From: Michal Hocko <mhocko@kernel.org>
To: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Roman Gushchin <guro@fb.com>,
Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>,
linux-mm@kvack.org, kernel-team@fb.com,
linux-kernel@vger.kernel.org, Rik van Riel <riel@surriel.com>
Subject: Re: [PATCH v2] mm: hugetlb: optionally allocate gigantic hugepages using cma
Date: Tue, 10 Mar 2020 18:42:19 +0100 [thread overview]
Message-ID: <20200310174219.GY8447@dhcp22.suse.cz> (raw)
In-Reply-To: <ce96c9e9-1082-df68-010e-b759d2ede69a@oracle.com>
On Tue 10-03-20 10:38:24, Mike Kravetz wrote:
> On 3/10/20 1:45 AM, Michal Hocko wrote:
> > On Mon 09-03-20 17:25:24, Roman Gushchin wrote:
> <snip>
> >> +early_param("hugetlb_cma", cmdline_parse_hugetlb_cma);
> >> +
> >> +void __init hugetlb_cma_reserve(void)
> >> +{
> >> + unsigned long totalpages = 0;
> >> + unsigned long start_pfn, end_pfn;
> >> + phys_addr_t size;
> >> + int nid, i, res;
> >> +
> >> + if (!hugetlb_cma_size && !hugetlb_cma_percent)
> >> + return;
> >> +
> >> + if (hugetlb_cma_percent) {
> >> + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
> >> + NULL)
> >> + totalpages += end_pfn - start_pfn;
> >> +
> >> + size = PAGE_SIZE * (hugetlb_cma_percent * 100 * totalpages) /
> >> + 10000UL;
> >> + } else {
> >> + size = hugetlb_cma_size;
> >> + }
> >> +
> >> + pr_info("hugetlb_cma: reserve %llu, %llu per node\n", size,
> >> + size / nr_online_nodes);
> >> +
> >> + size /= nr_online_nodes;
> >> +
> >> + for_each_node_state(nid, N_ONLINE) {
> >> + unsigned long min_pfn = 0, max_pfn = 0;
> >> +
> >> + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
> >> + if (!min_pfn)
> >> + min_pfn = start_pfn;
> >> + max_pfn = end_pfn;
> >> + }
> >
> > Do you want to compare the range to the size? But besides that, I
> > believe this really needs to be much more careful. I believe you do not
> > want to eat a considerable part of the kernel memory because the
> > resulting configuration will really struggle (yeah all the low mem/high
> > mem problems all over again).
>
> Will it struggle any worse than if the we allocated the same amount of memory
> for gigantic pages as is done today? Of course, sys admins may think reserving
> memory for CMA is better than pre-allocating and end up reserving a greater
> amount.
Yes the later is my main concern. It requires to have a deep MM
understanding to realize what the lowmem problem is. Even though who
might be familiar consider it 32b relict of the past. I have seen that
several times wrt. unproportional ZONE_MOVABLE sizing already.
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2020-03-10 17:42 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-10 0:25 [PATCH v2] mm: hugetlb: optionally allocate gigantic hugepages using cma Roman Gushchin
2020-03-10 0:30 ` Roman Gushchin
2020-03-10 8:45 ` Michal Hocko
2020-03-10 17:25 ` Roman Gushchin
2020-03-10 17:37 ` Michal Hocko
2020-03-16 1:08 ` Rik van Riel
2020-03-10 17:38 ` Mike Kravetz
2020-03-10 17:42 ` Michal Hocko [this message]
2020-03-10 9:01 ` Michal Hocko
2020-03-10 17:30 ` Roman Gushchin
2020-03-10 17:39 ` Michal Hocko
2020-03-10 17:58 ` Roman Gushchin
2020-03-10 17:27 ` Mike Kravetz
2020-03-10 18:05 ` Roman Gushchin
2020-03-10 18:22 ` Rik van Riel
2020-03-10 18:33 ` Mike Kravetz
2020-03-10 18:54 ` Andreas Schaufler
2020-03-10 18:56 ` Roman Gushchin
2020-03-10 19:00 ` Andreas Schaufler
2020-03-10 19:19 ` Roman Gushchin
2020-03-10 19:36 ` Michal Hocko
2020-03-10 19:46 ` Rik van Riel
2020-03-10 20:11 ` Mike Kravetz
2020-03-10 20:15 ` Rik van Riel
2020-03-10 20:29 ` Mike Kravetz
2020-03-10 20:38 ` Rik van Riel
2020-03-10 20:29 ` Roman Gushchin
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=20200310174219.GY8447@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mike.kravetz@oracle.com \
--cc=riel@surriel.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).