From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
To: "Surabhi Gogte (she/her)" <sgogte@purestorage.com>
Cc: Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@kernel.dk>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
mkhalfella@purestorage.com, randyj@purestorage.com,
adailey@purestorage.com, Hannes Reinecke <hare@kernel.org>,
dwagner@suse.de
Subject: Re: [PATCH v4 3/3] nvme-tcp: parallelize I/O queue allocation and startup
Date: Tue, 17 Nov 2026 20:11:32 +0900 [thread overview]
Message-ID: <avwxyzFIASk10lMI@shinmob> (raw)
In-Reply-To: <CAMof9cX9TNaXdL1ugdnCwxVG1Us8V-=c=Uk+YVKsMwFEYR7Vvg@mail.gmail.com>
On Nov 16, 2026 / 08:59, Surabhi Gogte (she/her) wrote:
[...]
> Hi Shin'ichiro, I ran bltkests with ktls 1.5.0. It contains the tlshd
> commit 3a6658e
> ("tlshd: Link the NFS keyrings per handshake instead of at startup")
> which fixes the keyring race during the handshake. Both tests 62 and
> 63 pass with it.
> Can you retest with that version to see if the issue persists? Can you
> also share the kernel logs of the failure.
>
> Ref: https://lore.kernel.org/linux-nvme/CAMof9cU5s0ck20fcSAYSvK-xpcP5_Hv2BmN20Bh3btpLum7THg@mail.gmail.com/
Hi Surabhi, thanks for the response. Ah, the nvme/062 and 063 failures were
already reported, so I should have tried ktls-utils 1.5.0.
I uninstalled the Fedora ktls-utils package 1.4.0, and compiled ktls-utils 1.5.0
from source code [a]. With this, I tsill observe the failures [b]. I also share
dmesg for your reference [c].
[a] ktls-utils, nvme and kernel versions
$ /usr/local/sbin/tlshd --version
tlshd, built from ktls-utils 1.5.0 on Nov 17 2026 09:52:23
$ nvme --version
nvme version 3.2 (git v3.2)
libnvme version 3.2 (git v3.2)
$ uname -a
Linux testnode1 7.4.0-rc3 #501 SMP PREEMPT_DYNAMIC Mon Nov 16 14:47:04 JST 2026 x86_64 GNU/Linux
[b] nvme/062, 063 failures
nvme/062 (tr=tcp) (Create TLS-encrypted connections) [failed]
runtime 12.978s ... 14.855s
--- tests/nvme/062.out 2026-11-09 20:12:01.056000000 +0900
+++ /home/shin/Blktests/blktests/results/nodev_tr_tcp/nvme/062.out.bad 2026-11-17 19:51:06.015000000 +0900
@@ -1,6 +1,10 @@
Running nvme/062
Test unencrypted connection w/ tls not required
Test encrypted connection w/ tls not required
+FAIL: nvme connect return error code
+WARNING: connection is not encrypted
Test unencrypted connection w/ tls required (should fail)
Test encrypted connection w/ tls required
...
(Run 'diff -u tests/nvme/062.out /home/shin/Blktests/blktests/results/nodev_tr_tcp/nvme/062.out.bad' to see the entire diff)
nvme/063 (tr=tcp) (Create authenticated TCP connections with secure concatenation)
runtime 5.639s ...
WARNING: Test did not clean up port: 0
nvme/063 (tr=tcp) (Create authenticated TCP connections with secure concatenation) [failed]
runtime 5.639s ... 5.820sost: nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349
--- tests/nvme/063.out 2026-11-09 20:12:01.060000000 +0900
+++ /home/shin/Blktests/blktests/results/nodev_tr_tcp/nvme/063.out.bad 2026-11-17 19:51:26.054000000 +0900
@@ -1,5 +1,4 @@
Running nvme/063
Test secure concatenation with SHA256
-Reset controller
-Test secure concatenation with SHA384
-Test complete
+FAIL: nvme connect return error code
[c] dmesg
[ 151.189255] [ T2481] loop: module loaded
[ 163.048150] [ T2446] run blktests nvme/062 at 2026-11-17 19:50:50.958502092
[ 163.352484] [ T2568] nvmet: adding nsid 1 to subsystem blktests-subsystem-1
[ 163.400186] [ T2571] nvmet: Allow non-TLS connections while TLS1.3 is enabled
[ 163.418639] [ T2574] nvmet_tcp: enabling port 0 (127.0.0.1:4420)
[ 163.559515] [ T321] nvmet: Created nvm controller 1 for subsystem blktests-subsystem-1 for NQN nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349.
