Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Subject: Re: Spurious instability with NFSoRDMA under moderate load
To:     Chuck Lever III <chuck.lever@oracle.com>
Cc:     Linux NFS Mailing List <linux-nfs@vger.kernel.org>,
        linux-rdma <linux-rdma@vger.kernel.org>
References: <4da3b074-a6be-d83f-ccd4-b151557066aa@rothenpieler.org>
 <72ECF9E1-1F6E-44AF-850C-536BED898DDD@oracle.com>
 <e12c24fd-beaf-31ce-cb49-36ad32bd22b3@rothenpieler.org>
 <daae674a-84d4-de36-336d-693dc582e3ef@rothenpieler.org>
 <9355de20-921c-69e0-e5a4-733b64e125e1@rothenpieler.org>
 <a28b403e-42cf-3189-a4db-86d20da1b7aa@rothenpieler.org>
 <4BA2A532-9063-4893-AF53-E1DAB06095CC@oracle.com>
From:   Timo Rothenpieler <timo@rothenpieler.org>
Message-ID: <c8025457-7376-e1b7-bd6c-e5c6ee5d9ce7@rothenpieler.org>
Date:   Tue, 10 Aug 2021 23:40:47 +0200
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101
 Thunderbird/78.12.0
MIME-Version: 1.0
In-Reply-To: <4BA2A532-9063-4893-AF53-E1DAB06095CC@oracle.com>
Content-Type: multipart/signed; protocol="application/pkcs7-signature"; micalg=sha-256; boundary="------------ms010509000302020909090602"
Precedence: bulk

This is a cryptographically signed message in MIME format.

--------------ms010509000302020909090602
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: quoted-printable

On 10.08.2021 19:17, Chuck Lever III wrote:
>=20
> What I see in this data is that the server is reporting
>=20
>     SEQ4_STATUS_CB_PATH_DOWN
>=20
> and the client is attempting to recover (repeatedly) using
> BIND_CONN_TO_SESSION. But apparently the recovery didn't
> actually work, because the server continues to report a
> callback path problem.
>=20
> [1712389.125641] nfs41_handle_sequence_flag_errors: "10.110.10.200" (cl=
ient ID 6765f8600a675814) flags=3D0x00000001
> [1712389.129264] nfs4_bind_conn_to_session: bind_conn_to_session was su=
ccessful for server 10.110.10.200!
>=20
> [1712389.171953] nfs41_handle_sequence_flag_errors: "10.110.10.200" (cl=
ient ID 6765f8600a675814) flags=3D0x00000001
> [1712389.178361] nfs4_bind_conn_to_session: bind_conn_to_session was su=
ccessful for server 10.110.10.200!
>=20
> [1712389.195606] nfs41_handle_sequence_flag_errors: "10.110.10.200" (cl=
ient ID 6765f8600a675814) flags=3D0x00000001
> [1712389.203891] nfs4_bind_conn_to_session: bind_conn_to_session was su=
ccessful for server 10.110.10.200!
>=20
> I guess it's time to switch to tracing on the server side
> to see if you can nail down why the server's callback
> requests are failing. On your NFS server, run:
>=20
>   # trace-cmd record -e nfsd -e sunrpc -e rpcgss -e rpcrdma
>=20
> at roughly the same point during your test that you captured
> the previous client-side trace.

I wonder if reverting 6820bf77864d on the server, to have an easier way=20
to reproduce this state, would be worth it.

Cause it seems like the actual underlying issue is the inability of the=20
NFS server (and/or client) to reestablish the backchannel if it gets=20
disconnected for whatever reason?

Right now I already rebooted the client, and everything is working=20
again, so I'll have to wait a potentially long time for this to happen=20
again otherwise.


--------------ms010509000302020909090602
Content-Type: application/pkcs7-signature; name="smime.p7s"
Content-Transfer-Encoding: base64
Content-Disposition: attachment; filename="smime.p7s"
Content-Description: S/MIME Cryptographic Signature
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--------------ms010509000302020909090602--