From: Aneesh Kumar K V <aneesh.kumar@linux.ibm.com>
To: Ying Huang <ying.huang@intel.com>
Cc: 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>,
linux-mm@kvack.org, akpm@linux-foundation.org
Subject: Re: [RFC PATCH v4 1/7] mm/demotion: Add support for explicit memory tiers
Date: Mon, 6 Jun 2022 11:31:20 +0530 [thread overview]
Message-ID: <eb6d7346-32a9-4fb2-61c2-a413c9f94f1c@linux.ibm.com> (raw)
In-Reply-To: <143e40bcf46097d14514504518fdc1870fd8d4a1.camel@intel.com>
On 6/6/22 11:03 AM, Ying Huang wrote:
> On Mon, 2022-06-06 at 09:26 +0530, Aneesh Kumar K V wrote:
>> On 6/6/22 8:19 AM, Ying Huang wrote:
>>> On Thu, 2022-06-02 at 14:07 +0800, Ying Huang wrote:
>>>> On Fri, 2022-05-27 at 17:55 +0530, Aneesh Kumar K.V wrote:
>>>>> From: Jagdish Gediya <jvgediya@linux.ibm.com>
>>>>>
>>>>> In the current kernel, memory tiers are defined implicitly via a
>>>>> demotion path relationship between NUMA nodes, which is created
>>>>> during the kernel initialization and updated when a NUMA node is
>>>>> hot-added or hot-removed. The current implementation puts all
>>>>> nodes with CPU into the top tier, and builds the tier hierarchy
>>>>> tier-by-tier by establishing the per-node demotion targets based
>>>>> on the distances between nodes.
>>>>>
>>>>> This current memory tier kernel interface needs to be improved for
>>>>> several important use cases,
>>>>>
>>>>> The current tier initialization code always initializes
>>>>> each memory-only NUMA node into a lower tier. But a memory-only
>>>>> NUMA node may have a high performance memory device (e.g. a DRAM
>>>>> device attached via CXL.mem or a DRAM-backed memory-only node on
>>>>> a virtual machine) and should be put into a higher tier.
>>>>>
>>>>> The current tier hierarchy always puts CPU nodes into the top
>>>>> tier. But on a system with HBM or GPU devices, the
>>>>> memory-only NUMA nodes mapping these devices should be in the
>>>>> top tier, and DRAM nodes with CPUs are better to be placed into the
>>>>> next lower tier.
>>>>>
>>>>> With current kernel higher tier node can only be demoted to selected nodes on the
>>>>> next lower tier as defined by the demotion path, not any other
>>>>> node from any lower tier. This strict, hard-coded demotion order
>>>>> does not work in all use cases (e.g. some use cases may want to
>>>>> allow cross-socket demotion to another node in the same demotion
>>>>> tier as a fallback when the preferred demotion node is out of
>>>>> space), This demotion order is also inconsistent with the page
>>>>> allocation fallback order when all the nodes in a higher tier are
>>>>> out of space: The page allocation can fall back to any node from
>>>>> any lower tier, whereas the demotion order doesn't allow that.
>>>>>
>>>>> The current kernel also don't provide any interfaces for the
>>>>> userspace to learn about the memory tier hierarchy in order to
>>>>> optimize its memory allocations.
>>>>>
>>>>> This patch series address the above by defining memory tiers explicitly.
>>>>>
>>>>> This patch adds below sysfs interface which is read-only and
>>>>> can be used to read nodes available in specific tier.
>>>>>
>>>>> /sys/devices/system/memtier/memtierN/nodelist
>>>>>
>>>>> Tier 0 is the highest tier, while tier MAX_MEMORY_TIERS - 1 is the
>>>>> lowest tier. The absolute value of a tier id number has no specific
>>>>> meaning. what matters is the relative order of the tier id numbers.
>>>>>
>>>>> All the tiered memory code is guarded by CONFIG_TIERED_MEMORY.
>>>>> Default number of memory tiers are MAX_MEMORY_TIERS(3). All the
>>>>> nodes are by default assigned to DEFAULT_MEMORY_TIER(1).
>>>>>
>>>>> Default memory tier can be read from,
>>>>> /sys/devices/system/memtier/default_tier
>>>>>
>>>>> Max memory tier can be read from,
>>>>> /sys/devices/system/memtier/max_tiers
>>>>>
>>>>> This patch implements the RFC spec sent by Wei Xu <weixugc@google.com> at [1].
>>>>>
>>>>> [1] https://lore.kernel.org/linux-mm/CAAPL-u-DGLcKRVDnChN9ZhxPkfxQvz9Sb93kVoX_4J2oiJSkUw@mail.gmail.com/
>>>>>
>>>>> Signed-off-by: Jagdish Gediya <jvgediya@linux.ibm.com>
>>>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>>>>
>>>> IMHO, we should change the kernel internal implementation firstly, then
>>>> implement the kerne/user space interface. That is, make memory tier
>>>> explicit inside kernel, then expose it to user space.
>>>
>>> Why ignore this comment for v5? If you don't agree, please respond me.
>>>
>>
>> I am not sure what benefit such a rearrange would bring in? Right now I
>> am writing the series from the point of view of introducing all the
>> plumbing and them switching the existing demotion logic to use the new
>> infrastructure. Redoing the code to hide all the userspace sysfs till we
>> switch the demotion logic to use the new infrastructure doesn't really
>> bring any additional clarity to patch review and would require me to
>> redo the series with a lot of conflicts across the patches in the patchset.
