linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Aneesh Kumar K V <aneesh.kumar@linux.ibm.com>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: linux-mm@kvack.org, akpm@linux-foundation.org,
	Wei Xu <weixugc@google.com>, Yang Shi <shy828301@gmail.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Tim C Chen <tim.c.chen@intel.com>,
	Michal Hocko <mhocko@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Hesham Almatary <hesham.almatary@huawei.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Alistair Popple <apopple@nvidia.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	jvgediya.oss@gmail.com
Subject: Re: [PATCH v11 8/8] mm/demotion: Update node_is_toptier to work with memory tiers
Date: Fri, 29 Jul 2022 12:17:45 +0530	[thread overview]
Message-ID: <e213cd43-e451-e837-b591-08e3400dd22e@linux.ibm.com> (raw)
In-Reply-To: <9fa09da8-eff7-e39a-96b0-2bc51711f08f@linux.ibm.com>

On 7/29/22 12:11 PM, Aneesh Kumar K V wrote:
> On 7/29/22 12:09 PM, Huang, Ying wrote:
>> "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> writes:
>>
>>> With memory tiers support we can have memory only NUMA nodes
>>> in the top tier from which we want to avoid promotion tracking NUMA
>>> faults. Update node_is_toptier to work with memory tiers.
>>> All NUMA nodes are by default top tier nodes. With lower memory
>>> tiers added we consider all memory tiers above a memory tier having
>>> CPU NUMA nodes as a top memory tier
>>>
>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>>> ---
>>>  include/linux/memory-tiers.h | 11 ++++++++++
>>>  include/linux/node.h         |  5 -----
>>>  mm/huge_memory.c             |  1 +
>>>  mm/memory-tiers.c            | 42 ++++++++++++++++++++++++++++++++++++
>>>  mm/migrate.c                 |  1 +
>>>  mm/mprotect.c                |  1 +
>>>  6 files changed, 56 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
>>> index f8dbeda617a7..bc9fb9d39b2c 100644
>>> --- a/include/linux/memory-tiers.h
>>> +++ b/include/linux/memory-tiers.h
>>> @@ -35,6 +35,7 @@ struct memory_dev_type *init_node_memory_type(int node, struct memory_dev_type *
>>>  #ifdef CONFIG_MIGRATION
>>>  int next_demotion_node(int node);
>>>  void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
>>> +bool node_is_toptier(int node);
>>>  #else
>>>  static inline int next_demotion_node(int node)
>>>  {
>>> @@ -45,6 +46,11 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
>>>  {
>>>  	*targets = NODE_MASK_NONE;
>>>  }
>>> +
>>> +static inline bool node_is_toptier(int node)
>>> +{
>>> +	return true;
>>> +}
>>>  #endif
>>>  
>>>  #else
>>> @@ -64,5 +70,10 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
>>>  {
>>>  	*targets = NODE_MASK_NONE;
>>>  }
>>> +
>>> +static inline bool node_is_toptier(int node)
>>> +{
>>> +	return true;
>>> +}
>>>  #endif	/* CONFIG_NUMA */
>>>  #endif  /* _LINUX_MEMORY_TIERS_H */
>>> diff --git a/include/linux/node.h b/include/linux/node.h
>>> index 40d641a8bfb0..9ec680dd607f 100644
>>> --- a/include/linux/node.h
>>> +++ b/include/linux/node.h
>>> @@ -185,9 +185,4 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
>>>  
>>>  #define to_node(device) container_of(device, struct node, dev)
>>>  
>>> -static inline bool node_is_toptier(int node)
>>> -{
>>> -	return node_state(node, N_CPU);
>>> -}
>>> -
>>>  #endif /* _LINUX_NODE_H_ */
>>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>>> index 834f288b3769..8405662646e9 100644
>>> --- a/mm/huge_memory.c
>>> +++ b/mm/huge_memory.c
>>> @@ -35,6 +35,7 @@
>>>  #include <linux/numa.h>
>>>  #include <linux/page_owner.h>
>>>  #include <linux/sched/sysctl.h>
>>> +#include <linux/memory-tiers.h>
>>>  
>>>  #include <asm/tlb.h>
>>>  #include <asm/pgalloc.h>
>>> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
>>> index 84e2be31a853..36d87dc422ab 100644
>>> --- a/mm/memory-tiers.c
>>> +++ b/mm/memory-tiers.c
>>> @@ -30,6 +30,7 @@ static DEFINE_MUTEX(memory_tier_lock);
>>>  static LIST_HEAD(memory_tiers);
>>>  struct memory_dev_type *node_memory_types[MAX_NUMNODES];
>>>  #ifdef CONFIG_MIGRATION
>>> +static int top_tier_adistance;
>>>  /*
>>>   * node_demotion[] examples:
>>>   *
>>> @@ -159,6 +160,31 @@ static struct memory_tier *__node_get_memory_tier(int node)
>>>  }
>>>  
>>>  #ifdef CONFIG_MIGRATION
>>> +bool node_is_toptier(int node)
>>> +{
>>> +	bool toptier;
>>> +	pg_data_t *pgdat;
>>> +	struct memory_tier *memtier;
>>> +
>>> +	pgdat = NODE_DATA(node);
>>> +	if (!pgdat)
>>> +		return false;
>>> +
>>> +	rcu_read_lock();
>>> +	memtier = rcu_dereference(pgdat->memtier);
>>> +	if (!memtier) {
>>> +		toptier = true;
>>> +		goto out;
>>> +	}
>>> +	if (memtier->adistance_start >= top_tier_adistance)
>>> +		toptier = true;
>>> +	else
>>> +		toptier = false;
>>> +out:
>>> +	rcu_read_unlock();
>>> +	return toptier;
>>> +}
>>> +
>>>  void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
>>>  {
>>>  	struct memory_tier *memtier;
>>> @@ -315,6 +341,22 @@ static void establish_demotion_targets(void)
>>>  			}
>>>  		} while (1);
>>>  	}
>>> +	/*
>>> +	 * Promotion is allowed from a memory tier to higher
>>> +	 * memory tier only if the memory tier doesn't include
>>> +	 * compute. We want to  skip promotion from a memory tier,
>>> +	 * if any node that is  part of the memory tier have CPUs.
>>> +	 * Once we detect such a memory tier, we consider that tier
>>> +	 * as top tiper from which promotion on is not allowed.
>>> +	 */
>>> +	list_for_each_entry(memtier, &memory_tiers, list) {
>>> +		tier_nodes = get_memtier_nodemask(memtier);
>>> +		nodes_and(tier_nodes, node_states[N_CPU], tier_nodes);
>>> +		if (!nodes_empty(tier_nodes)) {
>>> +			top_tier_adistance = memtier->adistance_start;
>>
>> IMHO, this should be,
>>
>> 			top_tier_adistance = memtier->adistance_start + MEMTIER_CHUNK_SIZE;
>>
> 
> Good catch. Will update. BTW i did send v12 version of the patchset already to the list. 
> 
>

