On Fri, 19 Oct 2018 17:59:21 +1030, Jonathan Woithe wrote:
> On 10/18/18 08:15, Jonathan Woithe wrote:
> > On Thu, Oct 18, 2018 at 08:03:32AM +0200, Heiner Kallweit wrote:
> > > Proposed fix is here:
> > > https://patchwork.ozlabs.org/patch/985014/
> > > Would be good if you could test it. Thanks!
On 10/17/18 22:07, Holger Hoffstätte wrote:
On 10/17/18 21:27, Heiner Kallweit wrote:
(snip)
Good to know. What's your kernel version and RTL8168 chip version?
Regarding the chip version the dmesg line with the XID would be relevant.
4.18.15 + PDS (custom CPU scheduler) + cherry pickings from
On Thu, Oct 18, 2018 at 01:52:33PM +0200, Holger Hoffstätte wrote:
> On 10/18/18 08:15, Jonathan Woithe wrote:
> > On Thu, Oct 18, 2018 at 08:03:32AM +0200, Heiner Kallweit wrote:
> > > Proposed fix is here:
> > > https://patchwork.ozlabs.org/patch/985014/
> > > Would be good if you could test it.
On 10/18/18 08:15, Jonathan Woithe wrote:
On Thu, Oct 18, 2018 at 08:03:32AM +0200, Heiner Kallweit wrote:
On 18.10.2018 07:58, Jonathan Woithe wrote:
On Thu, Oct 18, 2018 at 01:30:51AM +0200, Francois Romieu wrote:
Holger Hoffstätte :
[...]
The bug will induce delayed rx processing when a sp
From: Heiner Kallweit
Date: Thu, 18 Oct 2018 07:58:52 +0200
> On 18.10.2018 07:21, David Miller wrote:
>> From: Francois Romieu
>> Date: Thu, 18 Oct 2018 01:30:45 +0200
>>
>>> Heiner Kallweit :
>>> [...]
This issue has been there more or less forever (at least it exists in
3.16 alrea
On Thu, Oct 18, 2018 at 08:03:32AM +0200, Heiner Kallweit wrote:
> On 18.10.2018 07:58, Jonathan Woithe wrote:
> > On Thu, Oct 18, 2018 at 01:30:51AM +0200, Francois Romieu wrote:
> >> Holger Hoffstätte :
> >> [...]
> >> The bug will induce delayed rx processing when a spike of "load" is
> >> foll
On Thu, Oct 18, 2018 at 01:30:51AM +0200, Francois Romieu wrote:
> Holger Hoffstätte :
> [...]
> > I continued to use the BQL patch in my private tree after it was reverted
> > and also had occasional timeouts, but *only* after I started playing
> > with ethtool to change offload settings. Without
On 18.10.2018 07:58, Jonathan Woithe wrote:
> On Thu, Oct 18, 2018 at 01:30:51AM +0200, Francois Romieu wrote:
>> Holger Hoffstätte :
>> [...]
>>> I continued to use the BQL patch in my private tree after it was reverted
>>> and also had occasional timeouts, but *only* after I started playing
>>>
On 18.10.2018 07:21, David Miller wrote:
> From: Francois Romieu
> Date: Thu, 18 Oct 2018 01:30:45 +0200
>
>> Heiner Kallweit :
>> [...]
>>> This issue has been there more or less forever (at least it exists in
>>> 3.16 already), so I can't provide a "Fixes" tag.
>>
>> Hardly forever. It fixes
From: Francois Romieu
Date: Thu, 18 Oct 2018 01:30:45 +0200
> Heiner Kallweit :
> [...]
>> This issue has been there more or less forever (at least it exists in
>> 3.16 already), so I can't provide a "Fixes" tag.
>
> Hardly forever. It fixes da78dbff2e05630921c551dbbc70a4b7981a8fff.
I don't s
Holger Hoffstätte :
[...]
> I continued to use the BQL patch in my private tree after it was reverted
> and also had occasional timeouts, but *only* after I started playing
> with ethtool to change offload settings. Without offloads or the BQL patch
> everything has been rock-solid since then.
> T
Heiner Kallweit :
[...]
> This issue has been there more or less forever (at least it exists in
> 3.16 already), so I can't provide a "Fixes" tag.
Hardly forever. It fixes da78dbff2e05630921c551dbbc70a4b7981a8fff.
--
Ueimor
On 10/17/18 21:27, Heiner Kallweit wrote:
(snip)
Good to know. What's your kernel version and RTL8168 chip version?
