Thread (33 messages) 33 messages, 4 authors, 2019-02-10

Re: [PATCH 19/19] io_uring: add io_uring_event cache hit information

From: Hannes Reinecke <hare@suse.de>
Date: 2019-02-10 09:37:03
Also in: linux-block

On 2/9/19 10:13 PM, Jens Axboe wrote:
quoted hunk ↗ jump to hunk
Add hint on whether a read was served out of the page cache, or if it
hit media. This is useful for buffered async IO, O_DIRECT reads would
never have this set (for obvious reasons).

If the read hit page cache, cqe->flags will have IOCQE_FLAG_CACHEHIT
set.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
  fs/io_uring.c                 | 7 ++++++-
  include/uapi/linux/io_uring.h | 5 +++++
  2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 11a549b5dcbf..d7a10484d748 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -587,11 +587,16 @@ static void io_fput(struct io_kiocb *req)
  static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
  {
  	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+	unsigned ev_flags = 0;
  
  	kiocb_end_write(kiocb);
  
  	io_fput(req);
-	io_cqring_add_event(req->ctx, req->user_data, res, 0);
+
+	if (res > 0 && (req->flags & REQ_F_FORCE_NONBLOCK))
+		ev_flags = IOCQE_FLAG_CACHEHIT;
+
+	io_cqring_add_event(req->ctx, req->user_data, res, ev_flags);
  	io_free_req(req);
  }
  
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e23408692118..24906e99fdc7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -69,6 +69,11 @@ struct io_uring_cqe {
  	__u32	flags;
  };

+/*
+ * io_uring_event->flags
+ */
+#define IOCQE_FLAG_CACHEHIT	(1U << 0)	/* IO did not hit media */
+
  /*
   * Magic offsets for the application to mmap the data it needs
   */
Hmm. The point of this patch being ... what?
Just setting a newly introduced flag seems to be a bit pointless.
Unless it has some magic interaction with io_cqring_add_event().
But then that function would have had to have knowledge of that flag 
already, which would be ... odd.

Please clarify.

Cheers,

Hannes

--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org.  For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help