From: Mel Gorman <mgorman@techsingularity.net>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Chuck Lever <chuck.lever@oracle.com>,
Jesper Dangaard Brouer <brouer@redhat.com>,
Christoph Hellwig <hch@infradead.org>,
Alexander Duyck <alexander.duyck@gmail.com>,
Matthew Wilcox <willy@infradead.org>,
LKML <linux-kernel@vger.kernel.org>,
Linux-Net <netdev@vger.kernel.org>, Linux-MM <linux-mm@kvack.org>,
Linux-NFS <linux-nfs@vger.kernel.org>
Subject: Re: [PATCH 3/7] mm/page_alloc: Add a bulk page allocator
Date: Mon, 22 Mar 2021 08:30:39 +0000 [thread overview]
Message-ID: <20210322083039.GD3697@techsingularity.net> (raw)
In-Reply-To: <7c520bbb-efd7-7cad-95df-610000832a67@suse.cz>
On Fri, Mar 19, 2021 at 07:18:32PM +0100, Vlastimil Babka wrote:
> On 3/12/21 4:43 PM, Mel Gorman wrote:
> > This patch adds a new page allocator interface via alloc_pages_bulk,
> > and __alloc_pages_bulk_nodemask. A caller requests a number of pages
> > to be allocated and added to a list. They can be freed in bulk using
> > free_pages_bulk().
> >
> > The API is not guaranteed to return the requested number of pages and
> > may fail if the preferred allocation zone has limited free memory, the
> > cpuset changes during the allocation or page debugging decides to fail
> > an allocation. It's up to the caller to request more pages in batch
> > if necessary.
> >
> > Note that this implementation is not very efficient and could be improved
> > but it would require refactoring. The intent is to make it available early
> > to determine what semantics are required by different callers. Once the
> > full semantics are nailed down, it can be refactored.
> >
> > Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
>
> Although maybe premature, if it changes significantly due to the users'
> performance feedback, let's see :)
>
Indeed. The next version will have no users so that Jesper and Chuck
can check if an array-based or LRU based version is better. There were
also bugs such as broken accounting of stats that had to be fixed which
increases overhead.
> Some nits below:
>
> ...
>
> > @@ -4963,6 +4978,107 @@ static inline bool prepare_alloc_pages(gfp_t gfp, unsigned int order,
> > return true;
> > }
> >
> > +/*
> > + * This is a batched version of the page allocator that attempts to
> > + * allocate nr_pages quickly from the preferred zone and add them to list.
> > + *
> > + * Returns the number of pages allocated.
> > + */
> > +int __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
> > + nodemask_t *nodemask, int nr_pages,
> > + struct list_head *alloc_list)
> > +{
> > + struct page *page;
> > + unsigned long flags;
> > + struct zone *zone;
> > + struct zoneref *z;
> > + struct per_cpu_pages *pcp;
> > + struct list_head *pcp_list;
> > + struct alloc_context ac;
> > + gfp_t alloc_gfp;
> > + unsigned int alloc_flags;
> > + int allocated = 0;
> > +
> > + if (WARN_ON_ONCE(nr_pages <= 0))
> > + return 0;
> > +
> > + if (nr_pages == 1)
> > + goto failed;
> > +
> > + /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
> > + if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac,
> > + &alloc_gfp, &alloc_flags))
>
> Unusual identation here.
>
Fixed
> > + return 0;
> > + gfp = alloc_gfp;
> > +
> > + /* Find an allowed local zone that meets the high watermark. */
> > + for_each_zone_zonelist_nodemask(zone, z, ac.zonelist, ac.highest_zoneidx, ac.nodemask) {
> > + unsigned long mark;
> > +
> > + if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) &&
> > + !__cpuset_zone_allowed(zone, gfp)) {
> > + continue;
> > + }
> > +
> > + if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone &&
> > + zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) {
> > + goto failed;
> > + }
> > +
> > + mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
> > + if (zone_watermark_fast(zone, 0, mark,
> > + zonelist_zone_idx(ac.preferred_zoneref),
> > + alloc_flags, gfp)) {
> > + break;
> > + }
> > + }
> > + if (!zone)
> > + return 0;
>
> Why not also "goto failed;" here?
Good question. When first written, it was because the zone search for the
normal allocator was almost certainly going to fail to find a zone and
it was expected that callers would prefer to fail fast over blocking.
Now we know that sunrpc can sleep on a failing allocation and it would
be better to enter the single page allocator and reclaim pages instead of
"sleep and hope for the best".
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2021-03-22 8:30 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-12 15:43 [PATCH 0/7 v4] Introduce a bulk order-0 page allocator with two in-tree users Mel Gorman
2021-03-12 15:43 ` [PATCH 1/7] mm/page_alloc: Move gfp_allowed_mask enforcement to prepare_alloc_pages Mel Gorman
2021-03-19 16:11 ` Vlastimil Babka
2021-03-19 17:49 ` Mel Gorman
2021-03-12 15:43 ` [PATCH 2/7] mm/page_alloc: Rename alloced to allocated Mel Gorman
2021-03-19 16:22 ` Vlastimil Babka
2021-03-12 15:43 ` [PATCH 3/7] mm/page_alloc: Add a bulk page allocator Mel Gorman
2021-03-19 18:18 ` Vlastimil Babka
2021-03-22 8:30 ` Mel Gorman [this message]
2021-03-12 15:43 ` [PATCH 4/7] SUNRPC: Set rq_page_end differently Mel Gorman
2021-03-12 15:43 ` [PATCH 5/7] SUNRPC: Refresh rq_pages using a bulk page allocator Mel Gorman
2021-03-12 18:44 ` Alexander Duyck
2021-03-12 19:22 ` Chuck Lever III
2021-03-13 12:59 ` Mel Gorman
2021-03-12 15:43 ` [PATCH 6/7] net: page_pool: refactor dma_map into own function page_pool_dma_map Mel Gorman
2021-03-12 15:43 ` [PATCH 7/7] net: page_pool: use alloc_pages_bulk in refill code path Mel Gorman
2021-03-12 19:44 ` Alexander Duyck
2021-03-12 20:05 ` Ilias Apalodimas
2021-03-15 13:39 ` Jesper Dangaard Brouer
2021-03-13 13:30 ` Mel Gorman
2021-03-17 16:31 ` [PATCH 0/7 v4] Introduce a bulk order-0 page allocator with two in-tree users Alexander Lobakin
2021-03-17 16:38 ` Jesper Dangaard Brouer
2021-03-17 16:52 ` Alexander Lobakin
2021-03-17 17:19 ` Jesper Dangaard Brouer
2021-03-17 22:25 ` Alexander Lobakin
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=20210322083039.GD3697@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=akpm@linux-foundation.org \
--cc=alexander.duyck@gmail.com \
--cc=brouer@redhat.com \
--cc=chuck.lever@oracle.com \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
/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).