Heads-up: two regressions in v4.11-rc series

From	Jesper Dangaard Brouer <brouer@redhat.com>
Newsgroups	linux.kernel
Subject	Heads-up: two regressions in v4.11-rc series
Date	2017-04-20 11:10 +0200
Message-ID	<tygg9-73a-9@gated-at.bofh.it> (permalink)
Organization	linux.* mail to news gateway

Show all headers | View raw

Hi Linus,

Just wanted to give a heads-up on two regressions in 4.11-rc series.

(1) page allocator optimization revert

Mel Gorman and I have been playing with optimizing the page allocator,
but Tariq spotted that we caused a regression for (NIC) drivers that
refill DMA RX rings in softirq context.

The end result was a revert, and this is waiting in AKPMs quilt queue:
 http://ozlabs.org/~akpm/mmots/broken-out/revert-mm-page_alloc-only-use-per-cpu-allocator-for-irq-safe-requests.patch


(2) Busy softirq can cause userspace not to be scheduled

I bisected the problem to a499a5a14dbd ("sched/cputime: Increment
kcpustat directly on irqtime account"). See email thread with
 Subject: Bisected softirq accounting issue in v4.11-rc1~170^2~28
 http://lkml.kernel.org/r/20170328101403.34a82fbf@redhat.com

I don't know the scheduler code well enough to fix this, and will have
to rely others to figure out this scheduler regression.

To make it clear: I'm only seeing this scheduler regression when a
remote host is sending many many network packets, towards the kernel
which keeps NAPI/softirq busy all the time.  A possible hint: tool
"top" only shows this in "si" column, while on v4.10 "top" also blames
"ksoftirqd/N", plus "ps" reported cputime (0:00) seems wrong for ksoftirqd.


-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

Heads-up: two regressions in v4.11-rc series Jesper Dangaard Brouer <brouer@redhat.com> - 2017-04-20 11:10 +0200
  Re: Heads-up: two regressions in v4.11-rc series Frederic Weisbecker <fweisbec@gmail.com> - 2017-04-20 15:30 +0200
  Re: Heads-up: two regressions in v4.11-rc series Mel Gorman <mgorman@techsingularity.net> - 2017-04-20 16:40 +0200
    Re: Heads-up: two regressions in v4.11-rc series Linus Torvalds <torvalds@linux-foundation.org> - 2017-04-21 21:10 +0200
      Re: Heads-up: two regressions in v4.11-rc series Frederic Weisbecker <fweisbec@gmail.com> - 2017-04-21 22:40 +0200

csiph-web