Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1419648

Re: [PATCH 03/27] mm, vmscan: Move LRU lists to node

From Vlastimil Babka <vbabka@suse.cz>
Newsgroups linux.kernel
Subject Re: [PATCH 03/27] mm, vmscan: Move LRU lists to node
Date 2016-06-10 20:10 +0200
Message-ID <rIz2z-81e-45@gated-at.bofh.it> (permalink)
References <rIcyZ-1vR-3@gated-at.bofh.it> <rIcz0-1vR-51@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

[+CC Michal Hocko]

On 06/09/2016 08:04 PM, Mel Gorman wrote:
> This moves the LRU lists from the zone to the node and all related data
> such as counters, tracing, congestion tracking and writeback tracking.
> This is mostly a mechanical patch but note that it introduces a number
> of anomalies. For example, the scans are per-zone but using per-node
> counters. We also mark a node as congested when a zone is congested. This
> causes weird problems that are fixed later but is easier to review.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>


> @@ -535,17 +525,21 @@ struct zone {
>  
>  enum zone_flags {
>  	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
> -	ZONE_CONGESTED,			/* zone has many dirty pages backed by
> +	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */

This one has been zapped recently, looks like rebasing resurrected it.

> @@ -1455,13 +1455,22 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
>  		enum compact_result compact_result;
>  
>  		/*
> +		 * This over-estimates the number of pages available for
> +		 * reclaim/compaction but walking the LRU would take too
> +		 * long. The consequences are that compaction may retry
> +		 * longer than it should for a zone-constrained allocation
> +		 * request.
> +		 */
> +		available = pgdat_reclaimable_pages(zone->zone_pgdat);

I'm worried if "longer than it should" means "potentially forever", as
the limit on retries in should_compact_retry() doesn't apply when this
function returns true. Unless some later patches change that.

I'm starting to wonder if it's a good idea to give up per-zone LRU
accounting, because we still have per-zone watermarks that we are trying
to satisfy. How will we even recognize situation where a small zone is
so depleted of LRU pages that it can't even reach its watermarks,
causing a massive whole-node reclaim? Couldn't we have a combination of
per-node lru with per-zone accounting?

> +
> +		/*
>  		 * Do not consider all the reclaimable memory because we do not
>  		 * want to trash just for a single high order allocation which
>  		 * is even not guaranteed to appear even if __compaction_suitable
>  		 * is happy about the watermark check.
>  		 */
> -		available = zone_reclaimable_pages(zone) / order;

This removed the scaling by order. Accidentally I guess, as the comment
is still there.

>  		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> +		available = min(zone->managed_pages, available);
>  		compact_result = __compaction_suitable(zone, order, alloc_flags,
>  				ac_classzone_idx(ac), available);
>  		if (compact_result != COMPACT_SKIPPED &&

[...]

> @@ -1826,7 +1827,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
>  	}
>  
>  	page_lru = page_is_file_cache(page);
> -	mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
> +	mod_node_page_state(page_zone(page)->zone_pgdat, NR_ISOLATED_ANON + page_lru,

This again, I won't point out further. But I think a page_node() (or
page_pgdat()?) function is called for?

> @@ -3486,10 +3486,19 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
>  		unsigned long available;
>  		unsigned long reclaimable;
>  
> -		available = reclaimable = zone_reclaimable_pages(zone);
> -		available -= DIV_ROUND_UP(no_progress_loops * available,
> +		/*
> +		 * This over-estimates the number of pages available for
> +		 * reclaim but walking the LRU would take too long. The
> +		 * consequences are that this may continue trying to
> +		 * reclaim for zone-constrained allocations even if those
> +		 * zones are already depleted.
> +		 */
> +		reclaimable = pgdat_reclaimable_pages(zone->zone_pgdat);
> +		reclaimable = min(zone->managed_pages, reclaimable);
> +		available = reclaimable - DIV_ROUND_UP(no_progress_loops * reclaimable,
>  					  MAX_RECLAIM_RETRIES);
>  		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
> +		available = min(zone->managed_pages, available);
>  
>  		/*
>  		 * Would the allocation succeed if we reclaimed the whole

This adds to my worries about per-node LRU accounting :/

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH 00/27] Move LRU page reclaim from zones to nodes v6 Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
  [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
  [PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 07/27] mm, vmscan: Remove balance gap Vlastimil Babka <vbabka@suse.cz> - 2016-06-15 16:30 +0200
  [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 02/27] mm, vmscan: Move lru_lock to the node Vlastimil Babka <vbabka@suse.cz> - 2016-06-10 18:40 +0200
      Re: [PATCH 02/27] mm, vmscan: Move lru_lock to the node Peter Zijlstra <peterz@infradead.org> - 2016-06-10 19:50 +0200
      Re: [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-14 16:50 +0200
  [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for  the requested classzone Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 12:50 +0200
      Re: [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for  the requested classzone Mel Gorman <mgorman@techsingularity.net> - 2016-06-17 14:10 +0200
  [PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 18/27] mm: Move most file-based accounting to the node Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 10:40 +0200
  [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 10:30 +0200
  [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
  [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for  compaction on a per-node basis Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 11:30 +0200
      Re: [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for  compaction on a per-node basis Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 12:30 +0200
  [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether  kswapd sleeps Vlastimil Babka <vbabka@suse.cz> - 2016-06-15 17:20 +0200
      Re: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether  kswapd sleeps Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 10:40 +0200
        Re: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether  kswapd sleeps Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 11:20 +0200
  [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
  [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages  skipped during reclaim Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 14:40 +0200
  [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Vlastimil Babka <vbabka@suse.cz> - 2016-06-10 15:40 +0200
      Re: [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman <mgorman@techsingularity.net> - 2016-06-10 15:50 +0200
    Re: [PATCH 01/27] mm, vmstat: Add infrastructure for per-node  vmstats Christoph Lameter <cl@linux.com> - 2016-06-13 19:30 +0200
      Re: [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman <mgorman@techsingularity.net> - 2016-06-14 16:30 +0200
  [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms  of nodes Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 17:50 +0200
  [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node  basis Vlastimil Babka <vbabka@suse.cz> - 2016-06-15 15:00 +0200
  [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Vlastimil Babka <vbabka@suse.cz> - 2016-06-15 16:30 +0200
  [PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
  [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:10 +0200
    Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more  node-centric Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 15:40 +0200
      Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more  node-centric Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 16:50 +0200
  [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 16/27] mm: Move page mapped accounting to the node Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 18:00 +0200
      Re: [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 18:10 +0200
  [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 13:00 +0200
  [PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 09/27] mm, vmscan: By default have direct reclaim only  shrink once per node Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 11:00 +0200
  [PATCH 14/27] mm, workingset: Make working set detection node-aware Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 14/27] mm, workingset: Make working set detection  node-aware Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 17:20 +0200
      Re: [PATCH 14/27] mm, workingset: Make working set detection  node-aware Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 18:00 +0200
  [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Vlastimil Babka <vbabka@suse.cz> - 2016-06-17 13:30 +0200
      Re: [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman <mgorman@techsingularity.net> - 2016-06-17 14:10 +0200
  [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:20 +0200
    Re: [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones  to nodes Vlastimil Babka <vbabka@suse.cz> - 2016-06-16 17:10 +0200
      Re: [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones  to nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-16 18:00 +0200
  [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman <mgorman@techsingularity.net> - 2016-06-09 20:30 +0200
  Re: [PATCH 03/27] mm, vmscan: Move LRU lists to node Vlastimil Babka <vbabka@suse.cz> - 2016-06-10 20:10 +0200

csiph-web