Dan Williams
Dan Williams
The fallback to a smaller page size is referring to the eventual dax mappings of files from the filesystem mounted on this device. We'll fix up the documentation and also...
@swdavenport are you still seeing the warning with the v5.3-rc3 kernel? The "kernel BUG at mm/page_alloc.c" issue seems to be unrelated, but nonetheless concerning. Just checking if there are still...
Yes, and that was known at the time the patches went in that ndctl would need to eventually add that support. The current interface puts too much onus on the...
Yes, need better codespell discipline on commit. Care to send a fixup like you did for: https://github.com/pmem/ndctl/pull/138 ?
Fair critique, we'll take a look.
We're planning a verbose option that will include firmware details by default when available. You can get them today with the "--firmware" option if the platform supports the needed _DSM...
I'm able to readily reproduce this. Concurrent ndctl seems to be triggering double-free (double device-unregistration events). Still looking to narrow down all the scenarios where double unregistration occurs.
Proposed fixes here: https://lists.01.org/pipermail/linux-nvdimm/2019-June/021847.html
Also pushed out to libnvdimm-pending: https://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm.git/log/?h=libnvdimm-pending
I'll take a look at recreating the create-namespace crash. As to the other question, the reason we use the pfn UUID instead of the raw namespace UUID is that it...