From f950667356ce90a41b446b726d4595a10cb65415 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 19 May 2022 12:52:29 +0200
Subject: [PATCH] bfq: Relax waker detection for shared queues
Patch-mainline: v5.19-rc1
Git-commit: f950667356ce90a41b446b726d4595a10cb65415
References: bsc#1195915

Currently we look for waker only if current queue has no requests. This
makes sense for bfq queues with a single process however for shared
queues when there is a larger number of processes the condition that
queue has no requests is difficult to meet because often at least one
process has some request in flight although all the others are waiting
for the waker to do the work and this harms throughput. Relax the "no
queued request for bfq queue" condition to "the current task has no
queued requests yet". For this, we also need to start tracking number of
requests in flight for each task.

This patch (together with the following one) restores the performance
for dbench with 128 clients that regressed with commit c65e6fd460b4
("bfq: Do not let waker requests skip proper accounting") because
this commit makes requests of wakers properly enter BFQ queues and thus
these queues become ineligible for the old waker detection logic.
Dbench results:

         Vanilla 5.18-rc3        5.18-rc3 + revert      5.18-rc3 patched
Mean     1237.36 (   0.00%)      950.16 *  23.21%*      988.35 *  20.12%*

Numbers are time to complete workload so lower is better.

Fixes: c65e6fd460b4 ("bfq: Do not let waker requests skip proper accounting")
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220519105235.31397-1-jack@suse.cz
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Jan Kara <jack@suse.cz>

---
 block/bfq-iosched.c |    5 +++--
 block/bfq-iosched.h |    1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -2130,7 +2130,6 @@ static void bfq_check_waker(struct bfq_d
 	if (!bfqd->last_completed_rq_bfqq ||
 	    bfqd->last_completed_rq_bfqq == bfqq ||
 	    bfq_bfqq_has_short_ttime(bfqq) ||
-	    bfqq->dispatched > 0 ||
 	    now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC ||
 	    bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq)
 		return;
@@ -2201,7 +2200,7 @@ static void bfq_add_request(struct reque
 	bfqq->queued[rq_is_sync(rq)]++;
 	bfqd->queued++;
 
-	if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
+	if (bfq_bfqq_sync(bfqq) && RQ_BIC(rq)->requests <= 1) {
 		bfq_check_waker(bfqd, bfqq, now_ns);
 
 		/*
@@ -6549,6 +6548,7 @@ static void bfq_finish_requeue_request(s
 		bfq_completed_request(bfqq, bfqd);
 	}
 	bfq_finish_requeue_request_body(bfqq);
+	RQ_BIC(rq)->requests--;
 	spin_unlock_irqrestore(&bfqd->lock, flags);
 
 	/*
@@ -6770,6 +6770,7 @@ static struct bfq_queue *bfq_init_rq(str
 
 	bfqq_request_allocated(bfqq);
 	bfqq->ref++;
+	bic->requests++;
 	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
 		     rq, bfqq, bfqq->ref);
 
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -469,6 +469,7 @@ struct bfq_io_cq {
 	struct bfq_queue *stable_merge_bfqq;
 
 	bool stably_merged;	/* non splittable if true */
+	unsigned int requests;	/* Number of requests this process has in flight */
 };
 
 /**