[PATCH 3/3] nvme-tcp: fix I/O stalls on congested sockets

[Kamaljit Singh]

Hi Hannes,

On 5/6/25 11:05, Hannes Reinecke wrote:

>Can you please retest with the patchset '[PATCHv5 0/2] nvme-tcp: fixup
>I/O stall on congested sockets' _only_ ?
>(on top of nvme-6.16 latest, of course).
>I think I _should_ have included all the suggestions floating here,
>but we need to have confirmation.

I've built the kernel against the latest of nvme-6.16 branch along with
these patches. Its with test now. Will let you know when we get some
results back.

0. [PATCHv5 0/2] nvme-tcp: fixup I/O stall on congested sockets - Apr 29, 01:18
    Hannes Reinecke (2):
      nvme-tcp: sanitize request list handling
      nvme-tcp: fix I/O stalls on congested sockets

1. [PATCH 1/2] nvme-tcp: sanitize request list handling - Apr 29, 02:31
2. [PATCH 2/2] nvme-tcp: fix I/O stalls on congested sockets - Apr 29, 01:18

Meanwhile, quick question, is there a known issue in cloning from this
repo? I'm seeing super slow response, which eventually timesout. Had to
try multiple times over several hours.

$ git clone git://git.infradead.org/nvme.git  linux-nvme-6.16
    Cloning into 'linux-nvme-6.16'...
    remote: Enumerating objects: 10795230, done.
    remote: Counting objects: 100% (333577/333577), done.
    remote: Compressing objects: 100% (99866/99866), done.
    fatal: read error: Operation timed out 76.01 KiB | 1024 bytes/s
    fatal: early EOF
    fatal: fetch-pack: invalid index-pack output


Even a git pull --rebase into an older clone was failing to refresh
remotes & show the nvme-6.16 branch.

Thanks,
Kamaljit Singh