Network downlink slow on Dell Inspiron 531S

[Steve Baker]

Binary package hint: linux-image-2.6.22-12-generic

Network download is very slow on machine running generic gutsy on AMD Athlon(tm) 64 X2 Dual Core with forcedeth network driver.

Here is a typical iperf run:
$ iperf -c 192.168.1.50 -d
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
------------------------------------------------------------
Client connecting to 192.168.1.50, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 5] local 192.168.1.101 port 37835 connected with 192.168.1.50 port 5001
[ 4] local 192.168.1.101 port 5001 connected with 192.168.1.50 port 56946
[ 5] 0.0-10.0 sec 48.4 MBytes 40.6 Mbits/sec
[ 4] 0.0-10.2 sec 1.57 MBytes 1.29 Mbits/sec

Ifconfig shows RX packet errors:
$ ifconfig
eth0 Link encap:Ethernet HWaddr 00:1A:A0:53:4D:FB
          inet addr:192.168.1.101 Bcast:192.168.1.255 Mask:255.255.255.0
          UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
          RX packets:73886 errors:3443 dropped:0 overruns:0 frame:3391
          TX packets:108585 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000
          RX bytes:27746730 (26.4 MB) TX bytes:140126662 (133.6 MB)
          Interrupt:16 Base address:0x4000

Pertinent excerpts from lshw:
     *-cpu
          description: CPU
          product: AMD Athlon(tm) 64 X2 Dual Core Processor 4000+
     *-bridge
          description: Ethernet interface
          product: MCP61 Ethernet
          vendor: nVidia Corporation
          physical id: 7
          bus info: pci@0000:00:07.0
          logical name: eth0
          version: a2
          serial: 00:1a:a0:53:4d:fb
          size: 100000000
          capacity: 100000000
          width: 32 bits
          clock: 66MHz
          capabilities: bridge pm msi ht bus_master cap_list ethernet physical mii 10bt 10bt-fd 100bt 100bt-fd autonegotiation
          configuration: autonegotiation=on broadcast=yes driver=forcedeth driverversion=0.60 duplex=full ip=192.168.1.101 latency=0 link=yes maxlatency=20 mingnt=1 module=forcedeth multicast=yes port=MII speed=100MB/s

$ uname -a
Linux steveb-desktop 2.6.22-12-generic #1 SMP Sun Sep 23 18:11:30 GMT 2007 i686 GNU/Linux

In addition to the default boot options following boot options were tried which had no effect on iperf stats speed:
noapictimer irqpoll
noapic nolapic
noapic acpi=noirq
noapic acpi=off
noapictimer
noapic acpi=noirq nolapic

The following boot options segfaulted on boot:
clock=pmtmr notsc
notsc

Disabling fglrx had no effect on iperf stats.

The slow download has been occured attached to 2 different routers and different cables.

[Steve Baker (steve-stevebaker)]

I've also disabled ipv6 with no effect

[Christiansen (happylinux)]

I can confirm this on different hardware (Thinkpad and HP) too - expected (100%) upload speed, and mostly extreme low (<10%) download speed. I short periods of time the download speed seems normal, and then returns to almost nothing.

[Leann Ogasawara (leannogasawara)]

The Hardy Heron Alpha series was recently released which contains an updated version of the kernel. You can download and try the new Hardy Heron Alpha release from http://cdimage.ubuntu.com/releases/hardy/ . You should be able to then test the new kernel via the LiveCD. If you can, please verify if this bug still exists or not and report back your results. General information regarding the release can also be found here: http://www.ubuntu.com/testing/ . Thanks

[Leann Ogasawara (leannogasawara)]

Also just adding a note that this report will remain open against the actively developed kernel but will be closed against linux-source-2.6.22. Thanks.

[Steve Baker (steve-stevebaker)]

Running the most recent Hardy daily release:
$ cat /proc/version_signature
Ubuntu 2.6.24-7.12-generic

Uplink is still an order of magnitude slower:
$ iperf -c 192.168.1.50 -r
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
------------------------------------------------------------
Client connecting to 192.168.1.50, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 5] local 192.168.1.100 port 41121 connected with 192.168.1.50 port 5001
[ 5] 0.0-10.0 sec 109 MBytes 91.2 Mbits/sec
[ 4] local 192.168.1.100 port 5001 connected with 192.168.1.50 port 48584
[ 4] 0.0-10.2 sec 9.82 MBytes 8.11 Mbits/sec

This is compared to the network card I'm currently using:
$ iperf -c 192.168.1.50 -r
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
------------------------------------------------------------
Client connecting to 192.168.1.50, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[ 5] local 192.168.1.103 port 36423 connected with 192.168.1.50 port 5001
[ 5] 0.0-10.0 sec 112 MBytes 93.7 Mbits/sec
[ 4] local 192.168.1.103 port 5001 connected with 192.168.1.50 port 55805
[ 4] 0.0-10.1 sec 113 MBytes 93.9 Mbits/sec

[Leann Ogasawara (leannogasawara)]

The Ubuntu Kernel Team is planning to move to the 2.6.27 kernel for the upcoming Intrepid Ibex 8.10 release. As a result, the kernel team would appreciate it if you could please test this newer 2.6.27 Ubuntu kernel. There are one of two ways you should be able to test:

1) If you are comfortable installing packages on your own, the linux-image-2.6.27-* package is currently available for you to install and test.

--or--

2) The upcoming Alpha5 for Intrepid Ibex 8.10 will contain this newer 2.6.27 Ubuntu kernel. Alpha5 is set to be released Thursday Sept 4. Please watch http://www.ubuntu.com/testing for Alpha5 to be announced. You should then be able to test via a LiveCD.

Please let us know immediately if this newer 2.6.27 kernel resolves the bug reported here or if the issue remains. More importantly, please open a new bug report for each new bug/regression introduced by the 2.6.27 kernel and tag the bug report with 'linux-2.6.27'. Also, please specifically note if the issue does or does not appear in the 2.6.26 kernel. Thanks again, we really appreicate your help and feedback.

[Steve Baker (steve-stevebaker)]

This appears to be fixed in Intrepid.

[Leann Ogasawara (leannogasawara)]

Thanks Steve. Marking this "Fix Released".

[Launchpad Janitor (janitor)]

Per a decision made by the Ubuntu Kernel Team, bugs will longer be assigned to the ubuntu-kernel-team in Launchpad as part of the bug triage process. The ubuntu-kernel-team is being unassigned from this bug report. Refer to https://wiki.ubuntu.com/KernelTeamBugPolicies for more information. Thanks.