linux-kernel - Re: [PATCH v2 4/4] block, bfq: consider request size in bfq_asymmetric

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 26 Aug 2021 19:00:47 +0200
From:   Paolo Valente <paolo.valente@...aro.org>
To:     Yu Kuai <yukuai3@...wei.com>
Cc:     axboe@...nel.dk, linux-block@...r.kernel.org,
        linux-kernel@...r.kernel.org, yi.zhang@...wei.com
Subject: Re: [PATCH v2 4/4] block, bfq: consider request size in
 bfq_asymmetric_scenario()



> Il giorno 6 ago 2021, alle ore 04:08, Yu Kuai <yukuai3@...wei.com> ha scritto:
> 
> There is a special case when bfq do not need to idle when more than
> one groups is active:
> 

Unfortunately, there is a misunderstanding here.  If more than one
group is active, then idling is not needed only if a lot of symmetry
conditions also hold:
- all active groups have the same weight
- all active groups contain the same number of active queues
- all active queues have the same weight
- all active queues belong to the same I/O-priority class
- all dispatched requests have the same size

Similarly, if only one group is active, then idling is not needed only
if the above last three conditions hold.

The current logic, including your changes up to your previous patch,
is simply ignoring the last condition above.

So, unfortunately, your extra information about varied request size
should be used in the opposite way than how you propose to use it.

Thanks,
Paolo

> 1) all active queues have the same weight,
> 2) all active queues have the same request size.
> 3) all active queues belong to the same I/O-priority class,
> 
> Each time a request is dispatched, bfq can switch in service queue
> safely, since the throughput of each active queue is guaranteed to
> be equivalent.
> 
> Test procedure:
> run "fio -numjobs=1 -ioengine=psync -bs=4k -direct=1 -rw=randread..." in
> different cgroup(not root).
> 
> Test result: total bandwidth(Mib/s)
> | total jobs | before this patch | after this patch      |
> | ---------- | ----------------- | --------------------- |
> | 1          | 33.8              | 33.8                  |
> | 2          | 33.8              | 65.4 (32.7 each job)  |
> | 4          | 33.8              | 106.8 (26.7 each job) |
> | 8          | 33.8              | 126.4 (15.8 each job) |
> 
> Signed-off-by: Yu Kuai <yukuai3@...wei.com>
> ---
> block/bfq-iosched.c | 13 ++++++++++++-
> 1 file changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
> index 7df3fc0ef4ef..e5a07bd1fd84 100644
> --- a/block/bfq-iosched.c
> +++ b/block/bfq-iosched.c
> @@ -268,6 +268,16 @@ static struct kmem_cache *bfq_pool;
>  */
> #define BFQ_RATE_SHIFT		16
> 
> +/*
> + * 1) bfq keep dispatching requests with same size for at least one second.
> + * 2) bfq dispatch at lease 1024 requests
> + *
> + * We think bfq are dispatching request with same size if the above two
> + * conditions hold true.
> + */
> +#define VARIED_REQUEST_SIZE(bfqd) ((bfqd)->dispatch_count < 1024 ||\
> +		time_before(jiffies, (bfqd)->dispatch_time + HZ))
> +
> /*
>  * When configured for computing the duration of the weight-raising
>  * for interactive queues automatically (see the comments at the
> @@ -724,7 +734,8 @@ static bool bfq_asymmetric_scenario(struct bfq_data *bfqd,
> 	bool multiple_classes_busy;
> 
> #ifdef CONFIG_BFQ_GROUP_IOSCHED
> -	if (bfqd->num_groups_with_pending_reqs > 1)
> +	if (bfqd->num_groups_with_pending_reqs > 1 &&
> +	    VARIED_REQUEST_SIZE(bfqd))
> 		return true;
> 
> 	if (bfqd->num_groups_with_pending_reqs &&
> -- 
> 2.31.1
>