From: Wei Xu <weixugc@google.com>
To: "ying.huang@intel.com" <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Greg Thelen <gthelen@google.com>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
Yang Shi <shy828301@gmail.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Jagdish Gediya <jvgediya@linux.ibm.com>,
Michal Hocko <mhocko@kernel.org>,
Tim C Chen <tim.c.chen@intel.com>,
Dave Hansen <dave.hansen@intel.com>,
Alistair Popple <apopple@nvidia.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
Feng Tang <feng.tang@intel.com>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Davidlohr Bueso <dave@stgolabs.net>,
Dan Williams <dan.j.williams@intel.com>,
David Rientjes <rientjes@google.com>,
Linux MM <linux-mm@kvack.org>,
Brice Goglin <brice.goglin@gmail.com>,
Hesham Almatary <hesham.almatary@huawei.com>
Subject: Re: RFC: Memory Tiering Kernel Interfaces (v2)
Date: Fri, 13 May 2022 00:21:16 -0700 [thread overview]
Message-ID: <CAAPL-u89gri+R-5zQRF3HLMX98TBhfdD2pH=yc6cJVX3mwmGcA@mail.gmail.com> (raw)
In-Reply-To: <a3296507be17d99e60d4c1118699aa01268dd7b8.camel@intel.com>
On Fri, May 13, 2022 at 12:04 AM ying.huang@intel.com
<ying.huang@intel.com> wrote:
>
> On Thu, 2022-05-12 at 23:36 -0700, Wei Xu wrote:
> > On Thu, May 12, 2022 at 8:25 PM ying.huang@intel.com
> > <ying.huang@intel.com> wrote:
> > >
> > > On Wed, 2022-05-11 at 23:22 -0700, Wei Xu wrote:
> > > >
> > > > Memory Allocation for Demotion
> > > > ==============================
> > > >
> > > > To allocate a new page as the demotion target for a page, the kernel
> > > > calls the allocation function (__alloc_pages_nodemask) with the
> > > > source page node as the preferred node and the union of all lower
> > > > tier nodes as the allowed nodemask. The actual target node selection
> > > > then follows the allocation fallback order that the kernel has
> > > > already defined.
> > > >
> > > > The pseudo code looks like:
> > > >
> > > > targets = NODE_MASK_NONE;
> > > > src_nid = page_to_nid(page);
> > > > src_tier = node_tier_map[src_nid];
> > > > for (i = src_tier + 1; i < MAX_MEMORY_TIERS; i++)
> > > > nodes_or(targets, targets, memory_tiers[i]);
> > > > new_page = __alloc_pages_nodemask(gfp, order, src_nid, targets);
> > > >
> > > > The memopolicy of cpuset, vma and owner task of the source page can
> > > > be set to refine the demotion target nodemask, e.g. to prevent
> > > > demotion or select a particular allowed node as the demotion target.
> > >
> > > Consider a system with 3 tiers, if we want to demote some pages from
> > > tier 0, the desired behavior is,
> > >
> > > - Allocate pages from tier 1
> > > - If there's no enough free pages in tier 1, wakeup kswapd of tier 1 so
> > > demote some pages from tier 1 to tier 2
> > > - If there's still no enough free pages in tier 1, allocate pages from
> > > tier 2.
> > >
> > > In this way, tier 0 will have the hottest pages, while tier 1 will have
> > > the coldest pages.
> >
> > When we are already in the allocation path for the demotion of a page
> > from tier 0, I think we'd better not block this allocation to wait for
> > kswapd to demote pages from tier 1 to tier 2. Instead, we should
> > directly allocate from tier 2. Meanwhile, this demotion can wakeup
> > kswapd to demote from tier 1 to tier 2 in the background.
>
> Yes. That's what I want too. My original words may be misleading.
>
> > > With your proposed method, the demoting from tier 0 behavior is,
> > >
> > > - Allocate pages from tier 1
> > > - If there's no enough free pages in tier 1, allocate pages in tier 2
> > >
> > > The kswapd of tier 1 will not be waken up until there's no enough free
> > > pages in tier 2. In quite long time, there's no much hot/cold
> > > differentiation between tier 1 and tier 2.
> >
> > This is true with the current allocation code. But I think we can make
> > some changes for demotion allocations. For example, we can add a
> > GFP_DEMOTE flag and update the allocation function to wake up kswapd
> > when this flag is set and we need to fall back to another node.
> >
> > > This isn't hard to be fixed, just call __alloc_pages_nodemask() for each
> > > tier one by one considering page allocation fallback order.
