On Fri, 18 Nov 2011 22:20:48 +0100, sandeep patil [off-list ref] wrote:

I am running a simple test to allocate contiguous regions and write a log on
in a file on sdcard simultaneously. I can reproduce this migration failure 100%
times with it.
when I tracked the pages that failed to migrate, I found them on the
buffer head lru
list with a reference held on the buffer_head in the page, which
causes drop_buffers()
to fail.

So, i guess my question is, until all the migration failures are
tracked down and fixed,
is there a plan to retry the contiguous allocation from a new range in
the CMA region?

No.  Current CMA implementation will stick to the same range of pages also
on consequent allocations of the same size.

-- 
Best regards,                                         _     _
.o. | Liege of Serenely Enlightened Majesty of      o' \,=./ `o
..o | Computer Science,  Micha? ?mina86? Nazarewicz    (o o)
ooo +----<email/xmpp: mpn@google.com>--------------ooO--(_)--Ooo--