From: "Singh, Balbir" <sblbir@amazon.com>
To: "kbusch@kernel.org" <kbusch@kernel.org>
Cc: "axboe@fb.com" <axboe@fb.com>,
"sblbir@amzn.com" <sblbir@amzn.com>, "hch@lst.de" <hch@lst.de>,
"linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
"sagi@grimberg.me" <sagi@grimberg.me>
Subject: Re: [PATCH v2 2/2] nvme/host/core: Allow overriding of wait_ready timeout
Date: Tue, 17 Sep 2019 02:56:44 +0000 [thread overview]
Message-ID: <9612b87ed79704b89da559f42e3051ecb171a2ce.camel@amazon.com> (raw)
In-Reply-To: <20190917011441.GA31163@C02WT3WMHTD6>
On Mon, 2019-09-16 at 19:14 -0600, Keith Busch wrote:
> On Mon, Sep 16, 2019 at 09:04:31PM +0000, Singh, Balbir wrote:
> > I wonder if I should just call it debug_wait_ready_timeout and in the
> > comments about the help/description call out that this is a debug
> > feature.
> >
> > What do you suggest?
>
> I recommend going to the vendors that report incorrect timeout values, and
> apparently broken controllers that can't initialize, to have them fix
> both. If it doesn't initialize in 128 seconds, your only debugging
> recourse is to report to the vendor anyway; overriding the timeout to
> something under what the device reports it requires doesn't exactly
> provide you any additional debugging information.
>
In my case I was doing a simple mirror (using madadm across two nvme
devices) and when I get timeouts on one, I need to wait up to 128 seconds
before switching over. Ideally I want this to be really fast and drop
the slow broken controller.
> If you really need the driver to do spec non-compliant behavior, we have
> quirks for that.
I like the quirks approach, but it assumes the timeout value is not
variable, but rather fixed by the quirk. I was attempting to really have
mirrored IO timeout quickly on a bad device.
Balbir Singh.
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2019-09-17 2:57 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-13 23:36 [PATCH v2 1/2] nvme/host/pci: Fix a race in controller removal Balbir Singh
2019-09-13 23:36 ` [PATCH v2 2/2] nvme/host/core: Allow overriding of wait_ready timeout Balbir Singh
2019-09-16 7:41 ` Christoph Hellwig
2019-09-16 12:33 ` Singh, Balbir
2019-09-16 16:01 ` hch
2019-09-16 21:04 ` Singh, Balbir
2019-09-17 1:14 ` Keith Busch
2019-09-17 2:56 ` Singh, Balbir [this message]
2019-09-17 3:17 ` Bart Van Assche
2019-09-17 5:02 ` Singh, Balbir
2019-09-17 17:21 ` James Smart
2019-09-17 20:08 ` James Smart
2019-09-17 3:54 ` Keith Busch
2019-09-16 7:49 ` [PATCH v2 1/2] nvme/host/pci: Fix a race in controller removal Christoph Hellwig
2019-09-16 12:07 ` Singh, Balbir
2019-09-16 15:40 ` Bart Van Assche
2019-09-16 19:38 ` Singh, Balbir
2019-09-16 19:56 ` Bart Van Assche
2019-09-16 20:40 ` Singh, Balbir
2019-09-17 17:55 ` Bart Van Assche
2019-09-17 20:30 ` Keith Busch
2019-09-17 20:44 ` Singh, Balbir
2019-09-16 20:07 ` Keith Busch
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=9612b87ed79704b89da559f42e3051ecb171a2ce.camel@amazon.com \
--to=sblbir@amazon.com \
--cc=axboe@fb.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
--cc=sblbir@amzn.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