Linux-Devicetree Archive on lore.kernel.org
 help / color / Atom feed
From: Michal Hocko <mhocko@suse.com>
To: Minchan Kim <minchan@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	hyesoo.yu@samsung.com, david@redhat.com, surenb@google.com,
	pullip.cho@samsung.com, joaodias@google.com, hridya@google.com,
	john.stultz@linaro.org, sumit.semwal@linaro.org,
	linux-media@vger.kernel.org, devicetree@vger.kernel.org,
	hch@infradead.org, robh+dt@kernel.org,
	linaro-mm-sig@lists.linaro.org
Subject: Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range
Date: Wed, 27 Jan 2021 09:14:08 +0100
Message-ID: <20210127081408.GA827@dhcp22.suse.cz> (raw)
In-Reply-To: <YBBpGji3BJYHidHs@google.com>

On Tue 26-01-21 11:10:18, Minchan Kim wrote:
> On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote:
> > On Mon 25-01-21 11:33:36, Minchan Kim wrote:
> > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote:
> > > > On Thu 21-01-21 09:55:00, Minchan Kim wrote:
> > > > > Contiguous memory allocation can be stalled due to waiting
> > > > > on page writeback and/or page lock which causes unpredictable
> > > > > delay. It's a unavoidable cost for the requestor to get *big*
> > > > > contiguous memory but it's expensive for *small* contiguous
> > > > > memory(e.g., order-4) because caller could retry the request
> > > > > in different range where would have easy migratable pages
> > > > > without stalling.
> > > > > 
> > > > > This patch introduce __GFP_NORETRY as compaction gfp_mask in
> > > > > alloc_contig_range so it will fail fast without blocking
> > > > > when it encounters pages needed waiting.
> > > > 
> > > > I am not against controling how hard this allocator tries with gfp mask
> > > > but this changelog is rather void on any data and any user.
> > > > 
> > > > It is also rather dubious to have retries when then caller says to not
> > > > retry.
> > > 
> > > Since max_tries is 1 with ++tries, it shouldn't retry.
> > 
> > OK, I have missed that. This is a tricky code. ASYNC mode should be
> > completely orthogonal to the retries count. Those are different things.
> > Page allocator does an explicit bail out based on __GFP_NORETRY. You
> > should be doing the same.
> 
> A concern with __GFP_NOWAIT is regardless of flags passed to cma_alloc,
> internal implementation of alloc_contig_range inside will use blockable
> operation. See __alloc_contig_migrate_range.

Yes it is now. But nothing should prevent from making it non blockable.

> If we go with __GFP_NOWAIT, we should propagate the gfp_mask inside of
> __alloc_contig_migrate_range to make cma_alloc consistent with alloc_pages.

Absolutely. You should be doing that anyway. As I've said above you
shouldn't rely on side effects like ASYNC mode.

> (IIUC, that's what you want - make gfp_mask consistent between cma_alloc
> and alloc_pages) but I am worry about the direction will make complicate
> situation since cma invovles migration context as well as target page
> allocation context. Sometime, the single gfp flag could be trouble
> to express both contexts all at once. 

I am not sure I see your concern.

> > > > Also why didn't you consider GFP_NOWAIT semantic for non blocking mode?
> > > 
> > > GFP_NOWAIT seems to be low(specific) flags rather than the one I want to
> > > express. Even though I said only page writeback/lock in the description,
> > > the goal is to avoid costly operations we might find later so such
> > > "failfast", I thought GFP_NORETRY would be good fit.
> > 
> > I suspect you are too focused on implementation details here. Think
> > about the indended semantic. Callers of this functionality will not
> > think about those (I hope because if they rely on these details then the
> > whole thing will become unmaintainable because any change would require
> > an audit of all existing users). All you should be caring about is to
> > control how expensive the call can be. GFP_NOWAIT is not really low
> > level from that POV. It gives you a very lightweight non-sleeping
> > attempt to allocate. GFP_NORETRY will give you potentially sleeping but
> > an opportunistic-easy-to-fail attempt. And so on. See how that is
> > absolutely free of any page writeback or any specific locking.
> 
> With above reason I mentioned, I wanted to express __GFP_NORETRY as 
> "opportunistic-easy-to-fail attempt" to support cma_alloc as "failfast"
> for migration context.

Yes that is fine. And please note that I do not push for NOWAIT
semantic. If there is no user for that now then fine.
-- 
Michal Hocko
SUSE Labs

  reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-21 17:54 [PATCH v4 0/4] Chunk Heap Support on DMA-HEAP Minchan Kim
2021-01-21 17:54 ` [PATCH v4 1/4] mm: cma: introduce gfp flag in cma_alloc instead of no_warn Minchan Kim
2021-01-21 18:46   ` David Hildenbrand
2021-01-21 18:50   ` Minchan Kim
2021-01-25 13:07   ` Michal Hocko
2021-01-25 19:42     ` Minchan Kim
2021-01-26  7:38       ` Michal Hocko
2021-01-26 19:12         ` Minchan Kim
2021-01-27 20:21           ` Minchan Kim
2021-01-21 17:55 ` [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range Minchan Kim
2021-01-25 13:12   ` Michal Hocko
2021-01-25 13:13     ` Michal Hocko
2021-01-25 19:33     ` Minchan Kim
2021-01-26  7:44       ` Michal Hocko
2021-01-26 19:10         ` Minchan Kim
2021-01-27  8:14           ` Michal Hocko [this message]
2021-01-27 20:42         ` Minchan Kim
2021-01-28  7:53           ` Michal Hocko
2021-01-28 16:56             ` Minchan Kim
2021-01-21 17:55 ` [PATCH v4 3/4] dt-bindings: reserved-memory: Make DMA-BUF CMA heap DT-configurable Minchan Kim
2021-01-26  7:07   ` John Stultz
2021-01-27 20:25     ` Hridya Valsaraju
2021-02-05 22:55   ` Rob Herring
2021-01-21 17:55 ` [PATCH v4 4/4] dma-buf: heaps: add chunk heap to dmabuf heaps Minchan Kim
2021-01-26  7:07   ` Christoph Hellwig
2021-01-26 19:27     ` Minchan Kim
2021-01-26  7:32   ` John Stultz
2021-01-26 19:24     ` Minchan Kim
2021-01-26  7:46   ` Michal Hocko
2021-01-26 19:25     ` Minchan Kim
2021-01-27  8:09       ` Michal Hocko

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=20210127081408.GA827@dhcp22.suse.cz \
    --to=mhocko@suse.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=devicetree@vger.kernel.org \
    --cc=hch@infradead.org \
    --cc=hridya@google.com \
    --cc=hyesoo.yu@samsung.com \
    --cc=joaodias@google.com \
    --cc=john.stultz@linaro.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=pullip.cho@samsung.com \
    --cc=robh+dt@kernel.org \
    --cc=sumit.semwal@linaro.org \
    --cc=surenb@google.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

Linux-Devicetree Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-devicetree/0 linux-devicetree/git/0.git
	git clone --mirror https://lore.kernel.org/linux-devicetree/1 linux-devicetree/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-devicetree linux-devicetree/ https://lore.kernel.org/linux-devicetree \
		devicetree@vger.kernel.org
	public-inbox-index linux-devicetree

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-devicetree


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git