[Devel] [PATCH RHEL7 COMMIT] oom: pass points and overdraft to oom_kill_process

Konstantin Khorenko khorenko at virtuozzo.com
Thu Jan 28 08:21:30 PST 2016


The commit is pushed to "branch-rh7-3.10.0-327.3.1-vz7.10.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.3.1.vz7.10.7
------>
commit 67f0a5a4738e715a9ca61a989d4739e80611a6a8
Author: Vladimir Davydov <vdavydov at virtuozzo.com>
Date:   Thu Jan 28 20:21:30 2016 +0400

    oom: pass points and overdraft to oom_kill_process
    
    Rebase to RHEL 7.2 based kernel:
    https://jira.sw.ru/browse/PSBM-42320
    ===
    From: Vladimir Davydov <vdavydov at parallels.com>
    
    Patchset description: oom enhancements - part 2
    
     - Patches 1-2 prepare memcg for upcoming changes in oom design.
     - Patch 3 reworks oom locking design so that the executioner waits for
       victim to exit. This is necessary to increase oom kill rate, which is
       essential for berserker mode.
     - Patch 4 drops unused OOM_SCAN_ABORT
     - Patch 5 introduces oom timeout.
       https://jira.sw.ru/browse/PSBM-38581
     - Patch 6 makes oom fairer when it comes to selecting a victim among
       different containers.
       https://jira.sw.ru/browse/PSBM-37915
     - Patch 7 prepares oom for introducing berserker mode
     - Patch 8 resurrects oom berserker mode, which is supposed to cope with
       actively forking processes.
       https://jira.sw.ru/browse/PSBM-17930
    
    https://jira.sw.ru/browse/PSBM-26973
    
    Changes in v3:
     - rework oom_trylock (patch 3)
     - select exiting process instead of aborting oom scan so as not to keep
       busy-waiting for an exiting process to exit (patches 3, 4)
     - cleanup oom timeout handling + fix stuck process trace dumped
       multiple times on timeout (patch 5)
     - set max_overdraft to ULONG_MAX on selected processes (patch 6)
     - rework oom berserker process selection logic (patches 7, 8)
    
    Changes in v2:
     - s/time_after/time_after_eq to avoid BUG_ON in oom_trylock (patch 4)
     - propagate victim to the context that initiated oom in oom_unlock
       (patch 6)
     - always set oom_end on releasing oom context (patch 6)
    
    Vladimir Davydov (8):
      memcg: add mem_cgroup_get/put helpers
      memcg: add lock for protecting memcg->oom_notify list
      oom: rework locking design
      oom: introduce oom timeout
      oom: drop OOM_SCAN_ABORT
      oom: rework logic behind memory.oom_guarantee
      oom: pass points and overdraft to oom_kill_process
      oom: resurrect berserker mode
    
    Reviewed-by: Kirill Tkhai <ktkhai at odin.com>
    
    =========================================
    This patch description:
    
    This is required by oom berserker mode, which will be introduced later
    in this series.
    
    Signed-off-by: Vladimir Davydov <vdavydov at parallels.com>
---
 include/linux/oom.h |  3 ++-
 mm/memcontrol.c     |  6 +++---
 mm/oom_kill.c       | 26 ++++++++++++++++----------
 3 files changed, 21 insertions(+), 14 deletions(-)

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 9117d1d..6ea83b2 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -85,7 +85,8 @@ static inline bool oom_worse(unsigned long points, unsigned long overdraft,
 }
 
 extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-			     unsigned int points, unsigned long totalpages,
+			     unsigned long points, unsigned long overdraft,
+			     unsigned long totalpages,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
 			     const char *message);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 45ed5aa..ddd162a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1999,7 +1999,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long chosen_points = 0;
 	unsigned long totalpages;
 	unsigned long overdraft;
-	unsigned int points = 0;
+	unsigned long points = 0;
 	struct task_struct *chosen = NULL;
 
 	/*
@@ -2051,8 +2051,8 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	if (!chosen)
 		return;
-	points = chosen_points * 1000 / totalpages;
-	oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
+	oom_kill_process(chosen, gfp_mask, order, chosen_points, max_overdraft,
+			 totalpages, memcg,
 			 NULL, "Memory cgroup out of memory");
 }
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bea7a2a..a56c9a9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -353,7 +353,8 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
  *
  * (not docbooked, we don't want this one cluttering up the manual)
  */
-static struct task_struct *select_bad_process(unsigned int *ppoints,
+static struct task_struct *select_bad_process(unsigned long *ppoints,
+		unsigned long *poverdraft,
 		unsigned long totalpages, const nodemask_t *nodemask,
 		bool force_kill)
 {
@@ -389,7 +390,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		get_task_struct(chosen);
 	rcu_read_unlock();
 
-	*ppoints = chosen_points * 1000 / totalpages;
+	*ppoints = chosen_points;
+	*poverdraft = max_overdraft;
 	return chosen;
 }
 
@@ -694,7 +696,8 @@ void oom_unlock(struct mem_cgroup *memcg)
  * returning.
  */
 void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
-		      unsigned int points, unsigned long totalpages,
+		      unsigned long points, unsigned long overdraft,
+		      unsigned long totalpages,
 		      struct mem_cgroup *memcg, nodemask_t *nodemask,
 		      const char *message)
 {
@@ -723,8 +726,8 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_header(p, gfp_mask, order, memcg, nodemask);
 
 	task_lock(p);
-	pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n",
-		message, task_pid_nr(p), p->comm, points);
+	pr_err("%s: Kill process %d (%s) score %lu or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points * 1000 / totalpages);
 	task_unlock(p);
 
 	/*
@@ -864,7 +867,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
-	unsigned int uninitialized_var(points);
+	unsigned long uninitialized_var(points);
+	unsigned long uninitialized_var(overdraft);
 	enum oom_constraint constraint = CONSTRAINT_NONE;
 
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
@@ -899,19 +903,21 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	    !oom_unkillable_task(current, NULL, nodemask) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
-		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
-				 nodemask,
+		oom_kill_process(current, gfp_mask, order, 0, 0, totalpages,
+				 NULL, nodemask,
 				 "Out of memory (oom_kill_allocating_task)");
 		return;
 	}
 
-	p = select_bad_process(&points, totalpages, mpol_mask, force_kill);
+	p = select_bad_process(&points, &overdraft, totalpages, mpol_mask,
+			       force_kill);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
 		panic("Out of memory and no killable processes...\n");
 	} else
-		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
+		oom_kill_process(p, gfp_mask, order, points, overdraft,
+				 totalpages, NULL,
 				 nodemask, "Out of memory");
 }
 


More information about the Devel mailing list