[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Z-pVGyZ1vMBhUfYH@ryzen>
Date: Mon, 31 Mar 2025 10:40:59 +0200
From: Niklas Cassel <cassel@...nel.org>
To: yangxingui <yangxingui@...wei.com>
Cc: John Garry <john.g.garry@...cle.com>, Yihang Li <liyihang9@...wei.com>,
martin.petersen@...cle.com, James.Bottomley@...senpartnership.com,
linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org,
linuxarm@...wei.com, liuyonglong@...wei.com,
prime.zeng@...ilicon.com, dlemoal@...nel.org
Subject: Re: [PATCH 1/5] scsi: hisi_sas: Add host_tagset_enable module param
for v3 hw
Hello Xingui,
On Sat, Mar 29, 2025 at 05:49:47PM +0800, yangxingui wrote:
> Hi,John
>
> On 2025/3/29 16:50, John Garry wrote:
> > On 29/03/2025 07:32, Yihang Li wrote:
> >
> > +
> >
> > > From: Xingui Yang<yangxingui@...wei.com>
> > >
> > > After driver exposes all HW queues and application submits IO to multiple
> > > queues in parallel, if NCQ and non-NCQ commands are mixed to sata disk,
> > > ata_qc_defer() causes non-NCQ commands to be requeued and possibly
> > > repeated
> > > forever.
> >
> > I don't think that it is a good idea to mask out bugs with module
> > parameters.
> >
> > Was this the same libata/libsas issue reported some time ago?
>
> Yeah,related to this issue: https://lore.kernel.org/linux-block/eef1e927-c9b2-c61d-7f48-92e65d8b0418@huawei.com/
>
> And, Niklas tried to help fix this problem:
> https://lore.kernel.org/linux-scsi/ZynmfyDA9R-lrW71@ryzen/
>
> Considering that there is no formal solution yet. And our users rarely use
> SATA disks and SAS disks together on a single machine. For this reason, they
> can flexibly turn off the exposure of multiple queues in the scenario of
> using only SATA disks. In addition, it is also convenient to conduct
> performance comparison tests to expose multiple hardware queues and single
> queues.
The solution I sent is not good since it relies on EH.
One would need to come up with a better solution to fix libsas drivers,
possibly a workqueue.
I think Damien is planning to add a workqueue submit path to libata,
if so, perhaps we could base a better solution on top of that.
Kind regards,
Niklas
Powered by blists - more mailing lists