linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: John Garry <john.g.garry@oracle.com>,
	"Martin K . Petersen" <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org, Hannes Reinecke <hare@suse.de>,
	Ming Lei <ming.lei@redhat.com>,
	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Subject: Re: [PATCH v6 03/28] scsi: core: Make the budget map optional
Date: Wed, 22 Oct 2025 10:23:55 -0700	[thread overview]
Message-ID: <e241e5c1-a908-4d2f-8f66-82ac3fec937e@acm.org> (raw)
In-Reply-To: <60f9a312-455a-4714-81fc-abbcf86715f5@oracle.com>

On 10/22/25 1:29 AM, John Garry wrote:
> On 14/10/2025 21:15, Bart Van Assche wrote:
>> @@ -1360,6 +1361,9 @@ static inline int scsi_dev_queue_ready(struct 
>> request_queue *q,
>>   {
>>       int token;
>> +    if (!sdev->budget_map.map)
>> +        return INT_MAX;
> 
> For the record, I would not do things in this way.
> 
> The shost psuedo sdev does not need a budget, as mentioned.
> 
> However we complicate the code and add extra checks in the fastpath 
> (like in this function) by treating this sdev as special and not having 
> a budget.

Hi John,

The following patch series will be reposted after this patch series has
been merged: "[PATCH 0/3] Improve host-wide tag IOPS"
(https://lore.kernel.org/linux-scsi/20250910213254.1215318-1-bvanassche@acm.org/). 
Patch 3/3 from that series skips budget map
allocation if it is safe to do so. I don't think that it is possible to
skip budget map allocation in some cases without introducing an if-test.
In other words, the if-tests introduced by this patch will get more
users and will enable an important optimization for the fast path.

Thanks,

Bart.

  reply	other threads:[~2025-10-22 17:24 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-14 20:15 [PATCH v6 00/28] Optimize the hot path in the UFS driver Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 01/28] scsi: core: Support allocating reserved commands Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 02/28] scsi: core: Move two statements Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 03/28] scsi: core: Make the budget map optional Bart Van Assche
2025-10-16  6:06   ` Hannes Reinecke
2025-10-22  8:29   ` John Garry
2025-10-22 17:23     ` Bart Van Assche [this message]
2025-10-23 10:02       ` John Garry
2025-10-14 20:15 ` [PATCH v6 04/28] scsi: core: Support allocating a pseudo SCSI device Bart Van Assche
2025-10-20 11:10   ` John Garry
2025-10-20 16:10     ` Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 05/28] scsi: core: Introduce .queue_reserved_command() Bart Van Assche
2025-11-05  8:05   ` Hannes Reinecke
2025-10-14 20:15 ` [PATCH v6 06/28] scsi: core: Add scsi_{get,put}_internal_cmd() helpers Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 07/28] scsi_debug: Abort SCSI commands via an internal command Bart Van Assche
2025-10-22  8:46   ` John Garry
2025-10-23 16:19     ` Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 08/28] ufs: core: Move an assignment in ufshcd_mcq_process_cqe() Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 09/28] ufs: core: Change the type of one ufshcd_add_cmd_upiu_trace() argument Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 10/28] ufs: core: Only call ufshcd_add_command_trace() for SCSI commands Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 11/28] ufs: core: Change the type of one ufshcd_add_command_trace() argument Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 12/28] ufs: core: Change the type of one ufshcd_send_command() argument Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 13/28] ufs: core: Only call ufshcd_should_inform_monitor() for SCSI commands Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 14/28] ufs: core: Change the monitor function argument types Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 15/28] ufs: core: Rework ufshcd_mcq_compl_pending_transfer() Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 16/28] ufs: core: Rework ufshcd_eh_device_reset_handler() Bart Van Assche
2025-10-14 20:15 ` [PATCH v6 17/28] ufs: core: Rework the SCSI host queue depth calculation code Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 18/28] ufs: core: Allocate the SCSI host earlier Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 19/28] ufs: core: Call ufshcd_init_lrb() later Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 20/28] ufs: core: Use hba->reserved_slot Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 21/28] ufs: core: Make the reserved slot a reserved request Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 22/28] ufs: core: Do not clear driver-private command data Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 23/28] ufs: core: Optimize the hot path Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 24/28] ufs: core: Pass a SCSI pointer instead of an LRB pointer Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 25/28] ufs: core: Remove the ufshcd_lrb task_tag member Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 26/28] ufs: core: Make blk_mq_tagset_busy_iter() skip reserved requests Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 27/28] ufs: core: Move code out of ufshcd_wait_for_dev_cmd() Bart Van Assche
2025-10-14 20:16 ` [PATCH v6 28/28] ufs: core: Switch to scsi_get_internal_cmd() Bart Van Assche

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e241e5c1-a908-4d2f-8f66-82ac3fec937e@acm.org \
    --to=bvanassche@acm.org \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=hare@suse.de \
    --cc=john.g.garry@oracle.com \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=ming.lei@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).