Regarding the chip version the dmesg line with the XID would be relevant.
4.18.15 + PDS (custom CPU scheduler) + cherry pickings from mainline.
Applied both the original patch in
On 17.10.2018 21:11, Holger Hoffstätte wrote:
> On 10/17/18 20:12, Heiner Kallweit wrote:
>> On 16.10.2018 23:17, Holger Hoffstätte wrote:
>>> On 10/16/18 22:37, Heiner Kallweit wrote:
rtl_rx() and rtl_tx() are called only if the respective bits are set
in the interrupt status register. U
On 10/17/18 20:12, Heiner Kallweit wrote:
On 16.10.2018 23:17, Holger Hoffstätte wrote:
On 10/16/18 22:37, Heiner Kallweit wrote:
rtl_rx() and rtl_tx() are called only if the respective bits are set
in the interrupt status register. Under high load NAPI may not be
able to process all data (work
or at least the old dmesg
logs, I'd appreciate if you could let me know the quoted line from
dmesg output.
Thanks a lot,
Heiner
Forwarded Message
Subject: Re: [PATCH net] r8169: fix NAPI handling under high load
Date: Wed, 17 Oct 2018 20:12:48 +0200
From: Heiner Kallweit
On 16.10.2018 23:17, Holger Hoffstätte wrote:
> On 10/16/18 22:37, Heiner Kallweit wrote:
>> rtl_rx() and rtl_tx() are called only if the respective bits are set
>> in the interrupt status register. Under high load NAPI may not be
>> able to process all data (work_done == budget) and it will schedu
On 10/16/2018 5:23 PM, Eric Dumazet wrote:
>
>
> On 10/16/2018 04:08 PM, Florian Fainelli wrote:
>
>> I had started doing that about a month ago in light of the ixbge
>> ndo_poll_controller vs. napi problem, but have not had time to submit
>> that series yet:
>>
>> https://github.com/ffainell
On 10/16/2018 04:08 PM, Florian Fainelli wrote:
> I had started doing that about a month ago in light of the ixbge
> ndo_poll_controller vs. napi problem, but have not had time to submit
> that series yet:
>
> https://github.com/ffainelli/linux/commits/napi-check
>
> feel free to piggy back o
On 10/16/2018 04:03 PM, Stephen Hemminger wrote:
> Many drivers have buggy usage of napi_complete_done.
>
> Might even be worth forcing all network drivers to check the return
> value. But fixing 150 broken drivers will be a nuisance.
>
> diff --git a/include/linux/netdevice.h b/include/linux
On 10/16/2018 03:17 PM, Stephen Hemminger wrote:
> On Tue, 16 Oct 2018 22:37:31 +0200
> Heiner Kallweit wrote:
>
>> rtl_rx() and rtl_tx() are called only if the respective bits are set
>> in the interrupt status register. Under high load NAPI may not be
>> able to process all data (work_done =
On 10/16/2018 04:03 PM, Stephen Hemminger wrote:
> On Tue, 16 Oct 2018 23:17:31 +0200
> Holger Hoffstätte wrote:
>
>> On 10/16/18 22:37, Heiner Kallweit wrote:
>>> rtl_rx() and rtl_tx() are called only if the respective bits are set
>>> in the interrupt status register. Under high load NAPI may n
On Tue, 16 Oct 2018 23:17:31 +0200
Holger Hoffstätte wrote:
> On 10/16/18 22:37, Heiner Kallweit wrote:
> > rtl_rx() and rtl_tx() are called only if the respective bits are set
> > in the interrupt status register. Under high load NAPI may not be
> > able to process all data (work_done == budget)
On Tue, 16 Oct 2018 22:37:31 +0200
Heiner Kallweit wrote:
> rtl_rx() and rtl_tx() are called only if the respective bits are set
> in the interrupt status register. Under high load NAPI may not be
> able to process all data (work_done == budget) and it will schedule
> subsequent calls to the poll
On 10/16/18 22:37, Heiner Kallweit wrote:
rtl_rx() and rtl_tx() are called only if the respective bits are set
in the interrupt status register. Under high load NAPI may not be
able to process all data (work_done == budget) and it will schedule
subsequent calls to the poll callback.
rtl_ack_event
rtl_rx() and rtl_tx() are called only if the respective bits are set
in the interrupt status register. Under high load NAPI may not be
able to process all data (work_done == budget) and it will schedule
subsequent calls to the poll callback.
rtl_ack_events() however resets the bits in the interrupt
26 matches
Mail list logo
