On Sat, 12 Jun 2021, Aaron Tomlin wrote:
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index eefd3f5fde46..094b7b61d66f 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -160,6 +160,27 @@ static inline bool is_sysrq_oom(struct oom_control *oc)
> return oc->order == -1;
> }
>
> +/**
> + * is_task_eligible_oom - determine if and why a task cannot be OOM killed
> + * @tsk: task to check
> + *
> + * Needs to be called with task_lock().
> + */
> +static const char * is_task_oom_eligible(struct task_struct *p)
You should be able to just return a char.
> +{
> + long adj;
> +
> + adj = (long)p->signal->oom_score_adj;
> + if (adj == OOM_SCORE_ADJ_MIN)
> + return "S";
The value is already printed in the task dump, this doesn't look to add
any information.
> + else if (test_bit(MMF_OOM_SKIP, &p->mm->flags)
> + return "R";
We should be doing the task dump only when we're killing a victim (unless
we're panicking), so something else has been chosen. Since we would have
oom killed a process with MMF_OOM_SKIP already, can we simply choose to
not print a line for this process?
> + else if (in_vfork(p))
> + return "V";
Is this a transition state that we can simply disregard from the output as
well unless/until it becomes eligible?
> + else
> + return "";
> +}
> +
> /* return true if the task is not adequate as candidate victim task. */
> static bool oom_unkillable_task(struct task_struct *p)
> {
> @@ -401,12 +422,13 @@ static int dump_task(struct task_struct *p, void *arg)
> return 0;
> }
>
> - pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
> + pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %13s %s\n",
13 characters for one char output?
> task->pid, from_kuid(&init_user_ns, task_uid(task)),
> task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
> mm_pgtables_bytes(task->mm),
> get_mm_counter(task->mm, MM_SWAPENTS),
> - task->signal->oom_score_adj, task->comm);
> + task->signal->oom_score_adj, is_task_oom_eligible(task),
> + task->comm);
> task_unlock(task);
>
> return 0;
> @@ -420,12 +442,13 @@ static int dump_task(struct task_struct *p, void *arg)
> * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
> * are not shown.
> * State information includes task's pid, uid, tgid, vm size, rss,
> - * pgtables_bytes, swapents, oom_score_adj value, and name.
> + * pgtables_bytes, swapents, oom_score_adj value, oom eligibility status
> + * and name.
> */
> static void dump_tasks(struct oom_control *oc)
> {
> pr_info("Tasks state (memory values in pages):\n");
> - pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n");
> + pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj oom eligible? name\n");
Field names are single words.
>
> if (is_memcg_oom(oc))
> mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
