All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: Vijay Balakrishna <vijayb@linux.microsoft.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Oleg Nesterov <oleg@redhat.com>, Song Liu <songliubraving@fb.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Allen Pais <apais@microsoft.com>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>
Subject: Re: [[PATCH]] mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged
Date: Tue, 15 Sep 2020 14:22:33 -0400	[thread overview]
Message-ID: <CA+CK2bAyV5h_MWRmho7sXQvqzhS5kOXR5UKXbOMXgMXP5fgmXg@mail.gmail.com> (raw)
In-Reply-To: <1599770859-14826-1-git-send-email-vijayb@linux.microsoft.com>

On Thu, Sep 10, 2020 at 4:47 PM Vijay Balakrishna
<vijayb@linux.microsoft.com> 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.
>
> Fixes: f000565adb77 ("thp: set recommended min free kbytes")
>
> Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
> Cc: stable@vger.kernel.org
> ---
>  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();

The bug makes sense that min_free_kbytes should be consistent after
reboot or after hot-add, hence
Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>

  parent reply	other threads:[~2020-09-15 18:27 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-10 20:47 [[PATCH]] mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged Vijay Balakrishna
2020-09-10 22:01 ` Kirill A. Shutemov
2020-09-10 22:28   ` Pavel Tatashin
2020-09-10 22:28     ` Pavel Tatashin
2020-09-10 22:56     ` Vijay Balakrishna
2020-09-15  5:04   ` Vijay Balakrishna
2020-09-14 14:33 ` Michal Hocko
2020-09-14 16:57   ` Vijay Balakrishna
2020-09-15  8:18     ` Michal Hocko
2020-09-15 15:48       ` Vijay Balakrishna
2020-09-16  6:53         ` Michal Hocko
2020-09-16 18:28           ` Vijay Balakrishna
2020-09-17 12:12             ` Michal Hocko
2020-09-17 18:03               ` Vijay Balakrishna
2020-09-18  5:45                 ` Michal Hocko
2020-09-18 15:32                   ` Vijay Balakrishna
2020-09-21  7:00                     ` Michal Hocko
2020-09-15 18:22 ` Pavel Tatashin [this message]
2020-09-15 18:22   ` Pavel Tatashin

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=CA+CK2bAyV5h_MWRmho7sXQvqzhS5kOXR5UKXbOMXgMXP5fgmXg@mail.gmail.com \
    --to=pasha.tatashin@soleen.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=apais@microsoft.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=oleg@redhat.com \
    --cc=songliubraving@fb.com \
    --cc=vijayb@linux.microsoft.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.