On 10/08/2023 09:13, Chuyi Zhou wrote:
> This patch add a tracepoint to mark the scenario where nothing was
> chosen for OOM killer. This would allow BPF programs to catch the fact
> that the BPF OOM policy didn't work well.
>
> Suggested-by: Alan Maguire <alan.maguire@oracle.com>
> Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
> ---
> include/trace/events/oom.h | 18 ++++++++++++++++++
> mm/oom_kill.c | 1 +
> 2 files changed, 19 insertions(+)
>
> diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h
> index 26a11e4a2c36..b6ae1134229c 100644
> --- a/include/trace/events/oom.h
> +++ b/include/trace/events/oom.h
> @@ -6,6 +6,7 @@
> #define _TRACE_OOM_H
> #include <linux/tracepoint.h>
> #include <trace/events/mmflags.h>
> +#include <linux/oom.h>
>
> TRACE_EVENT(oom_score_adj_update,
>
> @@ -151,6 +152,23 @@ TRACE_EVENT(skip_task_reaping,
> TP_printk("pid=%d", __entry->pid)
> );
>
> +TRACE_EVENT(select_bad_process_end,
> +
would oom_select_bad_process_fail be a better name here?
"_end" is kind of neutral, whereas "_fail" indicates something
unexpected happened.
> + TP_PROTO(struct oom_control *oc),
> +
> + TP_ARGS(oc),
> +
> + TP_STRUCT__entry(
> + __array(char, policy_name, POLICY_NAME_LEN)
> + ),
> +
> + TP_fast_assign(
> + memcpy(__entry->policy_name, oc->policy_name, POLICY_NAME_LEN);
> + ),
> +
> + TP_printk("policy_name=%s", __entry->policy_name)
> +);
> +
> #ifdef CONFIG_COMPACTION
> TRACE_EVENT(compact_retry,
>
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 3239dcdba4d7..af40a1b750fa 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -1235,6 +1235,7 @@ bool out_of_memory(struct oom_control *oc)
> select_bad_process(oc);
> /* Found nothing?!?! */
> if (!oc->chosen) {
> + trace_select_bad_process_end(oc);
> dump_header(oc, NULL);
> pr_warn("Out of memory and no killable processes...\n");
> /*