Re: [PATCH] thp: reduce khugepaged freezing latency

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 11/09/2011 08:40 PM, Andrea Arcangeli wrote:
> On Wed, Nov 09, 2011 at 10:34:47AM -0800, Tejun Heo wrote:
>> know.  My instinct tells me to strongly recommend use of
>> wait_event_freezable_timeout() and run away.  :)
> 
> Passing false wasn't so appealing to me but ok. Jiri can you test this
> with some suspend? (beware builds but untested)
> 
> ===
> From: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Subject: thp: reduce khugepaged freezing latency
> 
> Use wait_event_freezable_timeout() instead of
> schedule_timeout_interruptible() to avoid missing freezer wakeups. A
> try_to_freeze() would have been needed in the
> khugepaged_alloc_hugepage tight loop too in case of the allocation
> failing repeatedly, and wait_event_freezable_timeout will provide it
> too.
> 
> khugepaged would still freeze just fine by trying again the next
> minute but it's better if it freezes immediately.
> 
> Reported-by: Jiri Slaby <jslaby@xxxxxxx>

Tested-by: Jiri Slaby <jslaby@xxxxxxx>

> Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> ---
>  mm/huge_memory.c |   14 ++++----------
>  1 files changed, 4 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 4298aba..fd925d0 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2259,12 +2259,9 @@ static void khugepaged_do_scan(struct page **hpage)
>  
>  static void khugepaged_alloc_sleep(void)
>  {
> -	DEFINE_WAIT(wait);
> -	add_wait_queue(&khugepaged_wait, &wait);
> -	schedule_timeout_interruptible(
> -		msecs_to_jiffies(
> -			khugepaged_alloc_sleep_millisecs));
> -	remove_wait_queue(&khugepaged_wait, &wait);
> +	wait_event_freezable_timeout(khugepaged_wait, false,
> +				     msecs_to_jiffies(
> +					     khugepaged_alloc_sleep_millisecs));
>  }
>  
>  #ifndef CONFIG_NUMA
> @@ -2313,14 +2310,11 @@ static void khugepaged_loop(void)
>  		if (unlikely(kthread_should_stop()))
>  			break;
>  		if (khugepaged_has_work()) {
> -			DEFINE_WAIT(wait);
>  			if (!khugepaged_scan_sleep_millisecs)
>  				continue;
> -			add_wait_queue(&khugepaged_wait, &wait);
> -			schedule_timeout_interruptible(
> +			wait_event_freezable_timeout(khugepaged_wait, false,
>  				msecs_to_jiffies(
>  					khugepaged_scan_sleep_millisecs));
> -			remove_wait_queue(&khugepaged_wait, &wait);
>  		} else if (khugepaged_enabled())
>  			wait_event_freezable(khugepaged_wait,
>  					     khugepaged_wait_event());

thanks,
-- 
js

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]