Skip to contentSkip to conversation

padata-dispatch-works-on-different-nodes.patch removed from -mm tree

merged mm-stable Andrew Morton 1 participant 1 message Mar 6, 2024

lore
Share & tools
lore

Andrew Morton

author tree notice Applied
#0 lore raw

The quilt patch titled

     different nodes Date: Thu, 22 Feb 2024 22:04:17 +0800

has been removed from the -mm tree. Its filename was
padata-dispatch-works-on-different-nodes.patch

This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Gang Li <[email protected]> Subject: padata: dispatch works on different nodes Date: Thu, 22 Feb 2024 22:04:17 +0800

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.

---

 include/linux/padata.h |    2 ++
 kernel/padata.c        |   14 ++++++++++++--
 mm/mm_init.c           |    1 +
 3 files changed, 15 insertions(+), 2 deletions(-)
include/linux/padata.h renamed from include/linux/padata.h~padata-dispatch-works-on-different-nodes +2 -0
@@ -137,6 +137,7 @@ 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: Distribute jobs to different nodes with CPU in a round robin fashion.
  */
 struct padata_mt_job {
 	void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
@@ -146,6 +147,7 @@ struct padata_mt_job {
 	unsigned long		align;
 	unsigned long		min_chunk;
 	int			max_threads;
+	bool			numa_aware;
 };
 
 /**
kernel/padata.c renamed from kernel/padata.c~padata-dispatch-works-on-different-nodes +12 -2
@@ -485,7 +485,8 @@ void __init padata_do_multithreaded(stru
 	struct padata_work my_work, *pw;
 	struct padata_mt_job_state ps;
 	LIST_HEAD(works);
-	int nworks;
+	int nworks, nid;
+	static atomic_t last_used_nid __initdata;
 
 	if (job->size == 0)
 		return;
@@ -517,7 +518,16 @@ void __init padata_do_multithreaded(stru
 	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) {
+			int old_node = atomic_read(&last_used_nid);
+
+			do {
+				nid = next_node_in(old_node, node_states[N_CPU]);
+			} while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid));
+			queue_work_node(nid, system_unbound_wq, &pw->pw_work);
+		} 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);
mm/mm_init.c renamed from mm/mm_init.c~padata-dispatch-works-on-different-nodes +1 -0
@@ -2231,6 +2231,7 @@ static int __init deferred_init_memmap(v
 			.align       = PAGES_PER_SECTION,
 			.min_chunk   = PAGES_PER_SECTION,
 			.max_threads = max_threads,
+			.numa_aware  = false,
 		};
 
 		padata_do_multithreaded(&job);

_

Patches currently in -mm which might be from [email protected] are