From: Sagi Grimberg <sagi@grimberg.me>
To: Leon Romanovsky <leon@kernel.org>
Cc: Patrisious Haddad <phaddad@nvidia.com>,
Christoph Hellwig <hch@lst.de>,
Israel Rukshin <israelr@nvidia.com>,
Linux-nvme <linux-nvme@lists.infradead.org>,
linux-rdma@vger.kernel.org,
Michael Guralnik <michaelgur@nvidia.com>,
Maor Gottlieb <maorg@nvidia.com>,
Max Gurtovoy <mgurtovoy@nvidia.com>
Subject: Re: [PATCH rdma-next 4/4] nvme-rdma: add more error details when a QP moves to an error state
Date: Wed, 7 Sep 2022 18:16:05 +0300 [thread overview]
Message-ID: <ac268c86-c013-5cc5-5e1c-71ee90111d8f@grimberg.me> (raw)
In-Reply-To: <YxiTxJvDWPaB9iMf@unreal>
>>> From: Israel Rukshin <israelr@nvidia.com>
>>>
>>> Add debug prints for fatal QP events that are helpful for finding the
>>> root cause of the errors. The ib_get_qp_err_syndrome is called at
>>> a work queue since the QP event callback is running on an
>>> interrupt context that can't sleep.
>>>
>>> Signed-off-by: Israel Rukshin <israelr@nvidia.com>
>>> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
>>> Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
>>
>> What makes nvme-rdma special here? Why do you get this in
>> nvme-rdma and not srp/iser/nfs-rdma/rds/smc/ipoib etc?
>>
>> This entire code needs to move to the rdma core instead
>> of being leaked to ulps.
>
> We can move, but you will lose connection between queue number,
> caller and error itself.
That still doesn't explain why nvme-rdma is special.
In any event, the ulp can log the qpn so the context can be interrogated
if that is important.
next prev parent reply other threads:[~2022-09-07 15:16 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-07 11:37 [PATCH rdma-next 0/4] Provide more error details when a QP moves to Patrisious Haddad
2022-09-07 11:37 ` [PATCH rdma-next 1/4] net/mlx5: Introduce CQE error syndrome Patrisious Haddad
2022-09-07 11:37 ` [PATCH rdma-next 2/4] RDMA/core: Introduce ib_get_qp_err_syndrome function Patrisious Haddad
2022-09-07 11:37 ` [PATCH rdma-next 3/4] RDMA/mlx5: Implement ib_get_qp_err_syndrome Patrisious Haddad
2022-09-07 11:38 ` [PATCH rdma-next 4/4] nvme-rdma: add more error details when a QP moves to an error state Patrisious Haddad
2022-09-07 12:02 ` Christoph Hellwig
2022-09-07 12:11 ` Leon Romanovsky
2022-09-07 12:34 ` Sagi Grimberg
2022-09-07 12:51 ` Leon Romanovsky
2022-09-07 15:16 ` Sagi Grimberg [this message]
2022-09-07 15:18 ` Christoph Hellwig
2022-09-07 17:39 ` Leon Romanovsky
2022-11-01 9:12 ` Mark Zhang
2022-11-02 1:56 ` Mark Zhang
2022-09-08 7:55 ` Patrisious Haddad
2022-09-07 17:29 ` Leon Romanovsky
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=ac268c86-c013-5cc5-5e1c-71ee90111d8f@grimberg.me \
--to=sagi@grimberg.me \
--cc=hch@lst.de \
--cc=israelr@nvidia.com \
--cc=leon@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-rdma@vger.kernel.org \
--cc=maorg@nvidia.com \
--cc=mgurtovoy@nvidia.com \
--cc=michaelgur@nvidia.com \
--cc=phaddad@nvidia.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).