dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org
Cc: Christian.Koenig@amd.com, Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Subject: [PATCH 2/4] oom: take per file badness into account
Date: Thu, 18 Jan 2018 11:47:50 -0500	[thread overview]
Message-ID: <1516294072-17841-3-git-send-email-andrey.grodzovsky@amd.com> (raw)
In-Reply-To: <1516294072-17841-1-git-send-email-andrey.grodzovsky@amd.com>

Try to make better decisions which process to kill based on
per file OOM badness

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 mm/oom_kill.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 29f8555..825ed52 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -49,6 +49,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
 
+#include <linux/fdtable.h>
+
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
@@ -182,6 +184,21 @@ static bool is_dump_unreclaim_slabs(void)
 }
 
 /**
+ * oom_file_badness - add per file badness
+ * @points: pointer to summed up badness points
+ * @file: tasks open file
+ * @n: file descriptor id (unused)
+ */
+static int oom_file_badness(const void *points, struct file *file, unsigned n)
+{
+	if (file->f_op->oom_file_badness)
+		*((long *)points) += file->f_op->oom_file_badness(file);
+
+	return 0;
+}
+
+
+/**
  * oom_badness - heuristic function to determine which candidate task to kill
  * @p: task struct of which task we should calculate
  * @totalpages: total present RAM allowed for page allocation
@@ -222,6 +239,12 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 */
 	points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
 		mm_pgtables_bytes(p->mm) / PAGE_SIZE;
+
+	/*
+	 * Add how much memory a task uses in opened files, e.g. device drivers.
+	 */
+	iterate_fd(p->files, 0, oom_file_badness, &points);
+
 	task_unlock(p);
 
 	/*
-- 
2.7.4

  parent reply	other threads:[~2018-01-18 16:47 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-18 16:47 [RFC] Per file OOM badness Andrey Grodzovsky
2018-01-18 16:47 ` [PATCH 1/4] fs: add OOM badness callback in file_operatrations struct Andrey Grodzovsky
2018-01-18 16:47 ` Andrey Grodzovsky [this message]
     [not found] ` <1516294072-17841-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
2018-01-18 16:47   ` [PATCH 3/4] drm/gem: adjust per file OOM badness on handling buffers Andrey Grodzovsky
2018-01-19  6:01     ` Chunming Zhou
2018-01-18 16:47   ` [PATCH 4/4] drm/amdgpu: Use drm_oom_badness for amdgpu Andrey Grodzovsky
2018-01-30  9:24     ` Daniel Vetter
     [not found]       ` <20180130092413.GD25930-dv86pmgwkMBes7Z6vYuT8azUEOm+Xw19@public.gmane.org>
2018-01-30 12:42         ` Andrey Grodzovsky
2018-01-18 17:00 ` [RFC] Per file OOM badness Michal Hocko
2018-01-18 17:13   ` Michal Hocko
2018-01-18 20:01     ` Eric Anholt
2018-01-19  8:20       ` Michal Hocko
     [not found]         ` <20180119082046.GL6584-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2018-01-19  8:39           ` Christian König
2018-01-19  9:32             ` Michel Dänzer
2018-01-19  9:58               ` Christian König
     [not found]                 ` <11153f4f-8b9a-5780-6087-bc1e85459584-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-01-19 10:02                   ` Michel Dänzer
2018-01-19 15:07                     ` Michel Dänzer
2018-01-21  6:50                       ` Eric Anholt
2018-01-19 10:40             ` Michal Hocko
2018-01-19 11:37               ` Christian König
2018-01-19 12:13                 ` Michal Hocko
2018-01-19 12:20                   ` Michal Hocko
2018-01-19 16:54                     ` Christian König
2018-01-23 11:39                       ` Michal Hocko
2018-01-19 16:48                 ` Michel Dänzer
2018-01-19  8:35       ` Christian König
2018-01-19  6:01     ` He, Roger
2018-01-19  8:25       ` Michal Hocko
2018-01-19 10:02         ` roger
2018-01-23 15:27   ` Roman Gushchin
2018-01-23 15:36     ` Michal Hocko
     [not found]       ` <20180123153631.GR1526-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2018-01-23 16:39         ` Michel Dänzer
2018-01-24  9:28           ` Michal Hocko
2018-01-24 10:27             ` Michel Dänzer
2018-01-24 11:01               ` Michal Hocko
2018-01-24 11:23                 ` Michel Dänzer
     [not found]                   ` <36b49523-792d-45f9-8617-32b6d9d77418-otUistvHUpPR7s880joybQ@public.gmane.org>
2018-01-24 11:50                     ` Michal Hocko
2018-01-24 12:11                       ` Christian König
2018-01-30  9:31                         ` Daniel Vetter
     [not found]                           ` <20180130093145.GE25930-dv86pmgwkMBes7Z6vYuT8azUEOm+Xw19@public.gmane.org>
2018-01-30  9:43                             ` Michel Dänzer
2018-01-30 10:40                               ` Christian König
2018-01-30 11:02                                 ` Michel Dänzer
2018-01-30 11:28                                   ` Christian König
2018-01-30 11:34                                     ` Michel Dänzer
2018-01-30 11:36                                       ` Nicolai Hähnle
2018-01-30 11:42                                         ` Michel Dänzer
2018-01-30 11:56                                           ` Christian König
2018-01-30 15:52                                             ` Michel Dänzer
2018-01-30 10:42                               ` Daniel Vetter
2018-01-30 10:48                                 ` Michel Dänzer
2018-01-30 11:35                                   ` Nicolai Hähnle
     [not found]                       ` <20180124115059.GC28465-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2018-01-24 14:31                         ` Michel Dänzer
2018-01-30  9:29                       ` Michel Dänzer
2018-01-30 10:28                         ` Michal Hocko
     [not found]                           ` <20180130102855.GY21609-2MMpYkNvuYDjFM9bn6wA6Q@public.gmane.org>
2018-03-26 14:36                             ` Lucas Stach
     [not found]                               ` <1522074988.1196.1.camel-bIcnvbaLZ9MEGnE8C9+IrQ@public.gmane.org>
2018-04-04  9:09                                 ` Michel Dänzer
2018-04-04  9:36                                   ` Lucas Stach
2018-04-04  9:46                                     ` Michel Dänzer
2018-01-19  5:39 ` He, Roger
2018-01-19  8:17   ` Christian König
2018-01-22 23:23 ` Andrew Morton
     [not found]   ` <20180122152315.749d88f3c91ffce4d70ac450-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2018-01-23  1:59     ` Andrey Grodzovsky

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=1516294072-17841-3-git-send-email-andrey.grodzovsky@amd.com \
    --to=andrey.grodzovsky@amd.com \
    --cc=Christian.Koenig@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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