From: Tim Chen <tim.c.chen@linux.intel.com>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
linux-mm@kvack.org, akpm@linux-foundation.org
Cc: Wei Xu <weixugc@google.com>, Huang Ying <ying.huang@intel.com>,
Greg Thelen <gthelen@google.com>, Yang Shi <shy828301@gmail.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Tim C Chen <tim.c.chen@intel.com>,
Brice Goglin <brice.goglin@gmail.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>,
Feng Tang <feng.tang@intel.com>,
Jagdish Gediya <jvgediya@linux.ibm.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
David Rientjes <rientjes@google.com>
Subject: Re: [PATCH v5 4/9] mm/demotion: Build demotion targets based on explicit memory tiers
Date: Tue, 07 Jun 2022 15:51:57 -0700 [thread overview]
Message-ID: <c4678658cdd04d14ced7d0407da32f5fdec19f95.camel@linux.intel.com> (raw)
In-Reply-To: <20220603134237.131362-5-aneesh.kumar@linux.ibm.com>
On Fri, 2022-06-03 at 19:12 +0530, Aneesh Kumar K.V wrote:
>
> +int next_demotion_node(int node)
> +{
> + struct demotion_nodes *nd;
> + int target, nnodes, i;
> +
> + if (!node_demotion)
> + return NUMA_NO_NODE;
> +
> + nd = &node_demotion[node];
> +
> + /*
> + * node_demotion[] is updated without excluding this
> + * function from running.
> + *
> + * Make sure to use RCU over entire code blocks if
> + * node_demotion[] reads need to be consistent.
> + */
> + rcu_read_lock();
> +
> + nnodes = nodes_weight(nd->preferred);
> + if (!nnodes)
> + return NUMA_NO_NODE;
> +
> + /*
> + * If there are multiple target nodes, just select one
> + * target node randomly.
> + *
> + * In addition, we can also use round-robin to select
> + * target node, but we should introduce another variable
> + * for node_demotion[] to record last selected target node,
> + * that may cause cache ping-pong due to the changing of
> + * last target node. Or introducing per-cpu data to avoid
> + * caching issue, which seems more complicated. So selecting
> + * target node randomly seems better until now.
> + */
> + nnodes = get_random_int() % nnodes;
> + target = first_node(nd->preferred);
> + for (i = 0; i < nnodes; i++)
> + target = next_node(target, nd->preferred);
We can simplify the above 4 lines.
target = node_random(nd->preferred);
There's still a loop overhead though :(
> +
> + rcu_read_unlock();
> +
> + return target;
> +}
> +
>
> + */
> +static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
> + unsigned long action, void *_arg)
> +{
> + struct memory_notify *arg = _arg;
> +
> + /*
> + * Only update the node migration order when a node is
> + * changing status, like online->offline.
> + */
> + if (arg->status_change_nid < 0)
> + return notifier_from_errno(0);
> +
> + switch (action) {
> + case MEM_OFFLINE:
> + /*
> + * In case we are moving out of N_MEMORY. Keep the node
> + * in the memory tier so that when we bring memory online,
> + * they appear in the right memory tier. We still need
> + * to rebuild the demotion order.
> + */
> + mutex_lock(&memory_tier_lock);
> + establish_migration_targets();
> + mutex_unlock(&memory_tier_lock);
> + break;
> + case MEM_ONLINE:
> + /*
> + * We ignore the error here, if the node already have the tier
> + * registered, we will continue to use that for the new memory
> + * we are adding here.
> + */
> + node_set_memory_tier(arg->status_change_nid, DEFAULT_MEMORY_TIER);
Should establish_migration_targets() be run here? Otherwise what are the
demotion targets for this newly onlined node?
