On 7/24/23 10:07?AM, Phil Elwell wrote:
Even though I don't think this is an actual problem, it is a bit confusing that you get 100% iowait while waiting without having IO pending. So I do think the suggested patch is probably worthwhile pursuing. I'll post it and hopefully have Andres test it too, if he's available.
If you CC me I'll happily test it for you.
Here it is.
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 89a611541bc4..f4591b912ea8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2493,11 +2493,20 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) return 0; }
+static bool current_pending_io(void) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx) + return false; + return percpu_counter_read_positive(&tctx->inflight); +} + /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { - int token, ret; + int io_wait, ret;
if (unlikely(READ_ONCE(ctx->check_cq))) return 1; @@ -2511,17 +2520,19 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return 0;
/* - * Use io_schedule_prepare/finish, so cpufreq can take into account - * that the task is waiting for IO - turns out to be important for low - * QD IO. + * Mark us as being in io_wait if we have pending requests, so cpufreq + * can take into account that the task is waiting for IO - turns out + * to be important for low QD IO. */ - token = io_schedule_prepare(); + io_wait = current->in_iowait; + if (current_pending_io()) + current->in_iowait = 1; ret = 0; if (iowq->timeout == KTIME_MAX) schedule(); else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) ret = -ETIME; - io_schedule_finish(token); + current->in_iowait = io_wait; return ret; }