LKML Archive on lore.kernel.org
 help / Atom feed
From: Michal Hocko <mhocko@kernel.org>
To: Davidlohr Bueso <dave@stgolabs.net>
Cc: akpm@linux-foundation.org, mingo@kernel.org,
	peterz@infradead.org, jack@suse.cz,
	torvalds@linux-foundation.org, kirill.shutemov@linux.intel.com,
	hch@infradead.org, ldufour@linux.vnet.ibm.com,
	mgorman@techsingularity.net, linux-kernel@vger.kernel.org,
	Davidlohr Bueso <dbueso@suse.de>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Vladimir Davydov <vdavydov.dev@gmail.com>
Subject: Re: [PATCH 16/17] mem/memcg: cache rightmost node
Date: Wed, 19 Jul 2017 09:50:36 +0200
Message-ID: <20170719075036.GA26779@dhcp22.suse.cz> (raw)
In-Reply-To: <20170719014603.19029-17-dave@stgolabs.net>

[CC Johannes and Vladimir - the whole series is
http://lkml.kernel.org/r/20170719014603.19029-1-dave@stgolabs.net]

On Tue 18-07-17 18:46:02, Davidlohr Bueso wrote:
> Such that we can optimize __mem_cgroup_largest_soft_limit_node().
> The only overhead is the extra footprint for the cached pointer,
> but this should not be an issue for mem_cgroup_tree_per_node.

The soft limit reclaim and the associated tree manipulation is not worth
touching/optimizing IMHO. We strongly discourage anybody configuring
soft limit because of the way how it is implemented and disruptive.

> Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
> ---
>  mm/memcontrol.c | 23 ++++++++++++++++++-----
>  1 file changed, 18 insertions(+), 5 deletions(-)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 3df3c04d73ab..2ef9328ace2e 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -119,6 +119,7 @@ static const char *const mem_cgroup_lru_names[] = {
>  
>  struct mem_cgroup_tree_per_node {
>  	struct rb_root rb_root;
> +	struct rb_node *rb_rightmost;
>  	spinlock_t lock;
>  };
>  
> @@ -386,6 +387,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
>  	struct rb_node **p = &mctz->rb_root.rb_node;
>  	struct rb_node *parent = NULL;
>  	struct mem_cgroup_per_node *mz_node;
> +	bool rightmost = true;
>  
>  	if (mz->on_tree)
>  		return;
> @@ -397,8 +399,11 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
>  		parent = *p;
>  		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
>  					tree_node);
> -		if (mz->usage_in_excess < mz_node->usage_in_excess)
> +		if (mz->usage_in_excess < mz_node->usage_in_excess) {
>  			p = &(*p)->rb_left;
> +			rightmost = false;
> +		}
> +
>  		/*
>  		 * We can't avoid mem cgroups that are over their soft
>  		 * limit by the same amount
> @@ -406,6 +411,10 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
>  		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
>  			p = &(*p)->rb_right;
>  	}
> +
> +	if (rightmost)
> +		mctz->rb_rightmost = &mz->tree_node;
> +
>  	rb_link_node(&mz->tree_node, parent, p);
>  	rb_insert_color(&mz->tree_node, &mctz->rb_root);
>  	mz->on_tree = true;
> @@ -416,6 +425,10 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
>  {
>  	if (!mz->on_tree)
>  		return;
> +
> +	if (&mz->tree_node == mctz->rb_rightmost)
> +		mctz->rb_rightmost = rb_next(&mz->tree_node);
> +
>  	rb_erase(&mz->tree_node, &mctz->rb_root);
>  	mz->on_tree = false;
>  }
> @@ -496,16 +509,15 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
>  static struct mem_cgroup_per_node *
>  __mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
>  {
> -	struct rb_node *rightmost = NULL;
>  	struct mem_cgroup_per_node *mz;
>  
>  retry:
>  	mz = NULL;
> -	rightmost = rb_last(&mctz->rb_root);
> -	if (!rightmost)
> +	if (!mctz->rb_rightmost)
>  		goto done;		/* Nothing to reclaim from */
>  
> -	mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node);
> +	mz = rb_entry(mctz->rb_rightmost,
> +		      struct mem_cgroup_per_node, tree_node);
>  	/*
>  	 * Remove the node now but someone else can add it back,
>  	 * we will to add it back at the end of reclaim to its correct
> @@ -5850,6 +5862,7 @@ static int __init mem_cgroup_init(void)
>  				    node_online(node) ? node : NUMA_NO_NODE);
>  
>  		rtpn->rb_root = RB_ROOT;
> +		rtpn->rb_rightmost = NULL;
>  		spin_lock_init(&rtpn->lock);
>  		soft_limit_tree.rb_tree_per_node[node] = rtpn;
>  	}
> -- 
> 2.12.0

-- 
Michal Hocko
SUSE Labs

  reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-19  1:45 [PATCH -next v4 00/17] rbtree: cache leftmost node internally Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 01/17] " Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 02/17] rbtree: optimize root-check during rebalancing loop Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 03/17] rbtree: add some additional comments for rebalancing cases Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 04/17] lib/rbtree_test.c: make input module parameters Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 05/17] lib/rbtree_test.c: add (inorder) traversal test Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 06/17] lib/rbtree_test.c: support rb_root_cached Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 07/17] sched/fair: replace cfs_rq->rb_leftmost Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 08/17] sched/deadline: replace earliest dl and rq leftmost caching Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 09/17] locking/rtmutex: replace top-waiter and pi_waiters " Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 10/17] block/cfq: replace cfq_rb_root " Davidlohr Bueso
2017-07-19  7:46   ` Jan Kara
2017-07-19  1:45 ` [PATCH 11/17] lib/interval_tree: fast overlap detection Davidlohr Bueso
2017-07-22 17:52   ` Doug Ledford
2017-08-01 17:16   ` Michael S. Tsirkin
2017-07-19  1:45 ` [PATCH 12/17] lib/interval-tree: correct comment wrt generic flavor Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 13/17] procfs: use faster rb_first_cached() Davidlohr Bueso
2017-07-19  1:46 ` [PATCH 14/17] fs/epoll: " Davidlohr Bueso
2017-07-19  1:46 ` [PATCH 15/17] fs/ext4: use cached rbtrees Davidlohr Bueso
2017-07-19  7:40   ` Jan Kara
2017-07-19 22:50     ` Davidlohr Bueso
2017-07-19  1:46 ` [PATCH 16/17] mem/memcg: cache rightmost node Davidlohr Bueso
2017-07-19  7:50   ` Michal Hocko [this message]
2017-07-26 21:09     ` Andrew Morton
2017-07-27  7:06       ` Michal Hocko
2017-07-19  1:46 ` [PATCH 17/17] block/cfq: cache rightmost rb_node Davidlohr Bueso
2017-07-19  7:59   ` Jan Kara

Reply instructions:

You may reply publically 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=20170719075036.GA26779@dhcp22.suse.cz \
    --to=mhocko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=dave@stgolabs.net \
    --cc=dbueso@suse.de \
    --cc=hannes@cmpxchg.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=ldufour@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vdavydov.dev@gmail.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

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


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


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