> + break;
> + }
> +
> + return notifier_from_errno(0);
> +}
> +
Tim
next prev parent reply other threads:[~2022-06-07 22:52 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-03 13:42 [PATCH v5 0/9] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-06-03 13:42 ` [PATCH v5 1/9] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-06-07 18:43 ` Tim Chen
2022-06-07 20:18 ` Wei Xu
2022-06-08 4:30 ` Aneesh Kumar K V
2022-06-08 6:06 ` Ying Huang
2022-06-08 4:37 ` Aneesh Kumar K V
2022-06-08 6:10 ` Ying Huang
2022-06-08 8:04 ` Aneesh Kumar K V
2022-06-07 21:32 ` Yang Shi
2022-06-08 1:34 ` Ying Huang
2022-06-08 16:37 ` Yang Shi
2022-06-09 6:52 ` Ying Huang
2022-06-08 4:58 ` Aneesh Kumar K V
2022-06-08 6:18 ` Ying Huang
2022-06-08 16:42 ` Yang Shi
2022-06-09 8:17 ` Aneesh Kumar K V
2022-06-09 16:04 ` Yang Shi
2022-06-08 14:11 ` Johannes Weiner
2022-06-08 14:21 ` Aneesh Kumar K V
2022-06-08 15:55 ` Johannes Weiner
2022-06-08 16:13 ` Aneesh Kumar K V
2022-06-08 18:16 ` Johannes Weiner
2022-06-09 2:33 ` Aneesh Kumar K V
2022-06-09 13:55 ` Johannes Weiner
2022-06-09 14:22 ` Jonathan Cameron
2022-06-09 20:41 ` Johannes Weiner
2022-06-10 6:15 ` Ying Huang
2022-06-10 9:57 ` Jonathan Cameron
2022-06-13 14:05 ` Johannes Weiner
2022-06-13 14:23 ` Aneesh Kumar K V
2022-06-13 15:50 ` Johannes Weiner
2022-06-14 6:48 ` Ying Huang
2022-06-14 8:01 ` Aneesh Kumar K V
2022-06-14 18:56 ` Johannes Weiner
2022-06-15 6:23 ` Aneesh Kumar K V
2022-06-16 1:11 ` Ying Huang
2022-06-16 3:45 ` Wei Xu
2022-06-16 4:47 ` Aneesh Kumar K V
2022-06-16 5:51 ` Ying Huang
2022-06-17 10:41 ` Jonathan Cameron
2022-06-20 1:54 ` Huang, Ying
2022-06-14 16:45 ` Jonathan Cameron
2022-06-21 8:27 ` Aneesh Kumar K V
2022-06-03 13:42 ` [PATCH v5 2/9] mm/demotion: Expose per node memory tier to sysfs Aneesh Kumar K.V
2022-06-07 20:15 ` Tim Chen
2022-06-08 4:55 ` Aneesh Kumar K V
2022-06-08 6:42 ` Ying Huang
2022-06-08 16:06 ` Tim Chen
2022-06-08 16:15 ` Aneesh Kumar K V
2022-06-03 13:42 ` [PATCH v5 3/9] mm/demotion: Move memory demotion related code Aneesh Kumar K.V
2022-06-06 13:39 ` Bharata B Rao
2022-06-03 13:42 ` [PATCH v5 4/9] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-06-07 22:51 ` Tim Chen [this message]
2022-06-08 5:02 ` Aneesh Kumar K V
2022-06-08 6:52 ` Ying Huang
2022-06-08 6:50 ` Ying Huang
2022-06-08 8:19 ` Aneesh Kumar K V
2022-06-08 8:00 ` Ying Huang
2022-06-03 13:42 ` [PATCH v5 5/9] mm/demotion/dax/kmem: Set node's memory tier to MEMORY_TIER_PMEM Aneesh Kumar K.V
2022-06-03 13:42 ` [PATCH v5 6/9] mm/demotion: Add support for removing node from demotion memory tiers Aneesh Kumar K.V
2022-06-07 23:40 ` Tim Chen
2022-06-08 6:59 ` Ying Huang
2022-06-08 8:20 ` Aneesh Kumar K V
2022-06-08 8:23 ` Ying Huang
2022-06-08 8:29 ` Aneesh Kumar K V
2022-06-08 8:34 ` Ying Huang
2022-06-03 13:42 ` [PATCH v5 7/9] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-06-03 13:42 ` [PATCH v5 8/9] mm/demotion: Add documentation for memory tiering Aneesh Kumar K.V
2022-06-03 13:42 ` [PATCH v5 9/9] mm/demotion: Update node_is_toptier to work with memory tiers Aneesh Kumar K.V
2022-06-06 3:11 ` Ying Huang
2022-06-06 3:52 ` Aneesh Kumar K V
2022-06-06 7:24 ` Ying Huang
2022-06-06 8:33 ` Aneesh Kumar K V
2022-06-08 7:26 ` Ying Huang
2022-06-08 8:28 ` Aneesh Kumar K V
2022-06-08 8:32 ` Ying Huang
2022-06-08 14:37 ` Aneesh Kumar K.V
2022-06-08 20:14 ` Tim Chen
2022-06-10 6:04 ` Ying Huang
2022-06-06 4:53 ` [PATCH] mm/demotion: Add sysfs ABI documentation Aneesh Kumar K.V
2022-06-08 13:57 ` [PATCH v5 0/9] mm/demotion: Memory tiers and demotion Johannes Weiner
2022-06-08 14:20 ` Aneesh Kumar K V
2022-06-09 8:53 ` Jonathan Cameron
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=c4678658cdd04d14ced7d0407da32f5fdec19f95.camel@linux.intel.com \
--to=tim.c.chen@linux.intel.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.ibm.com \
--cc=apopple@nvidia.com \
--cc=baolin.wang@linux.alibaba.com \
--cc=brice.goglin@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=dave@stgolabs.net \
--cc=feng.tang@intel.com \
--cc=gthelen@google.com \
--cc=hesham.almatary@huawei.com \
--cc=jvgediya@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=rientjes@google.com \
--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