linux-kernel.vger.kernel.org archive mirror
 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: 17+ 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 22:56     ` 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]

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 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).