> >
> > That would have worked, except that there is an example earlier, in
> > which it is actually preferred for some nodes to demote to their tier
> > + 2, not tier +1.
> >
> > More specifically, the example is:
> >
> > 20
> > Node 0 (DRAM) -- Node 1 (DRAM)
> > | | | |
> > | | 30 120 | |
> > | v v | 100
> > 100 | Node 2 (PMEM) |
> > | | |
> > | | 100 |
> > \ v v
> > -> Node 3 (Large Mem)
> >
> > Node distances:
> > node 0 1 2 3
> > 0 10 20 30 100
> > 1 20 10 120 100
> > 2 30 120 10 100
> > 3 100 100 100 10
> >
> > 3 memory tiers are defined:
> > tier 0: 0-1
> > tier 1: 2
> > tier 2: 3
> >
> > The demotion fallback order is:
> > node 0: 2, 3
> > node 1: 3, 2
> > node 2: 3
> > node 3: empty
> >
> > Note that even though node 3 is in tier 2 and node 2 is in tier 1,
> > node 1 (tier 0) still prefers node 3 as its first demotion target, not
> > node 2.
>
> Yes. I understand that we need to support this use case. We can use
> the tier order in allocation fallback list instead of from small to
> large. That is, for node 1, the tier order for demotion is tier 2, tier
> 1.
That could work, too, though I feel it might be simpler and more
efficient (no repeated calls to __alloc_pages for the same allocation)
to modify __alloc_pages() itself.
Anyway, we can discuss more on this when it comes to the
implementation of this demotion allocation function. I believe this
should not affect the general memory tiering interfaces proposed here.
> Best Regards,
> Huang, Ying
>
>
>
prev parent reply other threads:[~2022-05-13 7:21 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-12 6:22 RFC: Memory Tiering Kernel Interfaces (v2) Wei Xu
2022-05-12 7:03 ` ying.huang
2022-05-12 7:12 ` Aneesh Kumar K V
2022-05-12 7:18 ` ying.huang
2022-05-12 7:22 ` Wei Xu
2022-05-12 7:36 ` Aneesh Kumar K.V
2022-05-12 8:15 ` Wei Xu
2022-05-12 8:37 ` ying.huang
2022-05-13 2:52 ` ying.huang
2022-05-13 7:00 ` Wei Xu
2022-05-16 1:57 ` ying.huang
2022-05-12 21:12 ` Tim Chen
2022-05-12 21:31 ` Wei Xu
2022-05-12 15:00 ` Jonathan Cameron
2022-05-18 7:09 ` Wei Xu
2022-05-18 12:00 ` Jonathan Cameron
2022-05-24 7:36 ` Wei Xu
2022-05-24 13:26 ` Aneesh Kumar K.V
2022-05-25 5:27 ` Wei Xu
2022-05-25 7:47 ` Alistair Popple
2022-05-25 11:48 ` Jonathan Cameron
2022-05-25 15:32 ` Wei Xu
2022-05-20 3:06 ` Ying Huang
2022-05-24 7:04 ` Wei Xu
2022-05-24 8:24 ` Ying Huang
2022-05-25 5:32 ` Wei Xu
2022-05-25 9:03 ` Ying Huang
2022-05-25 10:01 ` Aneesh Kumar K V
2022-05-25 11:36 ` Mika Penttilä
2022-05-25 15:33 ` Wei Xu
2022-05-25 17:27 ` Wei Xu
2022-05-26 9:32 ` Jonathan Cameron
2022-05-26 20:30 ` Wei Xu
2022-05-27 9:26 ` Aneesh Kumar K V
2022-05-25 15:36 ` Wei Xu
2022-05-26 1:09 ` Ying Huang
2022-05-26 3:53 ` Wei Xu
2022-05-26 6:54 ` Ying Huang
2022-05-26 7:08 ` Wei Xu
2022-05-26 7:39 ` Ying Huang
2022-05-26 20:55 ` Wei Xu
2022-05-27 9:10 ` Jonathan Cameron
2022-05-30 6:54 ` Ying Huang
2022-05-13 3:25 ` ying.huang
2022-05-13 6:36 ` Wei Xu
2022-05-13 7:04 ` ying.huang
2022-05-13 7:21 ` Wei Xu [this message]
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='CAAPL-u89gri+R-5zQRF3HLMX98TBhfdD2pH=yc6cJVX3mwmGcA@mail.gmail.com' \
--to=weixugc@google.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=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).