Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 24 Apr 2019 14:34:15 -0700
From:   Davidlohr Bueso <dave@stgolabs.net>
To:     Eric Wong <e@80x24.org>
Cc:     linux-kernel@vger.kernel.org, Omar Kilani <omar.kilani@gmail.com>
Subject: Re: Strange issues with epoll since 5.0
Message-ID: <20190424213415.7muqd4tkuxsgwigz@linux-r8p5>
References: <CA+8F9hicnF=kvjXPZFQy=Pa2HJUS3JS+G9VswFHNQQynPMHGVQ@mail.gmail.com>
 <20190424193903.swlfmfuo6cqnpkwa@dcvr>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Disposition: inline
In-Reply-To: <20190424193903.swlfmfuo6cqnpkwa@dcvr>
User-Agent: NeoMutt/20180323
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 24 Apr 2019, Eric Wong wrote:

>Omar Kilani <omar.kilani@gmail.com> wrote:
>> Hi there,
>>
>> I???m still trying to piece together a reproducible test that triggers
>> this, but I wanted to post in case someone goes ???hmmm... change X
>> might have done this???.
>
>Maybe Davidlohr knows, since he's responsible for most of the
>epoll changes in 5.0.

Not really, I have not been made aware of any issues until now.

>
>> Basically, something???s broken (or at least, has changed enough to
>> cause problems in user space) in epoll since 5.0. It???s still broken in
>> 5.1-rc5.
>>
>> It doesn???t happen 100% of the time. It???s sort of hard to pin down but
>> I???ve observed the following:
>>
>> * nginx not accepting connections under load
>> * A java app which uses netty / NIO having strange writability
>> semantics on channels, which confuses netty / java enough to not
>> properly flush written data on the socket.
>>
>> I went and tested these Linux kernels:
>>
>> 4.20.17
>> 4.19.32
>> 4.14.111
>>
>> And the issue(s) do not show up there.
>>
>> I???m still actively chasing this up, and will report back ??? I haven???t
>> touched kernel code in 15 years so I???m a little rusty. :)

A bisection and/or workload that triggers the issue would be great to
see what's going on.

Thanks,
Davidlohr