Make NVME shutdown two-pass - Version 4

[Jeremy Allison]

This code is only exercised when the PCI shutdown function is called -
shutting down the VM is
how I've been testing it). I don't see a way of invoking that in blktest.

On Wed, Jan 3, 2024 at 8:48 PM Chaitanya Kulkarni <chaitanyak at nvidia.com> wrote:
>
> On 1/3/24 13:04, Jeremy Allison wrote:
> > This is version 4 of a patchset originally written by
> > Tanjore Suresh <tansuresh at google.com> to make shutdown
> > of nvme devices two-pass.
> >
> > Changes from version 3:
> >
> > 1). Removed duplicate setting of ctrl->ctrl_config in
> > nvme completion function. Noticed by Sagi Grimberg <sagi at grimberg.me>
> >
> > 2). Removed intermediate function nvme_wait_for_shutdown_cmpl(),
> > folded this code directly into nvme_shutdown_wait() by
> > exporting nvme_wait_ready() from drivers/nvme/host/core.c.
> > Requested by Sagi Grimberg <sagi at grimberg.me>
> >
> > -------------------------------------------------------------
> > Currently the Linux nvme driver shutdown code steps
> > through each connected drive, sets the NVME_CC_SHN_NORMAL
> > (normal shutdown) flag and then polls the given drive
> > waiting for the response NVME_CSTS_SHST_CMPLT flag
> > (shutdown complete).
> >
> > Each drive is taking around 13 seconds to respond to this.
> >
> > The customer has 20+ drives on the box so this time adds
> > up on shutdown when the nvme driver is being shut down.
> >
> > This patchset changes shutdown to proceed in parallel,
> > so the NVME_CC_SHN_NORMAL (normal shutdown) flag is
> > sent to all drives first, and then it polls waiting
> > for the NVME_CSTS_SHST_CMPLT flag (shutdown complete)
> > for all drives.
> >
> > In the specific customer case it reduces the NVME
> > shutdown time from over 300 seconds to around 15
> > seconds.
> > -------------------------------------------------------------
> >
> > Thanks for your consideration,
> >
> > Jeremy Allison.
> > CIQ / Samba Team.
> >
> >
> >
>
> Is there any plan to add a blktests for this or this needs a special setup
> for testing that cannot be done with blktest ?
>
> -ck
>
>