lkml.org 
[lkml]   [2022]   [Mar]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] bfq: default slice_idle to 0 for SSD
From
Date


> Il giorno 8 mar 2022, alle ore 01:02, Khazhismel Kumykov <khazhy@google.com> ha scritto:
>
> This improves performance on SSDs dramatically, and was default for CFQ
>

Ho,
unfortunately it is unacceptable, because it simply switches BFQ off with sync I/O.

Thanks,
Paolo

> Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
> ---
> block/bfq-iosched.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 36a66e97e3c2..f3196036940c 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -7105,7 +7105,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
> bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
> bfqd->bfq_back_max = bfq_back_max;
> bfqd->bfq_back_penalty = bfq_back_penalty;
> - bfqd->bfq_slice_idle = bfq_slice_idle;
> + /* Default to no idling for SSDs */
> + bfqd->bfq_slice_idle = blk_queue_nonrot(q) ? 0 : bfq_slice_idle;
> bfqd->bfq_timeout = bfq_timeout;
>
> bfqd->bfq_large_burst_thresh = 8;
> --
> 2.35.1.616.g0bdcbb4464-goog
>

\
 
 \ /
  Last update: 2022-03-08 10:14    [W:0.027 / U:3.408 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site