On 2025-01-04 2:24 AM, Zi Yan wrote:
Now page copies are batched, multi-threaded page copy can be used to
increase page copy throughput. Add copy_page_lists_mt() to copy pages in
multi-threaded manners. Empirical data show more than 32 base pages are
needed to show the benefit of using multi-threaded page copy, so use 32 as
the threshold.
>
Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
---
include/linux/migrate.h | 3 +
mm/Makefile | 2 +-
mm/copy_pages.c | 186 ++++++++++++++++++++++++++++++++++++++++
mm/migrate.c | 19 ++--
4 files changed, 199 insertions(+), 11 deletions(-)
create mode 100644 mm/copy_pages.c
[...snip...]
+++ b/mm/copy_pages.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Parallel page copy routine.
+ */
+
+#include <linux/sysctl.h>
+#include <linux/highmem.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/migrate.h>
+
+
+unsigned int limit_mt_num = 4;
+
+struct copy_item {
+ char *to;
+ char *from;
+ unsigned long chunk_size;
+};
+
+struct copy_page_info {
+ struct work_struct copy_page_work;
+ unsigned long num_items;
+ struct copy_item item_list[];
+};
+
+static void copy_page_routine(char *vto, char *vfrom,
+ unsigned long chunk_size)
+{
+ memcpy(vto, vfrom, chunk_size);
+}
+
+static void copy_page_work_queue_thread(struct work_struct *work)
+{
+ struct copy_page_info *my_work = (struct copy_page_info *)work;
+ int i;
+
+ for (i = 0; i < my_work->num_items; ++i)
+ copy_page_routine(my_work->item_list[i].to,
+ my_work->item_list[i].from,
+ my_work->item_list[i].chunk_size);
+}
+
+int copy_page_lists_mt(struct list_head *dst_folios,
+ struct list_head *src_folios, int nr_items)
+{
+ int err = 0;
+ unsigned int total_mt_num = limit_mt_num;
+ int to_node = folio_nid(list_first_entry(dst_folios, struct folio, lru));
+ int i;
+ struct copy_page_info *work_items[32] = {0};
+ const struct cpumask *per_node_cpumask = cpumask_of_node(to_node);
What happens here if to_node is a NUMA node without CPUs? (e.g. CXL
node).
And even with a NUMA node with CPUs I think offloading copies to CPUs
of either "from node" or "to node" will end up a CPU touching two pages
in two different NUMA nodes anyway, one page in the local node
and the other page in the remote node.
In that sense, I don't understand when push_0_pull_1 (introduced in
patch 5) should be 0 or 1. Am I missing something?
+ int cpu_id_list[32] = {0};
+ int cpu;
+ int max_items_per_thread;
+ int item_idx;
+ struct folio *src, *src2, *dst, *dst2;
+
+ total_mt_num = min_t(unsigned int, total_mt_num,
+ cpumask_weight(per_node_cpumask));
+
+ if (total_mt_num > 32)
+ total_mt_num = 32;
+
+ /* Each threads get part of each page, if nr_items < totla_mt_num */
+ if (nr_items < total_mt_num)
+ max_items_per_thread = nr_items;
+ else
+ max_items_per_thread = (nr_items / total_mt_num) +
+ ((nr_items % total_mt_num) ? 1 : 0);
+
+
+ for (cpu = 0; cpu < total_mt_num; ++cpu) {
+ work_items[cpu] = kzalloc(sizeof(struct copy_page_info) +
+ sizeof(struct copy_item) * max_items_per_thread,
+ GFP_NOWAIT);
> +
+ if (!work_items[cpu]) {
+ err = -ENOMEM;
+ goto free_work_items;
+ }
+ }
[...snip...]
+
+ /* Wait until it finishes */
+ for (i = 0; i < total_mt_num; ++i)
+ flush_work((struct work_struct *)work_items[i]);
+
+free_work_items:
+ for (cpu = 0; cpu < total_mt_num; ++cpu)
+ kfree(work_items[cpu]);
+
+ return err;
Should the kernel re-try migration without multi-threading if it failed
to allocate memory?
---
Hyeonggon
