[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220203182441.692354-1-usama.arif@bytedance.com>
Date: Thu, 3 Feb 2022 18:24:38 +0000
From: Usama Arif <usama.arif@...edance.com>
To: io-uring@...r.kernel.org, axboe@...nel.dk, asml.silence@...il.com,
linux-kernel@...r.kernel.org
Cc: fam.zheng@...edance.com, Usama Arif <usama.arif@...edance.com>
Subject: [PATCH v4 0/3] io_uring: avoid ring quiesce in io_uring_register for eventfd opcodes
This is done by creating a new RCU data structure (io_ev_fd) as part of
io_ring_ctx that holds the eventfd_ctx, with reads to the structure protected
by rcu_read_lock and writes (register/unregister calls) protected by a mutex.
With the above approach ring quiesce can be avoided which is much more
expensive then using RCU lock. On the system tested, io_uring_reigster with
IORING_REGISTER_EVENTFD takes less than 1ms with RCU lock, compared to 15ms
before with ring quiesce.
The first patch creates the RCU protected data structure and removes ring
quiesce for IORING_REGISTER_EVENTFD and IORING_UNREGISTER_EVENTFD.
The second patch builds on top of the first patch and removes ring quiesce
for IORING_REGISTER_EVENTFD_ASYNC.
---
v3->v4:
- Switch back to call_rcu and use rcu_barrier incase io_eventfd_register fails
to make sure all rcu callbacks have finished.
v2->v3:
- Switched to using synchronize_rcu from call_rcu in io_eventfd_unregister.
v1->v2:
- Added patch to remove eventfd from tracepoint (Patch 1) (Jens Axboe)
- Made the code of io_should_trigger_evfd as part of io_eventfd_signal (Jens Axboe)
Usama Arif (3):
io_uring: remove trace for eventfd
io_uring: avoid ring quiesce while registering/unregistering eventfd
io_uring: avoid ring quiesce for IORING_REGISTER_EVENTFD_ASYNC
fs/io_uring.c | 127 +++++++++++++++++++++++---------
include/trace/events/io_uring.h | 13 ++--
2 files changed, 96 insertions(+), 44 deletions(-)
--
2.25.1
Powered by blists - more mailing lists