[ 163.570048] [ T2581] nvme nvme5: creating 4 I/O queues.
[ 163.571893] [ T2581] nvme nvme5: mapped 4/0/0 default/read/poll queues.
[ 163.581555] [ T2581] nvme nvme5: new ctrl: NQN "blktests-subsystem-1", addr 127.0.0.1:4420, hostnqn: nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349
[ 164.430504] [ T2635] nvme nvme5: Removing ctrl: NQN "blktests-subsystem-1"
[ 164.701380] [ T2653] nvme nvme5: queue 0: failed to start TLS: -3
[ 164.708096] [ T51] nvmet_tcp: failed to allocate queue, error -107
[ 171.587415] [ T2900] nvmet: adding nsid 1 to subsystem blktests-subsystem-1
[ 171.653183] [ T2906] nvmet_tcp: enabling port 0 (127.0.0.1:4420)
[ 171.793463] [ T51] nvmet_tcp: failed to start TLS, err=-3
[ 171.804442] [ T51] nvmet_tcp: failed to allocate queue, error 0
[ 171.807577] [ T2913] nvme_tcp: queue 0: failed to receive icresp, error -104
[ 172.080585] [ T2934] nvme nvme5: queue 0: failed to start TLS: -3
[ 172.080739] [ T51] nvmet_tcp: failed to start TLS, err=-3
[ 172.085529] [ T51] nvmet_tcp: failed to allocate queue, error 0
[ 179.988608] [ T3283] loop: module loaded
[ 192.204777] [ T3248] run blktests nvme/063 at 2026-11-17 19:51:20.118835914
[ 192.524477] [ T3374] nvmet: adding nsid 1 to subsystem blktests-subsystem-1
[ 192.573747] [ T3377] nvmet: Allow non-TLS connections while TLS1.3 is enabled
[ 192.594083] [ T3380] nvmet_tcp: enabling port 0 (127.0.0.1:4420)
[ 192.753377] [ T29] nvmet: Created nvm controller 1 for subsystem blktests-subsystem-1 for NQN nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349 with DH-HMAC-CHAP.
[ 192.768611] [ T51] nvme nvme5: qid 0: authenticated with hash hmac(sha256) dhgroup ffdhe2048
[ 192.769604] [ T3387] nvme nvme5: qid 0: authenticated
[ 192.774532] [ T3387] nvme nvme5: queue 0: failed to start TLS: -3
[ 192.785871] [ T92] nvmet_tcp: failed to allocate queue, error -107
next prev parent reply other threads:[~2026-11-17 11:11 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-22 20:07 [PATCH v4 0/3] nvme-tcp: parallelize I/O setup queue in connect Surabhi Gogte
2026-09-22 20:07 ` [PATCH v4 1/3] nvme-tcp: store and use the caller's network namespace Surabhi Gogte
2026-09-22 20:07 ` [PATCH v4 2/3] nvme-tcp: refactor I/O queue setup path Surabhi Gogte
2026-09-22 20:07 ` [PATCH v4 3/3] nvme-tcp: parallelize I/O queue allocation and startup Surabhi Gogte
2026-10-18 12:25 ` Shin'ichiro Kawasaki
2026-10-20 20:48 ` Surabhi Gogte (she/her)
2026-11-15 11:36 ` Shin'ichiro Kawasaki
2026-11-16 16:59 ` Surabhi Gogte (she/her)
2026-11-17 11:11 ` Shin'ichiro Kawasaki [this message]
2026-10-26 10:57 ` Martin Belanger
2026-10-30 21:25 ` Surabhi Gogte (she/her)
2026-11-02 7:15 ` Hannes Reinecke
2026-11-13 18:02 ` Surabhi Gogte (she/her)
2026-11-02 11:16 ` Martin Belanger
2026-10-13 15:33 ` [PATCH v4 0/3] nvme-tcp: parallelize I/O setup queue in connect 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=avwxyzFIASk10lMI@shinmob \
--to=shinichiro.kawasaki@wdc.com \
--cc=adailey@purestorage.com \
--cc=axboe@kernel.dk \
--cc=dwagner@suse.de \
--cc=hare@kernel.org \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=mkhalfella@purestorage.com \
--cc=randyj@purestorage.com \
--cc=sagi@grimberg.me \
--cc=sgogte@purestorage.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