Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1540467

Re: [PATCH 0/8] device-dax: sub-division support

From Jeff Moyer <jmoyer@redhat.com>
Newsgroups linux.kernel
Subject Re: [PATCH 0/8] device-dax: sub-division support
Date 2016-12-12 18:20 +0100
Message-ID <sNCqB-75R-3@gated-at.bofh.it> (permalink)
References <sN5XH-4bM-3@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


Hi, Dan,

Dan Williams <dan.j.williams@intel.com> writes:

>>From [PATCH 6/8] dax: sub-division support:
>
> Device-DAX is a mechanism to establish mappings of performance / feature
> differentiated memory with strict fault behavior guarantees.  With
> sub-division support a platform owner can provision sub-allocations of a
> dax-region into separate devices. The provisioning mechanism follows the
> same scheme as the libnvdimm sub-system in that a 'seed' device is
> created at initialization time that can be resized from zero to become
> enabled.
>
> Unlike the nvdimm sub-system there is no on media labelling scheme
> associated with this partitioning. Provisioning decisions are ephemeral
> / not automatically restored after reboot. While the initial use case of
> device-dax is persistent memory other uses case may be volatile, so the
> device-dax core is unable to assume the underlying memory is pmem.  The
> task of recalling a partitioning scheme or permissions on the device(s)
> is left to userspace.

Can you explain this reasoning in a bit more detail, please?  If you
have specific use cases in mind, that would be helpful.

> For persistent allocations, naming, and permissions automatically
> recalled by the kernel, use filesystem-DAX. For a userspace helper

I'd agree with that guidance if it wasn't for the fact that device dax
was born out of the need to be able to flush dirty data in a safe manner
from userspace.  At best, we're giving mixed guidance to application
developers.

-Jeff

> library and utility for manipulating device-dax instances see libdaxctl
> and the daxctl utility here: https://github.com/pmem/ndctl
>
> ---
>
> Dan Williams (8):
>       dax: add region-available-size attribute
>       dax: add region 'id', 'size', and 'align' attributes
>       dax: register seed device
>       dax: use multi-order radix for resource lookup
>       dax: refactor locking out of size calculation routines
>       dax: sub-division support
>       dax: add / remove dax devices after provisioning
>       dax: add debug for region available_size
>
>
>  drivers/dax/Kconfig |    1 
>  drivers/dax/dax.c   |  747 ++++++++++++++++++++++++++++++++++++++++++++++++---
>  2 files changed, 698 insertions(+), 50 deletions(-)
> _______________________________________________
> Linux-nvdimm mailing list
> Linux-nvdimm@lists.01.org
> https://lists.01.org/mailman/listinfo/linux-nvdimm

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH 0/8] device-dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 2/8] dax: add region 'id', 'size', and 'align' attributes Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 7/8] dax: add / remove dax devices after provisioning Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 5/8] dax: refactor locking out of size calculation routines Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
    Re: [PATCH 5/8] dax: refactor locking out of size calculation  routines Johannes Thumshirn <jthumshirn@suse.de> - 2016-12-14 16:10 +0100
      Re: [PATCH 5/8] dax: refactor locking out of size calculation routines Dan Williams <dan.j.williams@intel.com> - 2016-12-14 17:10 +0100
  [PATCH 3/8] dax: register seed device Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 8/8] dax: add debug for region available_size Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 4/8] dax: use multi-order radix for resource lookup Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 6/8] dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
  [PATCH 1/8] dax: add region-available-size attribute Dan Williams <dan.j.williams@intel.com> - 2016-12-11 07:40 +0100
    Re: [PATCH 1/8] dax: add region-available-size attribute Johannes Thumshirn <jthumshirn@suse.de> - 2016-12-14 15:40 +0100
      Re: [PATCH 1/8] dax: add region-available-size attribute Dan Williams <dan.j.williams@intel.com> - 2016-12-14 17:00 +0100
        Re: [PATCH 1/8] dax: add region-available-size attribute Dan Williams <dan.j.williams@intel.com> - 2016-12-15 07:50 +0100
  Re: [PATCH 0/8] device-dax: sub-division support Jeff Moyer <jmoyer@redhat.com> - 2016-12-12 18:20 +0100
    Re: [PATCH 0/8] device-dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-12 19:50 +0100
      Re: [PATCH 0/8] device-dax: sub-division support Jeff Moyer <jmoyer@redhat.com> - 2016-12-14 00:50 +0100
        Re: [PATCH 0/8] device-dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-14 02:20 +0100
          Re: [PATCH 0/8] device-dax: sub-division support Jeff Moyer <jmoyer@redhat.com> - 2016-12-15 18:00 +0100
            Re: [PATCH 0/8] device-dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-16 00:50 +0100
              Re: [PATCH 0/8] device-dax: sub-division support Dan Williams <dan.j.williams@intel.com> - 2016-12-16 03:50 +0100

csiph-web