[Drbd-dev] [PATCH] drbd: Avoid GFP_KERNEL allocation from alloc_send_buffer()

[Philipp Reisner]

Am Donnerstag, 25. April 2019, 16:12:54 CEST schrieb Tetsuo Handa:
> On 2019/04/25 22:51, Philipp Reisner wrote:
> >> What happens if nobody volunteers a page when current thread is
> >> calling new_or_recycle_send_buffer_page() ? In other words, may I ask
> >> the reason why GFP_NOIO is safe here?
> > 
> > We always have one buffer page allocated. When the previous send_page()
> > finishes this buffer page gets recycled (it's page count drops to 1).
> > If the system has free memory for DRBD we are happy to use a new page
> > as the next buffer page, speeding up things, as we do not need to wait
> > for previous data to be finally sent.
> > It is guaranteed that we make progress here. Either because we get
> > memory (a) or because the previous buffer becomes reusable (b).
> 
> Then, I think that using GFP_NOIO here is NOT safe because
> alloc_page(GFP_NOIO) can't return NULL even if the previous buffer's page
> count dropped to 1 because current thread will keep looping inside
> __alloc_pages_nodemask() due to 'The "too small to fail" memory-allocation
> rule' after current thread once reached alloc_page(GFP_NOIO).
> 
> If you guarantee that page count drops to 1 by waiting for the previous
> send_page() to finish, GFP_NOWAIT | __GFP_NOWARN or GFP_NOIO |
> __GFP_NORETRY | __GFP_NOWARN should be used instead of GFP_NOIO |
> __GFP_NOWARN.

Ack. Do you want to send a patch that turns the current master into
GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN
?

I will ack and apply it.

cheers.
-- 
LINBIT | Keeping The Digital World Running

DRBD® and LINBIT® are registered trademarks of LINBIT, Austria.