linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: "Martin K. Petersen" <martin.petersen@oracle.com>
To: Max Gurtovoy <maxg@mellanox.com>
Cc: axboe@kernel.dk, sagi@grimberg.me,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	shlomin@mellanox.com, israelr@mellanox.com,
	vladimirk@mellanox.com, linux-nvme@lists.infradead.org,
	idanb@mellanox.com, oren@mellanox.com, kbusch@kernel.org,
	hch@lst.de
Subject: Re: [PATCH 13/15] nvmet: Add metadata/T10-PI support
Date: Tue, 28 Jan 2020 21:32:51 -0500	[thread overview]
Message-ID: <yq14kwf8018.fsf@oracle.com> (raw)
In-Reply-To: <99c92a01-be7b-fd47-3d28-b75e5372c3a6@mellanox.com> (Max Gurtovoy's message of "Mon, 27 Jan 2020 19:17:30 +0200")


Max,

> 2. There is some unclear (to me) behavior in the block layer regarding
> splitting integrity bios. We get guard error over the fabric
> transaction in case we need to split a bio (the error is at the target
> side).
>
> maybe you have an idea how to overcome this ?

I'm working on bringing our data integrity qualification tooling up on
an upstream kernel. The tooling has been stuck in the past for a while
and consequently I haven't tripped over this yet. Will get there soon.

> 3. The maximum_integrity_segments = 1 for NVMe devices, so we can use
> 4096/8=512 integrity sectors before reaching the limit of
> max_integrity_segments. This leads to mdts=6 (256KB) if the bs=512
> . I'm afraid that we might have issues with the fact that the target
> prot_sgl 1 and the NVMe driver set maximum_integrity_segments = 1.

> Therefore, I suggest to limit the mdts per transport (and internally
> check if this ctrl is pi_enabled).

Makes sense. That's kind of what I was fishing for when I asked where
this came from.

> All the above is happening when using submit_bio --> ... --> bio_split
> function that call bio_advance as well (that is called from completion
> context as well). This path is not used in local NVMe IO.

The splitting approach has changed since we cut our last production
kernel. Can't rule out regressions in this area, although I would have
hoped that blktests had caught them.

-- 
Martin K. Petersen	Oracle Linux Engineering

_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  reply	other threads:[~2020-01-29  2:34 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-06 13:37 [PATCH 00/15 V3] nvme-rdma/nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-01-06 13:37 ` [PATCH] nvme-cli/fabrics: Add pi_enable param to connect cmd Max Gurtovoy
2020-01-06 13:37 ` [PATCH 01/15] nvme: Introduce namespace features flag Max Gurtovoy
2020-01-07 18:07   ` Keith Busch
2020-01-08 12:00     ` Max Gurtovoy
2020-01-09  3:11   ` Martin K. Petersen
2020-01-09 10:38     ` Max Gurtovoy
2020-01-09 16:26       ` Keith Busch
2020-01-12  9:40         ` Max Gurtovoy
2020-01-13 20:31           ` Keith Busch
2020-01-14 16:04             ` Max Gurtovoy
2020-01-12  9:40         ` Max Gurtovoy
2020-01-06 13:37 ` [PATCH 02/15] nvme: Enforce extended LBA format for fabrics metadata Max Gurtovoy
2020-01-16 23:53   ` James Smart
2020-01-19 11:20     ` Max Gurtovoy
2020-01-21 17:40       ` James Smart
2020-01-06 13:37 ` [PATCH 03/15] nvme: Introduce max_integrity_segments ctrl attribute Max Gurtovoy
2020-01-09  3:12   ` Martin K. Petersen
2020-01-06 13:37 ` [PATCH 04/15] nvme-fabrics: Allow user enabling metadata/T10-PI support Max Gurtovoy
2020-01-06 13:37 ` [PATCH 05/15] nvme: Introduce NVME_INLINE_PROT_SG_CNT Max Gurtovoy
2020-01-09  3:13   ` Martin K. Petersen
2020-01-06 13:37 ` [PATCH 06/15] nvme-rdma: Introduce nvme_rdma_sgl structure Max Gurtovoy
2020-01-06 13:37 ` [PATCH 07/15] nvme-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-01-06 13:37 ` [PATCH 08/15] nvmet: Prepare metadata request Max Gurtovoy
2020-01-06 13:37 ` [PATCH 09/15] nvmet: Add metadata characteristics for a namespace Max Gurtovoy
2020-01-09  3:16   ` Martin K. Petersen
2020-01-06 13:37 ` [PATCH 10/15] nvmet: Rename nvmet_rw_len to nvmet_rw_data_len Max Gurtovoy
2020-01-09  3:17   ` Martin K. Petersen
2020-01-06 13:37 ` [PATCH 11/15] nvmet: Rename nvmet_check_data_len to nvmet_check_transfer_len Max Gurtovoy
2020-01-09  3:19   ` Martin K. Petersen
2020-01-06 13:37 ` [PATCH 12/15] nvme: Add Metadata Capabilities enumerations Max Gurtovoy
2020-01-06 13:37 ` [PATCH 13/15] nvmet: Add metadata/T10-PI support Max Gurtovoy
2020-01-09  3:24   ` Martin K. Petersen
2020-01-27 17:17     ` Max Gurtovoy
2020-01-29  2:32       ` Martin K. Petersen [this message]
2020-01-17 16:46   ` James Smart
2020-01-19 13:47     ` Max Gurtovoy
2020-01-06 13:37 ` [PATCH 14/15] nvmet: Add metadata support for block devices Max Gurtovoy
2020-01-06 13:37 ` [PATCH 15/15] nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-01-09  3:29   ` Martin K. Petersen
  -- strict thread matches above, loose matches on Subject: below --
2020-04-28 13:11 [PATCH 00/15 V6] nvme-rdma/nvmet-rdma: " Max Gurtovoy
2020-04-28 13:11 ` [PATCH 13/15] nvmet: add " Max Gurtovoy
2020-05-01 15:58   ` Christoph Hellwig
2020-05-01 16:19   ` Christoph Hellwig
2019-11-05 16:20 [PATCH 00/15] nvme-rdma/nvmet-rdma: Add " Max Gurtovoy
2019-11-05 16:20 ` [PATCH 13/15] nvmet: " Max Gurtovoy

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=yq14kwf8018.fsf@oracle.com \
    --to=martin.petersen@oracle.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=idanb@mellanox.com \
    --cc=israelr@mellanox.com \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=maxg@mellanox.com \
    --cc=oren@mellanox.com \
    --cc=sagi@grimberg.me \
    --cc=shlomin@mellanox.com \
    --cc=vladimirk@mellanox.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).