From: "Holger Hoffstätte" <holger@applied-asynchrony.com>
To: Heiner Kallweit <hkallweit1@gmail.com>,
David Miller <davem@davemloft.net>,
Realtek linux nic maintainers <nic_swsd@realtek.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>
Subject: Re: [PATCH net] r8169: fix NAPI handling under high load
Date: Tue, 16 Oct 2018 23:17:31 +0200 [thread overview]
Message-ID: <ada39488-8e9c-d6a8-461e-672642497db2@applied-asynchrony.com> (raw)
In-Reply-To: <8f84fe39-3d8d-396d-3b97-027e0a83f8cb@gmail.com>
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_events() however resets the bits in the interrupt status
> register, therefore subsequent calls to rtl8169_poll() won't call
> rtl_rx() and rtl_tx() - chip interrupts are still disabled.
Very interesting! Could this be the reason for the mysterious
hangs & resets we experienced when enabling BQL for r8169?
They happened more often with TSO/GSO enabled and several people
attempted to fix those hangs unsuccessfully; it was later reverted
and has been since then (#87cda7cb43).
If this bug has been there "forever" it might be tempting to
re-apply BQL and see what happens. Any chance you could give that
a try? I'll gladly test patches, just like I'll run this one.
cheers
Holger
next prev parent reply other threads:[~2018-10-17 5:19 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-16 20:37 [PATCH net] r8169: fix NAPI handling under high load Heiner Kallweit
2018-10-16 21:17 ` Holger Hoffstätte [this message]
2018-10-16 23:03 ` Stephen Hemminger
2018-10-16 23:08 ` Florian Fainelli
2018-10-17 0:23 ` Eric Dumazet
2018-10-17 3:10 ` Florian Fainelli
2018-10-17 0:21 ` Eric Dumazet
2018-10-17 18:12 ` Heiner Kallweit
2018-10-17 18:48 ` Fwd: " Heiner Kallweit
2018-10-17 19:11 ` Holger Hoffstätte
2018-10-17 19:27 ` Heiner Kallweit
2018-10-17 20:07 ` Holger Hoffstätte
2018-10-20 9:55 ` Holger Hoffstätte
2018-10-17 23:30 ` Francois Romieu
2018-10-18 5:58 ` Jonathan Woithe
2018-10-18 6:03 ` Heiner Kallweit
2018-10-18 6:15 ` Jonathan Woithe
2018-10-18 11:52 ` Holger Hoffstätte
2018-10-19 7:29 ` Jonathan Woithe
2018-10-21 23:07 ` Jonathan Woithe
2018-10-16 22:17 ` Stephen Hemminger
2018-10-17 0:19 ` Eric Dumazet
2018-10-17 23:30 ` Francois Romieu
2018-10-18 5:21 ` David Miller
2018-10-18 5:58 ` Heiner Kallweit
2018-10-18 6:24 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ada39488-8e9c-d6a8-461e-672642497db2@applied-asynchrony.com \
--to=holger@applied-asynchrony.com \
--cc=davem@davemloft.net \
--cc=hkallweit1@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=nic_swsd@realtek.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).