>
> IMHO, we shouldn't introduce regression even in the middle of a
> patchset. Each step should only rely on previous patches in the series
> to work correctly. In your current way of organization, after patch
> [1/7], on a system with 2 memory tiers, the user space interface will
> output wrong information (only 1 memory tier). So I think the correct
> way is to make it right inside the kenrel firstly, then expose the right
> information to user space.
>
The patchset doesn't add additional tier until "mm/demotion/dax/kmem:
Set node's memory tier to MEMORY_TIER_PMEM". ie, there is no additional
tiers done till all the demotion logic is in place. So even if the
system got dax/kmem, the support for adding dax/kmem as a memory tier
comes later in the patch series.
-aneesh
next prev parent reply other threads:[~2022-06-06 6:02 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-26 21:22 RFC: Memory Tiering Kernel Interfaces (v3) Wei Xu
2022-05-27 2:58 ` Ying Huang
2022-05-27 14:05 ` Hesham Almatary
2022-05-27 16:25 ` Wei Xu
2022-05-27 12:25 ` [RFC PATCH v4 0/7] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-05-27 12:25 ` [RFC PATCH v4 1/7] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-06-02 6:07 ` Ying Huang
2022-06-06 2:49 ` Ying Huang
2022-06-06 3:56 ` Aneesh Kumar K V
2022-06-06 5:33 ` Ying Huang
2022-06-06 6:01 ` Aneesh Kumar K V [this message]
2022-06-06 6:27 ` Aneesh Kumar K.V
2022-06-06 7:53 ` Ying Huang
2022-06-06 8:01 ` Aneesh Kumar K V
2022-06-06 8:52 ` Ying Huang
2022-06-06 9:02 ` Aneesh Kumar K V
2022-06-08 1:24 ` Ying Huang
2022-06-08 7:16 ` Ying Huang
2022-06-08 8:24 ` Aneesh Kumar K V
2022-06-08 8:27 ` Ying Huang
2022-05-27 12:25 ` [RFC PATCH v4 2/7] mm/demotion: Expose per node memory tier to sysfs Aneesh Kumar K.V
[not found] ` <20220527151531.00002a0c@Huawei.com>
2022-06-03 8:40 ` Aneesh Kumar K V
2022-06-06 14:59 ` Jonathan Cameron
2022-06-06 16:01 ` Aneesh Kumar K V
2022-06-06 16:16 ` Jonathan Cameron
2022-06-06 16:39 ` Aneesh Kumar K V
2022-06-06 17:46 ` Aneesh Kumar K.V
2022-06-08 7:18 ` Ying Huang
2022-06-08 8:25 ` Aneesh Kumar K V
2022-06-08 8:29 ` Ying Huang
2022-05-27 12:25 ` [RFC PATCH v4 3/7] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-05-30 3:35 ` [mm/demotion] 8ebccd60c2: BUG:sleeping_function_called_from_invalid_context_at_mm/compaction.c kernel test robot
2022-05-27 12:25 ` [RFC PATCH v4 4/7] mm/demotion/dax/kmem: Set node's memory tier to MEMORY_TIER_PMEM Aneesh Kumar K.V
2022-06-01 6:29 ` Bharata B Rao
2022-06-01 13:49 ` Aneesh Kumar K V
2022-06-02 6:36 ` Bharata B Rao
2022-06-03 9:04 ` Aneesh Kumar K V
2022-06-06 10:11 ` Bharata B Rao
2022-06-06 10:16 ` Aneesh Kumar K V
2022-06-06 11:54 ` Aneesh Kumar K.V
2022-06-06 12:09 ` Bharata B Rao
2022-06-06 13:00 ` Aneesh Kumar K V
2022-05-27 12:25 ` [RFC PATCH v4 5/7] mm/demotion: Add support to associate rank with memory tier Aneesh Kumar K.V
[not found] ` <20220527154557.00002c56@Huawei.com>
2022-05-27 15:45 ` Aneesh Kumar K V
2022-05-30 12:36 ` Jonathan Cameron
2022-06-02 6:41 ` Ying Huang
2022-05-27 12:25 ` [RFC PATCH v4 6/7] mm/demotion: Add support for removing node from demotion memory tiers Aneesh Kumar K.V
2022-06-02 6:43 ` Ying Huang
2022-05-27 12:25 ` [RFC PATCH v4 7/7] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-06-02 7:35 ` Ying Huang
2022-06-03 15:09 ` Aneesh Kumar K V
2022-06-06 0:43 ` Ying Huang
2022-06-06 4:07 ` Aneesh Kumar K V
2022-06-06 5:26 ` Ying Huang
2022-06-06 6:21 ` Aneesh Kumar K.V
2022-06-06 7:42 ` Ying Huang
2022-06-06 8:02 ` Aneesh Kumar K V
2022-06-06 8:06 ` Ying Huang
2022-06-06 17:07 ` Yang Shi
2022-05-27 13:40 ` RFC: Memory Tiering Kernel Interfaces (v3) Aneesh Kumar K V
2022-05-27 16:30 ` Wei Xu
2022-05-29 4:31 ` Ying Huang
2022-05-30 12:50 ` Jonathan Cameron
2022-05-31 1:57 ` Ying Huang
2022-06-07 19:25 ` Tim Chen
2022-06-08 4:41 ` 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=eb6d7346-32a9-4fb2-61c2-a413c9f94f1c@linux.ibm.com \
--to=aneesh.kumar@linux.ibm.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--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=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;
as well as URLs for NNTP newsgroup(s).