <[email protected]>
> ---
> 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
--
Michal Hocko
SUSE Labs
Hi
[This is an automated email]
This commit has been processed because it contains a "Fixes:" tag
fixing commit: f000565adb77 ("thp: set recommended min free kbytes").
The bot has tested the following trees: v5.8.10, v5.4.66, v4.19.146, v4.14.198, v4.9.236, v4.4.236.
v5.8.10: Build OK!
v5.4.66: Build OK!
v4.19.146: Failed to apply! Possible dependencies:
013de2d6671d ("csky: MMU and page table management")
27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
426dcd4b600f ("hexagon: switch to NO_BOOTMEM")
6471f52af786 ("alpha: switch to NO_BOOTMEM")
9143a9359d05 ("csky: Kernel booting")
aca52c398389 ("mm: remove CONFIG_HAVE_MEMBLOCK")
bc3ec75de545 ("dma-mapping: merge direct and noncoherent ops")
c32e64e852f3 ("csky: Build infrastructure")
ca9a46f8a4f0 ("mm/memory_hotplug: online_pages cannot be 0 in online_pages()")
de1193f0be66 ("mm, memory_hotplug: update pcp lists everytime onlining a memory block")
e0a9317d9004 ("hexagon: use generic dma_noncoherent_ops")
e900a918b098 ("mm: shuffle initial free memory to improve memory-side-cache utilization")
f3ecc0ff0457 ("dma-mapping: move the dma_coherent flag to struct device")
f406f222d4b2 ("hexagon: implement the sync_sg_for_device DMA operation")
v4.14.198: Failed to apply! Possible dependencies:
008ef0969dd9 ("btrfs: drop lock parameter from update_ioctl_balance_args and rename")
17ef445f9bef ("Documentation/filesystems: update documentation of file_operations")
27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
3d8f7615319b ("vfs: implement readahead(2) using POSIX_FADV_WILLNEED")
45cd0faae371 ("vfs: add the fadvise() file operation")
5740c99e9d30 ("vfs: dedupe: return int")
6e8b704df584 ("fs: update documentation to mention __poll_t and match the code")
87eb5eb24232 ("vfs: dedupe: rationalize args")
b4e98d9ac775 ("mm: account pud page tables")
c4812909f5d5 ("mm: introduce wrappers to access mm->nr_ptes")
ca9a46f8a4f0 ("mm/memory_hotplug: online_pages cannot be 0 in online_pages()")
de1193f0be66 ("mm, memory_hotplug: update pcp lists everytime onlining a memory block")
e900a918b098 ("mm: shuffle initial free memory to improve memory-side-cache utilization")
f51d2b59120f ("btrfs: allow to set compression level for zlib")
f5c29bd9dbd3 ("Btrfs: add __init macro to btrfs init functions")
v4.9.236: Failed to apply! Possible dependencies:
0b89ede62963 ("s390/mm: fork vs. 5 level page tabel")
27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
505a60e22560 ("asm-generic: introduce 5level-fixup.h")
a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages")
b4e98d9ac775 ("mm: account pud page tables")
c2febafc6773 ("mm: convert generic code to 5-level paging")
c4812909f5d5 ("mm: introduce wrappers to access mm->nr_ptes")
c763ea2650df ("x86/kconfig: Sort the 'config X86' selects alphabetically")
d94e068573f2 ("x86/kconfig: Move 64-bit only arch Kconfig selects to 'config X86_64'")
v4.4.236: Failed to apply! Possible dependencies:
0b57d6ba0bd1 ("mm/mmap.c: remove redundant local variables for may_expand_vm()")
1170532bb49f ("mm: convert printk(KERN_<LEVEL> to pr_<level>")
27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
5a6e75f8110c ("shmem: prepare huge= mount option and sysfs knob")
756a025f0009 ("mm: coalesce split strings")
84638335900f ("mm: rework virtual memory accounting")
8cee852ec53f ("mm, procfs: breakdown RSS for anon, shmem and file in /proc/pid/status")
b46e756f5e47 ("thp: extract khugepaged from mm/huge_memory.c")
d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR")
d977d56ce5b3 ("mm: warn about VmData over RLIMIT_DATA")
d9fe4fab1197 ("x86/mm/pat: Add untrack_pfn_moved for mremap")
eca56ff906bd ("mm, shmem: add internal shmem resident memory accounting")
NOTE: The patch will not be queued to stable trees until it is upstream.
How should we proceed with this patch?
--
Thanks
Sasha