This is another performance optimization - async requests are
better served on another core.
Async blocking requests are marked as such and treated as sync requests.
Example with mmap read
fio --size=1G --numjobs=32 --ioengine=mmap --output-format=normal,terse\
--directory=/scratch/dest/ --rw=read --bs=4K --group_reporting \
job-file.fio
jobs /dev/fuse uring gain uring gain gain
(core+1)
(to dev) (to dev) (uring same-core)
1 124.61 306.59 2.46 255.51 2.05 0.83
2 248.83 580.00 2.33 563.00 2.26 0.97
4 611.47 1049.65 1.72 998.57 1.63 0.95
8 1499.95 1848.42 1.23 1990.64 1.33 1.08
16 2206.30 2890.24 1.31 3439.13 1.56 1.19
24 2545.68 2704.87 1.06 4527.63 1.78 1.67
32 2233.52 2574.37 1.15 5263.09 2.36 2.04
Interesting here is that the max gain comes with more core usage,
I had actually expected the other way around.
Signed-off-by: Bernd Schubert <bschubert@xxxxxxx>
---
fs/fuse/dev_uring.c | 5 ++++-
fs/fuse/file.c | 1 +
fs/fuse/fuse_i.h | 1 +
3 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index fe80e66150c3..dff210658172 100644
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -1106,6 +1106,8 @@ int fuse_uring_queue_fuse_req(struct fuse_conn *fc, struct fuse_req *req)
struct list_head *req_queue, *ent_queue;
if (ring->per_core_queue) {
+ int cpu_off;
+
/*
* async requests are best handled on another core, the current
* core can do application/page handling, while the async request
@@ -1118,7 +1120,8 @@ int fuse_uring_queue_fuse_req(struct fuse_conn *fc, struct fuse_req *req)
* It should also not persistently switch between cores - makes
* it hard for the scheduler.
*/
- qid = task_cpu(current);
+ cpu_off = async ? 1 : 0;
+ qid = (task_cpu(current) + cpu_off) % ring->nr_queues;
if (unlikely(qid >= ring->nr_queues)) {
WARN_ONCE(1,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b57ce4157640..6fda1e7bd7f4 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -791,6 +791,7 @@ static ssize_t fuse_async_req_send(struct fuse_mount *fm,
ia->ap.args.end = fuse_aio_complete_req;
ia->ap.args.may_block = io->should_dirty;
+ ia->ap.args.async_blocking = io->blocking;
err = fuse_simple_background(fm, &ia->ap.args, GFP_KERNEL);
if (err)
fuse_aio_complete_req(fm, &ia->ap.args, err);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fadc51a22bb9..7dcf0472df67 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -309,6 +309,7 @@ struct fuse_args {
bool may_block:1;
bool is_ext:1;
bool is_pinned:1;
+ bool async_blocking : 1;
struct fuse_in_arg in_args[3];
struct fuse_arg out_args[2];
void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
--
2.40.1
