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>,
Ilias Apalodimas <ilias.apalodimas@linaro.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 2/9] mm/page_alloc: Add a bulk page allocator
Date: Mon, 12 Apr 2021 12:19:51 +0100 [thread overview]
Message-ID: <20210412111951.GW3697@techsingularity.net> (raw)
In-Reply-To: <20210412105938.GU3697@techsingularity.net>
On Mon, Apr 12, 2021 at 11:59:38AM +0100, Mel Gorman wrote:
> > I don't understand this comment. Only alloc_flags_nofragment() sets this flag
> > and we don't use it here?
> >
>
> It's there as a reminder that there are non-obvious consequences
> to ALLOC_NOFRAGMENT that may affect the bulk allocation success
> rate. __rmqueue_fallback will only select pageblock_order pages and if that
> fails, we fall into the slow path that allocates a single page. I didn't
> deal with it because it was not obvious that it's even relevant but I bet
> in 6 months time, I'll forget that ALLOC_NOFRAGMENT may affect success
> rates without the comment. I'm waiting for a bug that can trivially trigger
> a case with a meaningful workload where the success rate is poor enough to
> affect latency before adding complexity. Ideally by then, the allocation
> paths would be unified a bit better.
>
So this needs better clarification. ALLOC_NOFRAGMENT is not a
problem at the moment but at one point during development, it was a
non-obvious potential problem. If the paths are unified, ALLOC_NOFRAGMENT
*potentially* becomes a problem depending on how it's done and it needs
careful consideration. For example, it could be part unified by moving
the alloc_flags_nofragment() call into prepare_alloc_pages because in
__alloc_pages, it always happens and it looks like an obvious partial
unification. Hence the comment "May set ALLOC_NOFRAGMENT" because I wanted
a reminder in case I "fixed" this in 6 months time and forgot the downside.
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2021-04-12 11:19 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-25 11:42 [PATCH 0/9 v6] Introduce a bulk order-0 page allocator with two in-tree users Mel Gorman
2021-03-25 11:42 ` [PATCH 1/9] mm/page_alloc: Rename alloced to allocated Mel Gorman
2021-03-25 11:59 ` Matthew Wilcox
2021-04-12 10:01 ` Vlastimil Babka
2021-03-25 11:42 ` [PATCH 2/9] mm/page_alloc: Add a bulk page allocator Mel Gorman
2021-03-25 12:05 ` Matthew Wilcox
2021-03-25 12:37 ` Mel Gorman
2021-04-12 10:21 ` Vlastimil Babka
2021-04-12 10:59 ` Mel Gorman
2021-04-12 11:19 ` Mel Gorman [this message]
2021-03-25 11:42 ` [PATCH 3/9] mm/page_alloc: Add an array-based interface to the " Mel Gorman
2021-04-12 10:36 ` Vlastimil Babka
2021-03-25 11:42 ` [PATCH 4/9] mm/page_alloc: optimize code layout for __alloc_pages_bulk Mel Gorman
2021-03-25 12:12 ` Matthew Wilcox
2021-03-25 12:40 ` Mel Gorman
2021-04-12 10:41 ` Vlastimil Babka
2021-03-25 11:42 ` [PATCH 5/9] mm/page_alloc: inline __rmqueue_pcplist Mel Gorman
2021-04-12 10:59 ` Vlastimil Babka
2021-03-25 11:42 ` [PATCH 6/9] SUNRPC: Set rq_page_end differently Mel Gorman
2021-03-25 11:42 ` [PATCH 7/9] SUNRPC: Refresh rq_pages using a bulk page allocator Mel Gorman
2021-03-25 11:42 ` [PATCH 8/9] net: page_pool: refactor dma_map into own function page_pool_dma_map Mel Gorman
2021-03-25 11:42 ` [PATCH 9/9] net: page_pool: use alloc_pages_bulk in refill code path Mel Gorman
2021-03-25 13:33 ` Alexander Lobakin
2021-03-25 12:50 ` [PATCH 0/9 v6] Introduce a bulk order-0 page allocator with two in-tree users Matthew Wilcox
2021-03-25 13:25 ` Mel Gorman
2021-03-25 14:06 ` Uladzislau Rezki
2021-03-25 14:09 ` Matthew Wilcox
2021-03-25 14:13 ` Uladzislau Rezki
2021-03-25 14:26 ` Mel Gorman
2021-03-25 14:46 ` Uladzislau Rezki
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=20210412111951.GW3697@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=ilias.apalodimas@linaro.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