[PATCH] nvme-sysfs: display max_hw_sectors_kb without requiring namespaces

[Caleb Sander]

I agree it would be convenient for the kernel to expose a generic "max
data size" limit for the NVMe controller. For example, nvme-cli
currently pessimistically assumes a controller's maximum data transfer
size is 4 KB when sending Get Log Page commands:
https://github.com/linux-nvme/libnvme/blob/8cdd746b324bd84a0666e7a265aa253dbda9d932/src/nvme/ioctl.c#L330.
Fetching large log pages results in a lot of Get Log Page commands. If
nvme-cli could tell that the controller and kernel support larger data
transfers, it could fetch the entire log page (or a much larger chunk)
in a Get Log Page command.

Best,
Caleb


On Thu, Oct 17, 2024 at 9:46 AM Keith Busch <kbusch at kernel.org> wrote:
>
> On Wed, Oct 16, 2024 at 09:31:08PM +0000, Abhishek Bapat wrote:
> > max_hw_sectors based on DMA optimized limitation") introduced a
> > limitation on the value of max_hw_sectors_kb, restricting it to 128KiB
> > (MDTS = 5). This restricion was implemented to mitigate lockups
> > encountered in high-core count AMD servers.
>
> There are other limits that can constrain transfer sizes below the
> device's MDTS. For example, the driver can only preallocate so much
> space for DMA and SGL descriptors, so 8MB is the current max transfer
> sizes the driver can support, and a device's MDTS can be much bigger
> than that.
>
> Anyway, yeah, I guess having a controller generic way to export this
> sounds like a good idea, but I wonder if the nvme driver is the right
> place to do it. The request_queue has all the limits you need to know
> about, but these are only exported if a gendisk is attached to it.
> Maybe we can create a queue subdirectory to the char dev too.
>