Re: [patch 4/6] mm: merge populate and nopage into fault (fixes nonlinear)

[Bill Irwin <bill.irwin@oracle.com>]

On Wed, 7 Mar 2007 01:29:03 -0800 Bill Irwin <bill.irwin@oracle.com> wrote:
>> Guess what major real-life application not only uses nonlinear daily
>> but would even be very happy to see it extended with non-vma-creating
>> protections and more?

On Wed, Mar 07, 2007 at 01:39:42AM -0800, Andrew Morton wrote:
> uh-oh.  SQL server?

Close enough. ;)


On Wed, 7 Mar 2007 01:29:03 -0800 Bill Irwin <bill.irwin@oracle.com> wrote:
>> It's not terribly typical for things to be
>> truncated while remap_file_pages() is doing its work, though it's been
>> proposed as a method of dynamism. It won't stress remap_file_pages() vs.
>> truncate() in any meaningful way, though, as userspace will be rather
>> diligent about clearing in-use data out of the file offset range to be
>> truncated away anyway, and all that via O_DIRECT.

On Wed, Mar 07, 2007 at 01:39:42AM -0800, Andrew Morton wrote:
> The problem here isn't related to truncate or direct-IO.  It's just
> plain-old MAP_SHARED.  nonlinear VMAs are now using the old-style
> dirty-memory management.  msync() is basically a no-op and the code is
> wildly tricky and pretty much untested.  The chances that we broke it are
> considerable.

This would be of concern for swapping out tmpfs-backed nonlinearly-
mapped files under extreme stress in Oracle's case, though it's rather
typical for it all to be mlock()'d in-core and cases where that's
necessary to be considered grossly underprovisioned. As far as I know,
msync() is not used to manage the nonlinearly-mapped objects, which are
most typically expected to be memory-backed, rendering writeback to
disk of questionable value. Also quite happily, I'm not aware of any
data integrity issues it would explain. Bug though it may be, it
requires a usage model very rarely used by Oracle to trigger, so we've
not run into it.


-- wli