Linux-rt-users Archive on lore.kernel.org
 help / color / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Mel Gorman <mgorman@techsingularity.net>,
	Linux-MM <linux-mm@kvack.org>,
	Linux-RT-Users <linux-rt-users@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Chuck Lever <chuck.lever@oracle.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>, Michal Hocko <mhocko@kernel.org>
Subject: Re: [PATCH 05/11] mm/page_alloc: Batch the accounting updates in the bulk allocator
Date: Wed, 14 Apr 2021 18:31:18 +0200
Message-ID: <e9301fe4-04ce-8bb0-e76c-1ac824c8e1a5@suse.cz> (raw)
In-Reply-To: <20210414133931.4555-6-mgorman@techsingularity.net>

On 4/14/21 3:39 PM, Mel Gorman wrote:
> Now that the zone_statistics are simple counters that do not require
> special protection, the bulk allocator accounting updates can be batch
> updated without adding too much complexity with protected RMW updates or
> using xchg.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Vlastimil Babka <vbabka@suse.cz>

> ---
>  include/linux/vmstat.h |  8 ++++++++
>  mm/page_alloc.c        | 30 +++++++++++++-----------------
>  2 files changed, 21 insertions(+), 17 deletions(-)
> 
> diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> index dde4dec4e7dd..8473b8fa9756 100644
> --- a/include/linux/vmstat.h
> +++ b/include/linux/vmstat.h
> @@ -246,6 +246,14 @@ __count_numa_event(struct zone *zone, enum numa_stat_item item)
>  	raw_cpu_inc(pzstats->vm_numa_event[item]);
>  }
>  
> +static inline void
> +__count_numa_events(struct zone *zone, enum numa_stat_item item, long delta)
> +{
> +	struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats;
> +
> +	raw_cpu_add(pzstats->vm_numa_event[item], delta);
> +}
> +
>  extern void __count_numa_event(struct zone *zone, enum numa_stat_item item);
>  extern unsigned long sum_zone_node_page_state(int node,
>  					      enum zone_stat_item item);
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 9d0f047647e3..cff0f1c98b28 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3411,7 +3411,8 @@ void __putback_isolated_page(struct page *page, unsigned int order, int mt)
>   *
>   * Must be called with interrupts disabled.
>   */
> -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
> +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z,
> +				   long nr_account)
>  {
>  #ifdef CONFIG_NUMA
>  	enum numa_stat_item local_stat = NUMA_LOCAL;
> @@ -3424,12 +3425,12 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
>  		local_stat = NUMA_OTHER;
>  
>  	if (zone_to_nid(z) == zone_to_nid(preferred_zone))
> -		__count_numa_event(z, NUMA_HIT);
> +		__count_numa_events(z, NUMA_HIT, nr_account);
>  	else {
> -		__count_numa_event(z, NUMA_MISS);
> -		__count_numa_event(preferred_zone, NUMA_FOREIGN);
> +		__count_numa_events(z, NUMA_MISS, nr_account);
> +		__count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account);
>  	}
> -	__count_numa_event(z, local_stat);
> +	__count_numa_events(z, local_stat, nr_account);
>  #endif
>  }
>  
> @@ -3475,7 +3476,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
>  	page = __rmqueue_pcplist(zone,  migratetype, alloc_flags, pcp, list);
>  	if (page) {
>  		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
> -		zone_statistics(preferred_zone, zone);
> +		zone_statistics(preferred_zone, zone, 1);
>  	}
>  	local_unlock_irqrestore(&pagesets.lock, flags);
>  	return page;
> @@ -3536,7 +3537,7 @@ struct page *rmqueue(struct zone *preferred_zone,
>  				  get_pcppage_migratetype(page));
>  
>  	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
> -	zone_statistics(preferred_zone, zone);
> +	zone_statistics(preferred_zone, zone, 1);
>  	local_irq_restore(flags);
>  
>  out:
> @@ -5019,7 +5020,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
>  	struct alloc_context ac;
>  	gfp_t alloc_gfp;
>  	unsigned int alloc_flags = ALLOC_WMARK_LOW;
> -	int nr_populated = 0;
> +	int nr_populated = 0, nr_account = 0;
>  
>  	if (unlikely(nr_pages <= 0))
>  		return 0;
> @@ -5092,15 +5093,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
>  				goto failed_irq;
>  			break;
>  		}
> -
> -		/*
> -		 * Ideally this would be batched but the best way to do
> -		 * that cheaply is to first convert zone_statistics to
> -		 * be inaccurate per-cpu counter like vm_events to avoid
> -		 * a RMW cycle then do the accounting with IRQs enabled.
> -		 */
> -		__count_zid_vm_events(PGALLOC, zone_idx(zone), 1);
> -		zone_statistics(ac.preferred_zoneref->zone, zone);
> +		nr_account++;
>  
>  		prep_new_page(page, 0, gfp, 0);
>  		if (page_list)
> @@ -5110,6 +5103,9 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
>  		nr_populated++;
>  	}
>  
> +	__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
> +	zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);
> +
>  	local_unlock_irqrestore(&pagesets.lock, flags);
>  
>  	return nr_populated;
> 


