On Fri 04-08-17 14:55:06, Doug Ledford wrote:
> On Wed, 2017-08-02 at 14:17 -0700, Andrew Morton wrote:
> > On Wed, 2 Aug 2017 13:44:57 -0400 Jonathan Toppins <jtoppins@redhat.
> > com> wrote:
> > > The RDMA subsystem can generate several thousand of these messages
> > > per
> > > second eventually leading to a kernel crash. Ratelimit these
> > > messages
> > > to prevent this crash.
> > Well... why are all these EBUSY's occurring? It sounds inefficient
> > (at
> > least) but if it is expected, normal and unavoidable then perhaps we
> > should just remove that message altogether?
> I don't have an answer to that question. To be honest, I haven't
> looked real hard. We never had this at all, then it started out of the
> blue, but only on our Dell 730xd machines (and it hits all of them),
> but no other classes or brands of machines. And we have our 730xd
> machines loaded up with different brands and models of cards (for
> instance one dedicated to mlx4 hardware, one for qib, one for mlx5, an
> ocrdma/cxgb4 combo, etc), so the fact that it hit all of the machines
> meant it wasn't tied to any particular brand/model of RDMA hardware.
> To me, it always smelled of a hardware oddity specific to maybe the
> CPUs or mainboard chipsets in these machines, so given that I'm not an
> mm expert anyway, I never chased it down.
It would certainly be good to chase this down. I do not object to
ratelimiting, it is much better than having a non-bootable system but
this doesn't solve the underlying problem.
> A few other relevant details: it showed up somewhere around 4.8/4.9 or
> thereabouts. It never happened before, but the prinkt has been there
> since the 3.18 days, so possibly the test to trigger this message was
> changed, or something else in the allocator changed such that the
> situation started happening on these machines?
Is this still the case with the current Linus tree? We have had a fix
424f6c4818bb ("mm: alloc_contig: re-allow CMA to compact FS pages")
which made it into 4.10