Checking this again, we consider a node top tier if the node's memtier abstract distance
satisfy the below.  

	if (memtier->adistance_start <= top_tier_adistance)
		toptier = true;
	
With that we should be good with the current code. But I agree with you that top_tier_distance
should cover the full range of the top memory tier.

-aneesh


  reply	other threads:[~2022-07-29  6:48 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-28 19:04 [PATCH v11 0/8] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-07-28 19:04 ` [PATCH v11 1/8] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-07-29  6:25   ` Huang, Ying
2022-07-29  7:24     ` Aneesh Kumar K.V
2022-08-02  2:50   ` Dan Williams
2022-08-02  3:16     ` Huang, Ying
2022-08-02  3:40       ` Dan Williams
2022-08-02  5:03         ` Aneesh Kumar K V
2022-08-02  6:57         ` Huang, Ying
2022-08-02  9:34           ` Aneesh Kumar K V
2022-08-04  0:56             ` Huang, Ying
2022-08-04  4:49               ` Aneesh Kumar K V
2022-08-04  5:19                 ` Huang, Ying
2022-07-28 19:04 ` [PATCH v11 2/8] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-07-28 19:04 ` [PATCH v11 3/8] mm/demotion: Add hotplug callbacks to handle new numa node onlined Aneesh Kumar K.V
2022-07-28 19:04 ` [PATCH v11 4/8] mm/demotion/dax/kmem: Set node's abstract distance to MEMTIER_ADISTANCE_PMEM Aneesh Kumar K.V
2022-07-29  6:20   ` Huang, Ying
2022-07-29  7:19     ` Aneesh Kumar K.V
2022-08-01  2:06       ` Huang, Ying
2022-08-01  4:40         ` Aneesh Kumar K V
2022-08-01  5:10           ` Huang, Ying
2022-08-01  5:38             ` Aneesh Kumar K V
2022-08-01  6:37               ` Huang, Ying
2022-08-01  6:55                 ` Aneesh Kumar K V
2022-08-01  7:13                   ` Huang, Ying
2022-08-01  7:41                     ` Aneesh Kumar K V
2022-08-02  1:58                       ` Huang, Ying
2022-07-28 19:04 ` [PATCH v11 5/8] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-07-29  6:35   ` Huang, Ying
2022-07-29  7:22     ` Aneesh Kumar K.V
2022-08-01  2:15       ` Huang, Ying
2022-07-28 19:04 ` [PATCH v11 6/8] mm/demotion: Add pg_data_t member to track node memory tier details Aneesh Kumar K.V
2022-07-28 19:04 ` [PATCH v11 7/8] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-07-28 19:04 ` [PATCH v11 8/8] mm/demotion: Update node_is_toptier to work with memory tiers Aneesh Kumar K.V
2022-07-29  6:39   ` Huang, Ying
2022-07-29  6:41     ` Aneesh Kumar K V
2022-07-29  6:47       ` Aneesh Kumar K V [this message]
2022-08-01  1:04         ` Huang, Ying
2022-07-29  5:30 ` [PATCH v11 0/8] mm/demotion: Memory tiers and demotion Huang, Ying
2022-07-29  6:17   ` Aneesh Kumar K.V

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=e213cd43-e451-e837-b591-08e3400dd22e@linux.ibm.com \
    --to=aneesh.kumar@linux.ibm.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=apopple@nvidia.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=dave@stgolabs.net \
    --cc=hannes@cmpxchg.org \
    --cc=hesham.almatary@huawei.com \
    --cc=jvgediya.oss@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shy828301@gmail.com \
    --cc=tim.c.chen@intel.com \
    --cc=weixugc@google.com \
    --cc=ying.huang@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox