mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Qing Huang <qing.huang@oracle.com>
To: Michal Hocko <mhocko@kernel.org>, Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>,
	tariqt@mellanox.com, haakon.bugge@oracle.com,
	yanjun.zhu@oracle.com, netdev@vger.kernel.org,
	linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
	gi-oh.kim@profitbricks.com,
	"santosh.shilimkar@oracle.com" <santosh.shilimkar@oracle.com>
Subject: Re: [PATCH V4] mlx4_core: allocate ICM memory in page size chunks
Date: Thu, 31 May 2018 19:04:46 -0700	[thread overview]
Message-ID: <7d8f52e1-aa16-d20c-a9a8-35ad88c0b1ab@oracle.com> (raw)
In-Reply-To: <20180531091022.GL15278@dhcp22.suse.cz>



On 5/31/2018 2:10 AM, Michal Hocko wrote:
> On Thu 31-05-18 10:55:32, Michal Hocko wrote:
>> On Thu 31-05-18 04:35:31, Eric Dumazet wrote:
> [...]
>>> I merely copied/pasted from alloc_skb_with_frags() :/
>> I will have a look at it. Thanks!
> OK, so this is an example of an incremental development ;).
>
> __GFP_NORETRY was added by ed98df3361f0 ("net: use __GFP_NORETRY for
> high order allocations") to prevent from OOM killer. Yet this was
> not enough because fb05e7a89f50 ("net: don't wait for order-3 page
> allocation") didn't want an excessive reclaim for non-costly orders
> so it made it completely NOWAIT while it preserved __GFP_NORETRY in
> place which is now redundant. Should I send a patch?
>

Just curious, how about GFP_ATOMIC flag? Would it work in a similar 
fashion? We experimented
with it a bit in the past but it seemed to cause other issue in our 
tests. :-)

By the way, we didn't encounter any OOM killer events. It seemed that 
the mlx4_alloc_icm() triggered slowpath.
We still had about 2GB free memory while it was highly fragmented.

  #0 [ffff8801f308b380] remove_migration_pte at ffffffff811f0e0b
  #1 [ffff8801f308b3e0] rmap_walk_file at ffffffff811cb890
  #2 [ffff8801f308b440] rmap_walk at ffffffff811cbaf2
  #3 [ffff8801f308b450] remove_migration_ptes at ffffffff811f0db0
  #4 [ffff8801f308b490] __unmap_and_move at ffffffff811f2ea6
  #5 [ffff8801f308b4e0] unmap_and_move at ffffffff811f2fc5
  #6 [ffff8801f308b540] migrate_pages at ffffffff811f3219
  #7 [ffff8801f308b5c0] compact_zone at ffffffff811b707e
  #8 [ffff8801f308b650] compact_zone_order at ffffffff811b735d
  #9 [ffff8801f308b6e0] try_to_compact_pages at ffffffff811b7485
#10 [ffff8801f308b770] __alloc_pages_direct_compact at ffffffff81195f96
#11 [ffff8801f308b7b0] __alloc_pages_slowpath at ffffffff811978a1
#12 [ffff8801f308b890] __alloc_pages_nodemask at ffffffff81197ec1
#13 [ffff8801f308b970] alloc_pages_current at ffffffff811e261f
#14 [ffff8801f308b9e0] mlx4_alloc_icm at ffffffffa01f39b2 [mlx4_core]

Thanks!

  reply	other threads:[~2018-06-01  2:04 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-23 23:22 Qing Huang
2018-05-24  7:23 ` Gi-Oh Kim
2018-05-24  9:45 ` Tariq Toukan
2018-05-25 14:23 ` David Miller
2018-05-30  3:34   ` Eric Dumazet
2018-05-30  3:44     ` Eric Dumazet
2018-05-30  3:49       ` Eric Dumazet
2018-05-30 17:39         ` Qing Huang
2018-05-31  6:54         ` Michal Hocko
2018-05-31  8:35           ` Eric Dumazet
2018-05-31  8:55             ` Michal Hocko
2018-05-31  9:10               ` Michal Hocko
2018-06-01  2:04                 ` Qing Huang [this message]
2018-06-01  7:31                   ` Michal Hocko
2018-06-01 22:05                     ` Qing Huang
2018-06-04  6:27                       ` Michal Hocko
2018-06-04 12:40                         ` Vlastimil Babka
2018-06-05 18:51                           ` Qing Huang
2018-06-04 13:11                 ` Michal Hocko
2018-06-04 13:22                   ` Eric Dumazet
2018-06-05  8:32                     ` Michal Hocko
2018-05-30 17:53     ` Qing Huang

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=7d8f52e1-aa16-d20c-a9a8-35ad88c0b1ab@oracle.com \
    --to=qing.huang@oracle.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=gi-oh.kim@profitbricks.com \
    --cc=haakon.bugge@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mhocko@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=santosh.shilimkar@oracle.com \
    --cc=tariqt@mellanox.com \
    --cc=yanjun.zhu@oracle.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

all inboxes | Powered by JetHome®