All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Hocko <mhocko@suse.cz>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>,
	Hugh Dickins <hughd@google.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch 3/8] mm: vmscan: save work scanning (almost) empty LRU lists
Date: Thu, 13 Dec 2012 16:43:46 +0100	[thread overview]
Message-ID: <20121213154346.GF21644@dhcp22.suse.cz> (raw)
In-Reply-To: <1355348620-9382-4-git-send-email-hannes@cmpxchg.org>

On Wed 12-12-12 16:43:35, Johannes Weiner wrote:
> In certain cases (kswapd reclaim, memcg target reclaim), a fixed
> minimum amount of pages is scanned from the LRU lists on each
> iteration, to make progress.
> 
> Do not make this minimum bigger than the respective LRU list size,
> however, and save some busy work trying to isolate and reclaim pages
> that are not there.
> 
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>

Hmm, shrink_lruvec would do:
	nr_to_scan = min_t(unsigned long,
			   nr[lru], SWAP_CLUSTER_MAX);
	nr[lru] -= nr_to_scan;
and isolate_lru_pages does
	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++)
so it shouldn't matter and we shouldn't do any additional loops, right?

Anyway it would be beter if get_scan_count wouldn't ask for more than is
available.
Reviewed-by: Michal Hocko <mhocko@suse.cz>

> ---
>  include/linux/swap.h |  2 +-
>  mm/vmscan.c          | 10 ++++++----
>  2 files changed, 7 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 68df9c1..8c66486 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -156,7 +156,7 @@ enum {
>  	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
>  };
>  
> -#define SWAP_CLUSTER_MAX 32
> +#define SWAP_CLUSTER_MAX 32UL
>  #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
>  
>  /*
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6e53446..1763e79 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1748,15 +1748,17 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
>  out:
>  	for_each_evictable_lru(lru) {
>  		int file = is_file_lru(lru);
> +		unsigned long size;
>  		unsigned long scan;
>  
> -		scan = get_lru_size(lruvec, lru);
> +		size = get_lru_size(lruvec, lru);
+		size = scan = get_lru_size(lruvec, lru);

>  		if (sc->priority || noswap) {
> -			scan >>= sc->priority;
> +			scan = size >> sc->priority;
>  			if (!scan && force_scan)
> -				scan = SWAP_CLUSTER_MAX;
> +				scan = min(size, SWAP_CLUSTER_MAX);
>  			scan = div64_u64(scan * fraction[file], denominator);
> -		}
> +		} else
> +			scan = size;

And this is not necessary then but this is totally nit.

>  		nr[lru] = scan;
>  	}
>  }
> -- 
> 1.7.11.7
> 

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Michal Hocko <mhocko@suse.cz>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>,
	Hugh Dickins <hughd@google.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch 3/8] mm: vmscan: save work scanning (almost) empty LRU lists
Date: Thu, 13 Dec 2012 16:43:46 +0100	[thread overview]
Message-ID: <20121213154346.GF21644@dhcp22.suse.cz> (raw)
In-Reply-To: <1355348620-9382-4-git-send-email-hannes@cmpxchg.org>

On Wed 12-12-12 16:43:35, Johannes Weiner wrote:
> In certain cases (kswapd reclaim, memcg target reclaim), a fixed
> minimum amount of pages is scanned from the LRU lists on each
> iteration, to make progress.
> 
> Do not make this minimum bigger than the respective LRU list size,
> however, and save some busy work trying to isolate and reclaim pages
> that are not there.
> 
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>

Hmm, shrink_lruvec would do:
	nr_to_scan = min_t(unsigned long,
			   nr[lru], SWAP_CLUSTER_MAX);
	nr[lru] -= nr_to_scan;
and isolate_lru_pages does
	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++)
so it shouldn't matter and we shouldn't do any additional loops, right?

