Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Ralf-Peter Rohbeck <Ralf-Peter.Rohbeck@quantum.com>,
	Michal Hocko <mhocko@suse.cz>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>
Subject: Re: OOM killer changes
Date: Fri, 19 Aug 2016 08:27:34 +0200
Message-ID: <f7a9ea9d-bb88-bfd6-e340-3a933559305a@suse.cz> (raw)
In-Reply-To: <ea18e6b3-9d47-b154-5e12-face50578302@Quantum.com>

On 08/19/2016 04:42 AM, Ralf-Peter Rohbeck wrote:
> On 18.08.2016 13:12, Vlastimil Babka wrote:
>> On 18.8.2016 22:01, Ralf-Peter Rohbeck wrote:
>>> On 17.08.2016 23:57, Vlastimil Babka wrote:
>>>> Vlastimil
>>> Yes, that change was in my test with linux-next-20160817. Here's the diff:
>>>
>>> diff --git a/mm/compaction.c b/mm/compaction.c
>>> index f94ae67..60a9ca2 100644
>>> --- a/mm/compaction.c
>>> +++ b/mm/compaction.c
>>> @@ -1083,8 +1083,10 @@ static void isolate_freepages(struct
>>> compact_control *cc)
>>>                           continue;
>>>
>>>                   /* Check the block is suitable for migration */
>>> +/*
>>>                   if (!suitable_migration_target(page))
>>>                           continue;
>>> +*/
>> OK, could you please also try if uncommenting the above still works without OOM?
>> Or just plain linux-next-20160817, I guess we don't need the printk's to test
>> this difference.
>>
>> Thanks a lot!
>> Vlastimil
>>
> With the two lines back in I had OOMs again. See the attached logs.

Thanks for the confirmation.

We however shouldn't disable the heuristic completely, so here's a compromise
patch hooking into the new compaction priorities. Can you please test on top of
linux-next?

-----8<-----

  reply index

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <d8f3adcc-3607-1ef6-9ec5-82b2e125eef2@quantum.com>
2016-08-01  6:16 ` Michal Hocko
     [not found]   ` <b1a39756-a0b5-1900-6575-d6e1f502cb26@Quantum.com>
     [not found]     ` <20160801182358.GB31957@dhcp22.suse.cz>
     [not found]       ` <30dbabc4-585c-55a5-9f3a-4e243c28356a@Quantum.com>
2016-08-01 19:26         ` Michal Hocko
2016-08-01 19:35           ` Ralf-Peter Rohbeck
2016-08-01 19:43             ` Michal Hocko
2016-08-01 19:52               ` Ralf-Peter Rohbeck
2016-08-01 20:09                 ` Michal Hocko
2016-08-01 20:16                   ` Ralf-Peter Rohbeck
2016-08-01 20:26                     ` Michal Hocko
2016-08-01 21:14                       ` Ralf-Peter Rohbeck
2016-08-01 21:27                         ` Ralf-Peter Rohbeck
2016-08-02  7:10                           ` Michal Hocko
2016-08-02 19:25                             ` Ralf-Peter Rohbeck
2016-08-15  4:48                               ` Ralf-Peter Rohbeck
2016-08-15  9:16                                 ` Vlastimil Babka
2016-08-15 15:01                                   ` Michal Hocko
2016-08-15 18:42                                     ` Ralf-Peter Rohbeck
2016-08-16  7:32                                       ` Michal Hocko
2016-08-16  7:43                                         ` Michal Hocko
2016-08-17  9:14                                           ` Ralf-Peter Rohbeck
2016-08-17  9:23                                             ` Vlastimil Babka
2016-08-17  9:28                                               ` Ralf-Peter Rohbeck
2016-08-17  9:33                                                 ` Michal Hocko
2016-08-17 23:37                                                   ` Ralf-Peter Rohbeck
2016-08-18  6:57                                                     ` Vlastimil Babka
2016-08-18 20:01                                                       ` Ralf-Peter Rohbeck
2016-08-18 20:12                                                         ` Vlastimil Babka
2016-08-19  2:42                                                           ` Ralf-Peter Rohbeck
2016-08-19  6:27                                                             ` Vlastimil Babka [this message]
2016-08-19  7:33                                                               ` Michal Hocko
2016-08-19  7:47                                                                 ` Vlastimil Babka
2016-08-19  8:26                                                                   ` Michal Hocko
2016-08-24 18:13                                                                     ` Ralf-Peter Rohbeck
2016-08-25  7:22                                                                       ` Michal Hocko
2016-08-25 20:35                                                                         ` Ralf-Peter Rohbeck
2016-08-26  8:35                                                                           ` Michal Hocko
2016-09-06 11:09                                                                             ` Vlastimil Babka
2016-08-23  5:02                                                               ` Joonsoo Kim
2016-08-23  7:45                                                                 ` Michal Hocko
2016-08-17  0:26                                         ` Ralf-Peter Rohbeck
2016-08-17  7:43                                           ` Vlastimil Babka
2016-08-16  3:12                                   ` Joonsoo Kim
2016-08-16  7:44                                     ` Vlastimil Babka
2016-08-17  4:48                                     ` Ralf-Peter Rohbeck
2016-08-17  7:56                                       ` Vlastimil Babka
2016-08-17  8:16                                         ` Joonsoo Kim
2016-08-17  9:21                                           ` Ralf-Peter Rohbeck
2016-08-17  9:11                                         ` Ralf-Peter Rohbeck
2016-08-17  9:20                                           ` Vlastimil Babka
2016-08-02  7:11           ` Vlastimil Babka
2016-08-02  9:02           ` 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=f7a9ea9d-bb88-bfd6-e340-3a933559305a@suse.cz \
    --to=vbabka@suse.cz \
    --cc=Ralf-Peter.Rohbeck@quantum.com \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.cz \
    /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-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.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-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


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