linux-kernel - RE: [PATCH 10/13] scsi: fnic: Add support for multiqueue (MQ) in fnic

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] [day] [month] [year] [list]

Message-ID: <SJ0PR11MB5896F9262C82755C5491B85FC3AFA@SJ0PR11MB5896.namprd11.prod.outlook.com>
Date:   Thu, 9 Nov 2023 02:21:17 +0000
From:   "Karan Tilak Kumar (kartilak)" <kartilak@...co.com>
To:     John Garry <john.g.garry@...cle.com>,
        "Sesidhar Baddela (sebaddel)" <sebaddel@...co.com>
CC:     "Arulprabhu Ponnusamy (arulponn)" <arulponn@...co.com>,
        "Dhanraj Jhawar (djhawar)" <djhawar@...co.com>,
        "Gian Carlo Boffa (gcboffa)" <gcboffa@...co.com>,
        "Masa Kai (mkai2)" <mkai2@...co.com>,
        "Satish Kharat (satishkh)" <satishkh@...co.com>,
        "jejb@...ux.ibm.com" <jejb@...ux.ibm.com>,
        "martin.petersen@...cle.com" <martin.petersen@...cle.com>,
        "linux-scsi@...r.kernel.org" <linux-scsi@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: RE: [PATCH 10/13] scsi: fnic: Add support for multiqueue (MQ) in
 fnic_main.c

On Wednesday, November 8, 2023 5:57 AM, John Garry <john.g.garry@...cle.com> wrote:
> Please be aware of comment on nr_hw_queues in scsi_host.h - maybe it is relevant to this adapter:
>
> "the total queue depth per host is nr_hw_queues * can_queue"

Thanks John.

> Also, since you seem to be using blk_mq_unique_tag() as the per-IO tag, I assume that you don't need to set shost.host_tagset (for that reason).

Yes, that's correct.

> > +void fnic_mq_map_queues_cpus(struct Scsi_Host *host)
>
> This function looks to do effectively the same as blk_mq_pci_map_queues(), right?

Yes, it looks like it is accomplishing the same goal. Thanks for this information.
I'll experiment with this function on my setup and make suitable modifications in v3, if successful.

Regards,
Karan