From 07754bfd9aee59063f8549f6e4d455eae636ecc7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 14 Mar 2025 10:19:01 -0600 Subject: io_uring: enable toggle of iowait usage when waiting on CQEs By default, io_uring marks a waiting task as being in iowait, if it's sleeping waiting on events and there are pending requests. This isn't necessarily always useful, and may be confusing on non-storage setups where iowait isn't expected. It can also cause extra power usage, by preventing the CPU from entering lower sleep states. This adds a new enter flag, IORING_ENTER_NO_IOWAIT. If set, then io_uring will not account the sleeping task as being in iowait. If the kernel supports this feature, then it will be marked by having the IORING_FEAT_NO_IOWAIT feature flag set. As the kernel currently does not support separating the iowait accounting and CPU frequency boosting, the IORING_ENTER_NO_IOWAIT controls both of these at the same time. In the future, if those do end up being split, then it'd be possible to control them separately. However, it seems more likely that the kernel will decouple iowait and CPU frequency boosting anyway. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 050fa8eb2e8f..0d6c83c8d1cf 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -541,6 +541,7 @@ struct io_cqring_offsets { #define IORING_ENTER_REGISTERED_RING (1U << 4) #define IORING_ENTER_ABS_TIMER (1U << 5) #define IORING_ENTER_EXT_ARG_REG (1U << 6) +#define IORING_ENTER_NO_IOWAIT (1U << 7) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -578,6 +579,7 @@ struct io_uring_params { #define IORING_FEAT_RECVSEND_BUNDLE (1U << 14) #define IORING_FEAT_MIN_TIMEOUT (1U << 15) #define IORING_FEAT_RW_ATTR (1U << 16) +#define IORING_FEAT_NO_IOWAIT (1U << 17) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3