Re: [RFC][PATCH 0/9] Network receive deadlock prevention for NBD

Evgeniy Polyakov wrote:

One must receive a packet to determine if that packet must be dropped
until tricky hardware with header split capabilities or MMIO copying is
used. Peter uses special pool to get data from when system is in OOM (at
least in his latest patchset), so allocations are separated and thus
network code is not affected by OOM condition, which allows to make
forward progress.

Nice executive summary.  Crucial point: you want to say "in reclaim"
not "in OOM".

Yes, right from the beginning the patch set got its sk_buff memory
from a special pool when the system is in reclaim, however the exact
nature of the pool and how/where it is accounted has evolved... mostly
forward.

Regards,

Daniel