Re: [PATCH] vmxnet3: fix starving rx ring when alloc_skb fails

From: Ben Hutchings <redacted>
Date: Fri, 17 Jun 2011 13:14:20 +0100

But this means the driver drops received packets as soon as there is an
allocation failure, rather than only if there are repeated failures.  I
don't see how that's preferable.

Because it decreases the possibility of RX ring starvation.

If you get one allocation failure during a NAPI poll run, and you're
proabably processing a set of packets, they are all going to fail.