  reply index

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-14 13:39 [PATCH 0/11 v3] Use local_lock for pcp protection and reduce stat overhead Mel Gorman
2021-04-14 13:39 ` [PATCH 01/11] mm/page_alloc: Split per cpu page lists and zone stats Mel Gorman
2021-04-14 13:39 ` [PATCH 02/11] mm/page_alloc: Convert per-cpu list protection to local_lock Mel Gorman
2021-04-14 13:39 ` [PATCH 03/11] mm/vmstat: Convert NUMA statistics to basic NUMA counters Mel Gorman
2021-04-14 13:39 ` [PATCH 04/11] mm/vmstat: Inline NUMA event counter updates Mel Gorman
2021-04-14 16:20   ` Vlastimil Babka
2021-04-14 16:26     ` Vlastimil Babka
2021-04-15  9:34       ` Mel Gorman
2021-04-14 13:39 ` [PATCH 05/11] mm/page_alloc: Batch the accounting updates in the bulk allocator Mel Gorman
2021-04-14 16:31   ` Vlastimil Babka [this message]
2021-04-14 13:39 ` [PATCH 06/11] mm/page_alloc: Reduce duration that IRQs are disabled for VM counters Mel Gorman
2021-04-14 17:10   ` Vlastimil Babka
2021-04-14 13:39 ` [PATCH 07/11] mm/page_alloc: Remove duplicate checks if migratetype should be isolated Mel Gorman
2021-04-14 17:21   ` Vlastimil Babka
2021-04-15  9:33     ` Mel Gorman
2021-04-15 11:24       ` Vlastimil Babka
2021-04-14 13:39 ` [PATCH 08/11] mm/page_alloc: Explicitly acquire the zone lock in __free_pages_ok Mel Gorman
2021-04-15 10:24   ` Vlastimil Babka
2021-04-14 13:39 ` [PATCH 09/11] mm/page_alloc: Avoid conflating IRQs disabled with zone->lock Mel Gorman
2021-04-15 12:25   ` Vlastimil Babka
2021-04-15 14:11     ` Mel Gorman
2021-04-14 13:39 ` [PATCH 10/11] mm/page_alloc: Update PGFREE outside the zone lock in __free_pages_ok Mel Gorman
2021-04-15 13:04   ` Vlastimil Babka
2021-04-14 13:39 ` [PATCH 11/11] mm/page_alloc: Embed per_cpu_pages locking within the per-cpu structure Mel Gorman
2021-04-15 14:53   ` Vlastimil Babka
2021-04-15 15:29     ` Mel Gorman

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=e9301fe4-04ce-8bb0-e76c-1ac824c8e1a5@suse.cz \
    --to=vbabka@suse.cz \
    --cc=brouer@redhat.com \
    --cc=chuck.lever@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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

Linux-rt-users Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rt-users/0 linux-rt-users/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rt-users linux-rt-users/ https://lore.kernel.org/linux-rt-users \
		linux-rt-users@vger.kernel.org
	public-inbox-index linux-rt-users

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rt-users


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git