Anyway it would be beter if get_scan_count wouldn't ask for more than is
available.
Reviewed-by: Michal Hocko <mhocko@suse.cz>

> ---
>  include/linux/swap.h |  2 +-
>  mm/vmscan.c          | 10 ++++++----
>  2 files changed, 7 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 68df9c1..8c66486 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -156,7 +156,7 @@ enum {
>  	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
>  };
>  
> -#define SWAP_CLUSTER_MAX 32
> +#define SWAP_CLUSTER_MAX 32UL
>  #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
>  
>  /*
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6e53446..1763e79 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1748,15 +1748,17 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
>  out:
>  	for_each_evictable_lru(lru) {
>  		int file = is_file_lru(lru);
> +		unsigned long size;
>  		unsigned long scan;
>  
> -		scan = get_lru_size(lruvec, lru);
> +		size = get_lru_size(lruvec, lru);
+		size = scan = get_lru_size(lruvec, lru);

>  		if (sc->priority || noswap) {
> -			scan >>= sc->priority;
> +			scan = size >> sc->priority;
>  			if (!scan && force_scan)
> -				scan = SWAP_CLUSTER_MAX;
> +				scan = min(size, SWAP_CLUSTER_MAX);
>  			scan = div64_u64(scan * fraction[file], denominator);
> -		}
> +		} else
> +			scan = size;

And this is not necessary then but this is totally nit.

>  		nr[lru] = scan;
>  	}
>  }
> -- 
> 1.7.11.7
> 

-- 
Michal Hocko
SUSE Labs

  parent reply	other threads:[~2012-12-13 15:43 UTC|newest]

