On Wed, 11 Jun 2014, Eric Dumazet wrote:

On Wed, 2014-06-11 at 18:55 -0700, dormando wrote:

quoted

I sent the udpkill utility in an off-list mail (in case that got binned by
anyone).

Just threw this patch on top of the other two, on 3.10.42. udpkill's been
running for an hour without fault. I've just put traffic back onto the
machine am leaving udpkill enabled for a while longer.

So, this is an improvement :)

Nice. I suspect regression came with 3.6 ip route cache removal, but I
am lazy to point the exact commit.

Think I owe you a keg at this point. I'll let this bake and we'll see if
the other crashes come back... it'll take a week or two.

I'll have to circle back around to figure out what's gone wrong with 3.14.

Please let me know if there's anything else to test.