public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH 8/8] io_uring: warn when ring exit takes too long
Date: Thu,  4 Mar 2021 13:59:31 +0000	[thread overview]
Message-ID: <4bc9b29f2f5b7952b313be604f43b131a2dfe277.1614866085.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>

We use system_unbound_wq to run io_ring_exit_work(), so it's hard to
monitor whether removal hang or not. Add WARN_ONCE to catch hangs.

Signed-off-by: Pavel Begunkov <[email protected]>
---
 fs/io_uring.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 46a2417187ff..b4820f6261fe 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8547,6 +8547,8 @@ static void io_ring_exit_work(struct work_struct *work)
 	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
 	struct io_tctx_exit exit;
 	struct io_tctx_node *node;
+	const u64 bias_ms = MSEC_PER_SEC * 60 * 5;
+	ktime_t start = ktime_get();
 	int ret;
 
 	/*
@@ -8557,10 +8559,13 @@ static void io_ring_exit_work(struct work_struct *work)
 	 */
 	do {
 		io_uring_try_cancel_requests(ctx, NULL, NULL);
+		WARN_ON_ONCE(ktime_ms_delta(ktime_get(), start) > bias_ms);
 	} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
 
 	mutex_lock(&ctx->uring_lock);
 	while (!list_empty(&ctx->tctx_list)) {
+		WARN_ON_ONCE(ktime_ms_delta(ktime_get(), start) > bias_ms);
+
 		node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
 					ctx_node);
 		exit.ctx = ctx;
-- 
2.24.0


  parent reply	other threads:[~2021-03-04 14:05 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-04 13:59 [PATCH 5.12 0/8] remove task file notes Pavel Begunkov
2021-03-04 13:59 ` [PATCH 1/8] io_uring: cancel-match based on flags Pavel Begunkov
2021-03-04 13:59 ` [PATCH 2/8] io_uring: reliably cancel linked timeouts Pavel Begunkov
2021-03-04 13:59 ` [PATCH 3/8] io_uring: make del_task_file more forgiving Pavel Begunkov
2021-03-04 13:59 ` [PATCH 4/8] io_uring: introduce ctx to tctx back map Pavel Begunkov
2021-03-04 13:59 ` [PATCH 5/8] io_uring: do ctx initiated file note removal Pavel Begunkov
2021-03-04 13:59 ` [PATCH 6/8] io_uring: don't take task ring-file notes Pavel Begunkov
2021-03-04 13:59 ` [PATCH 7/8] io_uring: index io_uring->xa by ctx not file Pavel Begunkov
2021-03-04 13:59 ` Pavel Begunkov [this message]
2021-03-05  4:25   ` [PATCH 8/8] io_uring: warn when ring exit takes too long Jens Axboe
2021-03-05 11:15     ` Pavel Begunkov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4bc9b29f2f5b7952b313be604f43b131a2dfe277.1614866085.git.asml.silence@gmail.com \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox