On Tue, 2024-01-02 at 21:12 +0800, Gang Li wrote:
> When a group of tasks that access different nodes are scheduled on the
> same node, they may encounter bandwidth bottlenecks and access latency.
>
> Thus, numa_aware flag is introduced here, allowing tasks to be
> distributed across different nodes to fully utilize the advantage of
> multi-node systems.
>
> Signed-off-by: Gang Li <gang.li@xxxxxxxxx>
> ---
> include/linux/padata.h | 3 +++
> kernel/padata.c | 8 ++++++--
> mm/mm_init.c | 1 +
> 3 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/padata.h b/include/linux/padata.h
> index 495b16b6b4d72..f79ccd50e7f40 100644
> --- a/include/linux/padata.h
> +++ b/include/linux/padata.h
> @@ -137,6 +137,8 @@ struct padata_shell {
> * appropriate for one worker thread to do at once.
> * @max_threads: Max threads to use for the job, actual number may be less
> * depending on task size and minimum chunk size.
> + * @numa_aware: Dispatch jobs to different nodes. If a node only has memory but
> + * no CPU, dispatch its jobs to a random CPU.
> */
> struct padata_mt_job {
> void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
> @@ -146,6 +148,7 @@ struct padata_mt_job {
> unsigned long align;
> unsigned long min_chunk;
> int max_threads;
> + bool numa_aware;
> };
>
> /**
> diff --git a/kernel/padata.c b/kernel/padata.c
> index 179fb1518070c..1c2b3a337479e 100644
> --- a/kernel/padata.c
> +++ b/kernel/padata.c
> @@ -485,7 +485,7 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
> struct padata_work my_work, *pw;
> struct padata_mt_job_state ps;
> LIST_HEAD(works);
> - int nworks;
> + int nworks, nid = 0;
If we always start from 0, we may be biased towards the low numbered node,
and not use high numbered nodes at all. Suggest you do
static nid = 0;
>
> if (job->size == 0)
> return;
> @@ -517,7 +517,11 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
> ps.chunk_size = roundup(ps.chunk_size, job->align);
>
> list_for_each_entry(pw, &works, pw_list)
> - queue_work(system_unbound_wq, &pw->pw_work);
> + if (job->numa_aware)
> + queue_work_node((++nid % num_node_state(N_MEMORY)),
> + system_unbound_wq, &pw->pw_work);
I think we should use nid = next_node(nid, node_states[N_CPU]) instead of
++nid % num_node_state(N_MEMORY). You are picking the next node with CPU
to handle the job.
Tim
> + else
> + queue_work(system_unbound_wq, &pw->pw_work);
>
> /* Use the current thread, which saves starting a workqueue worker. */
> padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index 89dc29f1e6c6f..59fcffddf65a3 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -2225,6 +2225,7 @@ static int __init deferred_init_memmap(void *data)
> .align = PAGES_PER_SECTION,
> .min_chunk = PAGES_PER_SECTION,
> .max_threads = max_threads,
> + .numa_aware = false,
> };
>
> padata_do_multithreaded(&job);