Thread overview: 114+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-12 21:43 [patch 0/8] page reclaim bits Johannes Weiner
2012-12-12 21:43 ` Johannes Weiner
2012-12-12 21:43 ` [patch 1/8] mm: memcg: only evict file pages when we have plenty Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 21:53   ` Rik van Riel
2012-12-12 21:53     ` Rik van Riel
2012-12-12 22:28     ` Johannes Weiner
2012-12-12 22:28       ` Johannes Weiner
2012-12-13 10:07       ` Mel Gorman
2012-12-13 10:07         ` Mel Gorman
2012-12-13 14:44         ` Mel Gorman
2012-12-13 14:44           ` Mel Gorman
2012-12-13 14:55       ` Michal Hocko
2012-12-13 14:55         ` Michal Hocko
2012-12-16  1:21         ` Simon Jeons
2012-12-16  1:21           ` Simon Jeons
2012-12-17 15:54           ` Michal Hocko
2012-12-17 15:54             ` Michal Hocko
2012-12-19  5:21             ` Simon Jeons
2012-12-19  5:21               ` Simon Jeons
2012-12-19  9:20               ` Mel Gorman
2012-12-19  9:20                 ` Mel Gorman
2012-12-13  5:36     ` Simon Jeons
2012-12-13  5:36       ` Simon Jeons
2012-12-13  5:34   ` Simon Jeons
2012-12-13  5:34     ` Simon Jeons
2012-12-12 21:43 ` [patch 2/8] mm: vmscan: disregard swappiness shortly before going OOM Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:01   ` Rik van Riel
2012-12-12 22:01     ` Rik van Riel
2012-12-13  5:56   ` Simon Jeons
2012-12-13  5:56     ` Simon Jeons
2012-12-13 10:34   ` Mel Gorman
2012-12-13 10:34     ` Mel Gorman
2012-12-13 15:29     ` Michal Hocko
2012-12-13 15:29       ` Michal Hocko
2012-12-13 16:05       ` Michal Hocko
2012-12-13 16:05         ` Michal Hocko
2012-12-13 22:25         ` Satoru Moriya
2012-12-13 22:25           ` Satoru Moriya
2012-12-14  4:50           ` Johannes Weiner
2012-12-14  4:50             ` Johannes Weiner
2012-12-14  8:37             ` Michal Hocko
2012-12-14  8:37               ` Michal Hocko
2012-12-14 15:43               ` Rik van Riel
2012-12-14 15:43                 ` Rik van Riel
2012-12-14 16:13                 ` Michal Hocko
2012-12-14 16:13                   ` Michal Hocko
2012-12-15  0:18                   ` Johannes Weiner
2012-12-15  0:18                     ` Johannes Weiner
2012-12-17 16:37                     ` Michal Hocko
2012-12-17 16:37                       ` Michal Hocko
2012-12-17 17:54                       ` Johannes Weiner
2012-12-17 17:54                         ` Johannes Weiner
2012-12-17 19:58                         ` Michal Hocko
2012-12-17 19:58                           ` Michal Hocko
2012-12-14 20:17                 ` Satoru Moriya
2012-12-14 20:17                   ` Satoru Moriya
2012-12-14 19:44               ` Satoru Moriya
2012-12-14 19:44                 ` Satoru Moriya
2012-12-13 19:05     ` Johannes Weiner
2012-12-13 19:05       ` Johannes Weiner
2012-12-13 19:47       ` Mel Gorman
2012-12-13 19:47         ` Mel Gorman
2012-12-12 21:43 ` [patch 3/8] mm: vmscan: save work scanning (almost) empty LRU lists Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:02   ` Rik van Riel
2012-12-12 22:02     ` Rik van Riel
2012-12-13 10:41   ` Mel Gorman
2012-12-13 10:41     ` Mel Gorman
2012-12-13 19:33     ` Johannes Weiner
2012-12-13 19:33       ` Johannes Weiner
2012-12-13 15:43   ` Michal Hocko [this message]
2012-12-13 15:43     ` Michal Hocko
2012-12-13 19:38     ` Johannes Weiner
2012-12-13 19:38       ` Johannes Weiner
2012-12-14  8:46       ` Michal Hocko
2012-12-14  8:46         ` Michal Hocko
2012-12-12 21:43 ` [patch 4/8] mm: vmscan: clarify LRU balancing close to OOM Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:03   ` Rik van Riel
2012-12-12 22:03     ` Rik van Riel
2012-12-13 10:46   ` Mel Gorman
2012-12-13 10:46     ` Mel Gorman
2012-12-12 21:43 ` [patch 5/8] mm: vmscan: improve comment on low-page cache handling Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:04   ` Rik van Riel
2012-12-12 22:04     ` Rik van Riel
2012-12-13 10:47   ` Mel Gorman
2012-12-13 10:47     ` Mel Gorman
2012-12-13 16:07   ` Michal Hocko
2012-12-13 16:07     ` Michal Hocko
2012-12-12 21:43 ` [patch 6/8] mm: vmscan: clean up get_scan_count() Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:06   ` Rik van Riel
2012-12-12 22:06     ` Rik van Riel
2012-12-13 11:07   ` Mel Gorman
2012-12-13 11:07     ` Mel Gorman
2012-12-13 16:18   ` Michal Hocko
2012-12-13 16:18     ` Michal Hocko
2012-12-12 21:43 ` [patch 7/8] mm: vmscan: compaction works against zones, not lruvecs Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:31   ` Rik van Riel
2012-12-12 22:31     ` Rik van Riel
2012-12-13 11:12   ` Mel Gorman
2012-12-13 11:12     ` Mel Gorman
2012-12-13 16:48   ` Michal Hocko
2012-12-13 16:48     ` Michal Hocko
2012-12-12 21:43 ` [patch 8/8] mm: reduce rmap overhead for ex-KSM page copies created on swap faults Johannes Weiner
2012-12-12 21:43   ` Johannes Weiner
2012-12-12 22:34   ` Rik van Riel
2012-12-12 22:34     ` Rik van Riel
2012-12-12 21:50 ` [patch 0/8] page reclaim bits Andrew Morton
2012-12-12 21:50   ` Andrew Morton

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=20121213154346.GF21644@dhcp22.suse.cz \
    --to=mhocko@suse.cz \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=riel@redhat.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.