Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1692963

Re: commit 16ecba59 breaks 82574L under heavy load.

Show all headers | View raw

On Wed, Jul 19, 2017 at 05:07:47PM -0700, Benjamin Poirier wrote:
> Are you sure about this? In my testing, while triggering the overrun
> with the msleep, I read ICR when entering e1000_msix_other() and RXO is
> consistently set.

I had thousands of calls to e1000_msix_other where the only bit set
was OTHER.

I don't know if the cause is overruns, it just seems plausible.

> I'm working on a patch that uses that fact to handle the situation and
> limit the interrupt.

Excellent.

Running in MSI mode rather than MSI-X seems to not have the problem of
unexpected interrupts, but has other issues (such as loosing the IRQ
affinity setting if you do ifconfig down;ifconfig up on the interface,
which does not happen in MSI-X's case.)  That's rather annoying as you
can't set the affinity before bringing up the interface which is rather
undesirable.

-- 
Len Sorensen

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

Thread

commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-18 16:40 +0200
  Re: commit 16ecba59 breaks 82574L under heavy load. Benjamin Poirier <bpoirier@suse.com> - 2017-07-19 01:20 +0200
    Re: commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-19 16:20 +0200
      Re: commit 16ecba59 breaks 82574L under heavy load. Benjamin Poirier <bpoirier@suse.com> - 2017-07-20 02:10 +0200
        Re: commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-20 16:10 +0200
          Re: commit 16ecba59 breaks 82574L under heavy load. Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 01:50 +0200
            Re: commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-21 17:30 +0200
              Re: commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-21 18:10 +0200
                [PATCH 4/5] e1000e: Separate signaling for link check/link up Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 20:40 +0200
                Re: [PATCH 4/5] e1000e: Separate signaling for link check/link up lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-21 21:00 +0200
                [PATCH 5/5] e1000e: Avoid receiver overrun interrupt bursts Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 20:40 +0200
                Re: [PATCH 5/5] e1000e: Avoid receiver overrun interrupt bursts lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-21 20:50 +0200
                [PATCH 1/5] e1000e: Fix error path in link detection Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 20:40 +0200
                [PATCH 2/5] e1000e: Fix wrong comment related to link detection Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 20:40 +0200
                [PATCH 3/5] e1000e: Fix return value test Benjamin Poirier <bpoirier@suse.com> - 2017-07-21 20:40 +0200
            Re: commit 16ecba59 breaks 82574L under heavy load. lsorense@csclub.uwaterloo.ca (Lennart Sorensen) - 2017-07-21 21:10 +0200
            Re: commit 16ecba59 breaks 82574L under heavy load. Philip Prindeville <philipp_subx@redfish-solutions.com> - 2017-07-25 00:00 +0200

csiph-web