From: David Chang <dchang@suse.com>
To: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Realtek linux nic maintainers <nic_swsd@realtek.com>,
netdev@vger.kernel.org,
Martti Laaksonen <martti.laaksonen@sci.fi>
Subject: Re: r8169 Driver - Poor Network Performance Since Kernel 4.19
Date: Fri, 15 Feb 2019 10:51:30 +0800 [thread overview]
Message-ID: <20190215025130.GH7193@linux-kyyb.suse> (raw)
In-Reply-To: <47a0819f-5ec3-6d73-210e-235d6bbcaab1@gmail.com>
Hi Heiner,
On Feb 14, 2019 at 07:17:44 +0100, Heiner Kallweit wrote:
> Hi David,
>
> On 14.02.2019 03:45, David Chang wrote:
> > Hi Heiner,
> >
> > On Feb 05, 2019 at 19:50:30 +0100, Heiner Kallweit wrote:
> >> Hi David,
> >>
> >> meanwhile there's the following bug report matching what reported.
> >> It's even the same chip version (RTL8168h).
> >> https://bugzilla.redhat.com/show_bug.cgi?id=1671958
> >>
> >> Symptom there is also a significant number of rx_missed packets.
> >> Could you try what I mentioned there last:
> >> Try building a kernel with the call to rtl_hw_aspm_clkreq_enable(tp, true) at the
> >> end of rtl_hw_start_8168h_1() being disabled.
> >
> > After disabled the aspm function that you mentioned, we finally got the
> > positive testing result. And the rx_missed error was gone. If without
> > the patch, the receive side get back to bad performance.
> >
> Good to know, thanks. I also checked with Realtek, they confirmed that their Windows
> driver uses some heuristics to disable ASPM under high load. So it seems like there
> is some hw issue. Open so far is whether this affects certain chip versions only.
> Let's see whether they can provide more information.
Ok!
> Disabling ASPM in general would hurt notebook users because based on some past
> measurements we know ASPM can significantly save energy.
I understand, thanks!
regards,
David
>
> > kernel: r8169: loading out-of-tree module taints kernel.
> > kernel: r8169: module verification failed: signature and/or required key missing - tainting kernel
> > kernel: libphy: r8169: probed
> > kernel: r8169 0000:01:00.0 eth0: RTL8168h/8111h, ec:8e:b5:5a:2c:f5, XID 54100880, IRQ 128
> > kernel: r8169 0000:01:00.0 eth0: jumbo features [frames: 9200 bytes, tx checksumming: ko]
> > kernel: r8169 0000:01:00.0 enp1s0: renamed from eth0
> > kernel: Generic PHY r8169-100:00: attached PHY driver [Generic PHY] (mii_bus:phy_addr=r8169-100:00, irq=IGNORE)
> > kernel: r8169 0000:01:00.0 enp1s0: Link is Up - 1Gbps/Full - flow control off
> >
> > NIC statistics:
> > tx_packets: 1653804
> > rx_packets: 1555966
> > tx_errors: 0
> > rx_errors: 0
> > rx_missed: 0
> > align_errors: 0
> > tx_single_collisions: 0
> > tx_multi_collisions: 0
> > unicast: 1555884
> > broadcast: 78
> > multicast: 4
> > tx_aborted: 0
> > tx_underrun: 0
> >
> > iperf receive:
> > -----------------------------------------------------------
> > Server listening on 5201
> > -----------------------------------------------------------
> > Accepted connection from 10.x.x.x, port 55516
> > [ 5] local 10.x.x.x port 5201 connected to 10.x.x.x port 58172
> > [ ID] Interval Transfer Bitrate
> > [ 5] 0.00-1.00 sec 108 MBytes 906 Mbits/sec
> > [ 5] 1.00-2.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 2.00-3.00 sec 112 MBytes 940 Mbits/sec
> > [ 5] 3.00-4.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 4.00-5.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 5.00-6.00 sec 112 MBytes 942 Mbits/sec
> > [ 5] 6.00-7.00 sec 112 MBytes 939 Mbits/sec
> > [ 5] 7.00-8.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 8.00-9.00 sec 112 MBytes 938 Mbits/sec
> > [ 5] 9.00-10.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 10.00-11.00 sec 112 MBytes 941 Mbits/sec
> > [...]
> > [ 5] 50.00-51.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 51.00-52.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 52.00-53.00 sec 112 MBytes 942 Mbits/sec
> > [ 5] 53.00-54.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 54.00-55.00 sec 111 MBytes 934 Mbits/sec
> > [ 5] 55.00-56.00 sec 112 MBytes 942 Mbits/sec
> > [ 5] 56.00-57.00 sec 112 MBytes 937 Mbits/sec
> > [ 5] 57.00-58.00 sec 112 MBytes 941 Mbits/sec
> > [ 5] 58.00-59.00 sec 111 MBytes 932 Mbits/sec
> > [ 5] 59.00-60.00 sec 112 MBytes 942 Mbits/sec
> > [ 5] 60.00-60.04 sec 4.06 MBytes 939 Mbits/sec
> > - - - - - - - - - - - - - - - - - - - - - - - - -
> > [ ID] Interval Transfer Bitrate
> > [ 5] 0.00-60.04 sec 6.57 GBytes 940 Mbits/sec receiver
> >
> > regards,
> > David
> >
> Heiner
>
prev parent reply other threads:[~2019-02-15 2:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-28 11:13 r8169 Driver - Poor Network Performance Since Kernel 4.19 Peter Ceiley
2019-01-28 18:28 ` Heiner Kallweit
2019-01-28 22:10 ` Peter Ceiley
2019-01-29 6:16 ` Heiner Kallweit
2019-01-29 6:20 ` Peter Ceiley
2019-01-29 6:44 ` Heiner Kallweit
2019-01-30 9:59 ` Peter Ceiley
2019-01-30 19:15 ` Heiner Kallweit
2019-01-31 2:32 ` David Chang
2019-01-31 6:21 ` Heiner Kallweit
2019-01-31 6:35 ` Heiner Kallweit
2019-01-31 6:49 ` Heiner Kallweit
2019-01-31 7:23 ` David Chang
2019-01-31 12:09 ` Peter Ceiley
2019-01-31 18:28 ` Heiner Kallweit
2019-02-01 4:27 ` David Chang
2019-02-01 4:29 ` David Chang
2019-02-01 6:32 ` Heiner Kallweit
2019-02-02 12:25 ` Heiner Kallweit
2019-02-05 18:50 ` Heiner Kallweit
2019-02-05 18:53 ` Heiner Kallweit
2019-02-11 6:23 ` David Chang
2019-02-14 2:45 ` David Chang
2019-02-14 6:17 ` Heiner Kallweit
2019-02-15 2:51 ` David Chang [this message]
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=20190215025130.GH7193@linux-kyyb.suse \
--to=dchang@suse.com \
--cc=hkallweit1@gmail.com \
--cc=martti.laaksonen@sci.fi \
--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).