Linux-NVME Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: ming.lei@redhat.com (Ming Lei)
Subject: fstrim error - AORUS NVMe Gen4 SSD
Date: Wed, 24 Jul 2019 09:45:12 +0800	[thread overview]
Message-ID: <20190724014510.GD22421@ming.t460p> (raw)
In-Reply-To: <5ef41ec4-abb8-90bf-e2eb-8a62f51ad951@tds.net>

On Tue, Jul 23, 2019@04:56:10PM -0500, davidc502 wrote:
> Ming,
> 
> On 7/23/19 4:38 PM, davidc502 wrote:
> > Hello,
> > 
> > On 7/22/19 11:38 PM, Ming Lei wrote:
> > > Hi,
> > > 
> > > On Mon, Jul 22, 2019@09:39:07PM -0500, davidc502 wrote:
> > > > See attached:? nvme_io_trace.log
> > > > 
> > > > 
> > > > On 7/22/19 9:19 PM, Ming Lei wrote:
> > > > > Hi,
> > > > > 
> > > > > On Sat, Jul 20, 2019@09:41:24PM -0500, davidc502 wrote:
> > > > > > ? ?Hello,
> > > > > > 
> > > > > > ? ?I've assembled a X570 board with a 1TB AORUS NVMe Gen4 SSD.
> > > > > > 
> > > > > > ? ?When attempting to fstrim the NVMe, I receive the following error.
> > > > > > ? ?davidc502 at Ryzen-3900x:~$ sudo fstrim -a -v
> > > > > > ? ?fstrim: /boot/efi: FITRIM ioctl failed: Input/output error
> > > > > > ? ?fstrim: /: FITRIM ioctl failed: Input/output error
> > > > > > 
> > > > > > ? ?Anyhow, I have put some details below which might be
> > > > > > helpful. Note that
> > > > > > this NVMe is supposed to be TRIM and SMART compliant.
> > > > > > The SMART outputs are
> > > > > > available using the utility ?nvme-cli?.
> > > > > > ? ?I am willing to provide whatever command outputs that
> > > > > > are needed to help
> > > > > > solve this issue.
> > > > > > 
> > > > > > ? ?OS= Ubuntu 18.4.2 LTS
> > > > > > ? ?Different Kernels I?ve tried = 5.1.16, 5.2 rc7, and 4.18
> > > > > > ? ?fstrim version =? fstrim from util-linux 2.31.1
> > > > > > ? ?Firmware version for Aorus NVMe = EGFM11.0
> > > > > > 
> > > > > I saw discard timeout on HGST 1.6TB NVMe, not sure if yours
> > > > > is same with
> > > > > that one.
> > > > > 
> > > > > Could you collect logs via the following steps?
> > > > > 
> > > > > Suppose your nvme disk name is /dev/nvme0n1:
> > > > > 
> > > > > 1) queue limits log:
> > > > > 
> > > > > ????#(cd /sys/block/nvme0n1/queue && find . -type f -exec
> > > > > grep -aH . {} \;)
> > > > > 
> > > > > 
> > > > > 2) NVMe IO trace
> > > > > 
> > > > > - enable nvme IO trace before running fstrim:
> > > > > 
> > > > > ????#echo 1? > /sys/kernel/debug/tracing/events/nvme_setup_cmd/enable
> > > > > ????#echo 1? >
> > > > > /sys/kernel/debug/tracing/events/nvme_complete_rq/enable
> > > > > 
> > > > > - run fstrim
> > > > > 
> > > > > - after the fstrim failure is triggered, disable the nvme io
> > > > > trace & post the log:
> > > > > 
> > > > > ????#echo 0? > /sys/kernel/debug/tracing/events/nvme_setup_cmd/enable
> > > > > ????#echo 0? >
> > > > > /sys/kernel/debug/tracing/events/nvme_complete_rq/enable
> > > > > 
> > > > > ????#cp??? /sys/kernel/debug/tracing/trace /root/nvme_io_trace.log
> > > > > 
> > > > > 
> > > > > 
> > > > > thanks,
> > > > > Ming
> > > > 
> > > > Hello Ming
> > > > 
> > > > Thank you for the quick reply --? See attached
> > > ?From the IO trace, discard command(nvme_cmd_dsm) is failed:
> > > 
> > > ?? kworker/15:1H-462?? [015] .... 91814.342452: nvme_setup_cmd:
> > > nvme0: disk=nvme0n1, qid=7, cmdid=552, nsid=1, flags=0x0, meta=0x0,
> > > cmd=(nvme_cmd_dsm nr=0, attributes=4)
> > > ?????????? <idle>-0???? [013] d.h. 91814.342708: nvme_complete_rq:
> > > nvme0: disk=nvme0n1, qid=7, cmdid=552, res=0, retries=0, flags=0x0,
> > > status=8198
> > > 
> > > And the returned error code is 0x8198, I am not sure how to parse the
> > > 'Command Specific Status Values' of 0x98, maybe Christoph, Keith or
> > > our other
> > > NVMe guys can help to understand the failure.
> > > 
> > > 
> > > Thanks,
> > > Ming
> > 
> > Long story short we have 3 new PCI Gen 4 SSD - NVMe drives from
> > Gigabyte. But actually, Gigabyte is just putting their name on it as I
> > believe it is actually from "Phison".
> > 
> > Here is the website where you can see the new drives --
> > https://www.gigabyte.com/Solid-State-Drive/Gen-4
> > 
> > I have opened a ticket with Gigabyte, and have inquired about any
> > available firmware updates. It will take 3-5 days to hear back from
> > them, but will report back the finding.
> > 
> > Thank you for taking a look at the tracing file, and hopefully that
> > gives enough insight as to what might be happening.
> > 
> > Best Regards,
> > 
> > David
> > 
> > 
> I have attempted to CC ilnux-nvme at lists.infradead.org, but receive a
> immediate notification " 550 Unknown recipient ".? So it just gets bounced
> back to me.

It should have been linux-nvme at lists.infradead.org.

Thanks,
Ming

       reply	other threads:[~2019-07-24  1:45 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <fb510e33-5c81-6d62-fcde-a2989b3a1a8f@tds.net>
     [not found] ` <20190723021928.GF30776@ming.t460p>
     [not found]   ` <4a7ec7aa-f6ee-f9dc-4a17-38f2b169c721@tds.net>
     [not found]     ` <20190723043803.GB13829@ming.t460p>
     [not found]       ` <38cf2485-727b-268d-f42c-6c53b971cb87@tds.net>
     [not found]         ` <5ef41ec4-abb8-90bf-e2eb-8a62f51ad951@tds.net>
2019-07-24  1:45           ` Ming Lei [this message]
     [not found]       ` <20190724213054.GA5921@localhost.localdomain>
2019-07-26 13:30         ` fstrim error - AORUS NVMe Gen4 SSD davidc502

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=20190724014510.GD22421@ming.t460p \
    --to=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