weird realtek gigabit ethernet issue
[please cc me in any response as not subscribed]
I have an Asus M3A78-EM motherboard with a "Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02)" (per lspci)
which is using the r8169 module on ubuntu intrepid (specifically ubuntu kernel 2.6.27-9-generic)
kernel reports
RTL8168c/8111c at 0xf88be000, 00:22:15:a1:d2:41, XID 3c4000c0 IRQ 222
well, what's the issue, its going crazy on the dropped packets, even when the only thing connected to it is is an ssh session.
namely ifconfig shows
eth0 Link encap:Ethernet HWaddr 00:22:15:a1:d2:41 inet addr:192.168.0.41 Bcast:192.168.0.255 Mask:255.255.255.0 inet6 addr: fe80::222:15ff:fea1:d241/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:499 errors:0 dropped:2867537736 overruns:0 frame:0 TX packets:538 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000
RX bytes:38995 (38.9 KB) TX bytes:87571 (87.5 KB) Interrupt:222 Base address:0xe000
and the dropped count keeps on cycling through its entire space rapidly.
it's running in gigabit mode
root@nas:/home/spotter# mii-tool eth0: negotiated 1000baseT-FD flow-control, link ok
I have no idea why. never seen anything like this before. been wondering what could be doing it.
in investigating the driver
/*
* The driver does not support incoming fragmented
* frames. They are seen as a symptom of over-mtu
* sized frames.
*/
if (unlikely(rtl8169_fragmented_frame(status))) {
dev->stats.rx_dropped++;
dev->stats.rx_length_errors++;
rtl8169_mark_to_asic(desc, tp->rx_buf_sz);
continue;
}so it would appear to be some issue relating to fragmented frames.
However, based on the amount of packets received, it seems to be very strange.
I would have thought maybe it had something to do with jumbo packets, but all the machines on the net are using an mtu of 1500 currently.
anyways, any explanation, if its not a bug, would be appreciated.
On Mon, Dec 8, 2008 at 6:56 AM, Shaya Potter <[email protected]> wrote:> [please cc me in any response as not subscribed]>> I have an Asus M3A78-EM motherboard with a "Realtek Semiconductor Co.,> Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02)"> (per lspci)>> which is using the r8169 module on ubuntu intrepid (specifically ubuntu> kernel 2.6.27-9-generic)>> kernel reports>> RTL8168c/8111c at 0xf88be000, 00:22:15:a1:d2:41, XID 3c4000c0 IRQ 222>> well, what's the issue, its going crazy on the dropped packets, even> when the only thing connected to it is is an ssh session.>> namely ifconfig shows>> eth0 Link encap:Ethernet HWaddr 00:22:15:a1:d2:41> inet addr:192.168.0.41 Bcast:192.168.0.255 Mask:255.255.255.0> inet6 addr: fe80::222:15ff:fea1:d241/64 Scope:Link> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1> RX packets:499 errors:0 dropped:2867537736 overruns:0 frame:0> TX packets:538 errors:0 dropped:0 overruns:0 carrier:0> collisions:0 txqueuelen:1000> RX bytes:38995 (38.9 KB) TX bytes:87571 (87.5 KB)> Interrupt:222 Base address:0xe000>> and the dropped count keeps on cycling through its entire space rapidly.>> it's running in gigabit mode>> root@nas:/home/spotter# mii-tool> eth0: negotiated 1000baseT-FD flow-control, link ok>> I have no idea why. never seen anything like this before. been> wondering what could be doing it.>> in investigating the driver>> /*> * The driver does not support incoming fragmented> * frames. They are seen as a symptom of over-mtu> * sized frames.> */> if (unlikely(rtl8169_fragmented_frame(status))) {> dev->stats.rx_dropped++;> dev->stats.rx_length_errors++;> rtl8169_mark_to_asic(desc, tp->rx_buf_sz);> continue;> }>> so it would appear to be some issue relating to fragmented frames.>> However, based on the amount of packets received, it seems to be very> strange.>> I would have thought maybe it had something to do with jumbo packets,> but all the machines on the net are using an mtu of 1500 currently.>> anyways, any explanation, if its not a bug, would be appreciated.> --> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in> the body of a message to [email protected]> More majordomo info at http://vger.kernel.org/majordomo-info.html> Please read the FAQ at http://www.tux.org/lkml/>Did you try using iproute2 instead of ifconfig? I have the sameproblem with ifconfig, but iproute says that there's no problem:ifconfig :
eth0 Link encap:Ethernet HWaddr 00:1f:d0:ae:41:0e inet addr:192.168.1.3 Bcast:192.168.1.255 Mask:255.255.255.0 UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:16100 errors:0 dropped:152365729778 overruns:0 frame:0 TX packets:15465 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:15693968 (14.9 MiB) TX bytes:2565833 (2.4 MiB) Interrupt:245 Base address:0xc000
ip -stats link show eth0 :
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_faststate UNKNOWN qlen 1000 link/ether 00:1f:d0:ae:41:0e brd ff:ff:ff:ff:ff:ff RX: bytes packets errors dropped overrun mcast 15677088 16028 0 0 0 0 TX: bytes packets errors dropped carrier collsns 2536480 15384 0 0 0 0
-- You highest men whom my eyes have seen, this is my doubt about you andmy secret laughter: I guess that you would call my overman—devil!What is great is so alien to your souls that the overman would beterrifying to you in his goodness ...���{.n�+�������+%�����ݶ��w��{.n�+����{��G�����{ay�ʇڙ�,j��f���h��������z_�(�階�ݢj"���m������G������?����&���~��iO��z��v�^�m����������?�I�
Quoted 83 lines · Giangiacomo Mariotti
Quoted 60 lines · Shaya Potter
[please cc me in any response as not subscribed]
I have an Asus M3A78-EM motherboard with a "Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02)" (per lspci)
which is using the r8169 module on ubuntu intrepid (specifically ubuntu kernel 2.6.27-9-generic)
kernel reports
RTL8168c/8111c at
0xf88be000, 00:22:15:a1:d2:41, XID3c4000c0IRQ 222well, what's the issue, its going crazy on the dropped packets, even when the only thing connected to it is is an ssh session.
namely ifconfig shows
eth0 Link encap:Ethernet HWaddr 00:22:15:a1:d2:41 inet addr:192.168.0.41 Bcast:192.168.0.255 Mask:255.255.255.0 inet6 addr: fe80::222:15ff:fea1:d241/64 Scope:Link UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:499 errors:0 dropped:2867537736 overruns:0 frame:0 TX packets:538 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000
RX bytes:38995 (38.9 KB) TX bytes:87571 (87.5 KB) Interrupt:222 Base address:0xe000and the dropped count keeps on cycling through its entire space rapidly.
it's running in gigabit mode
root@nas:/home/spotter# mii-tool eth0: negotiated 1000baseT-FD flow-control, link okI have no idea why. never seen anything like this before. been wondering what could be doing it.
in investigating the driver
/*
* The driver does not support incoming fragmented
* frames. They are seen as a symptom of over-mtu
* sized frames.
*/if (unlikely(rtl8169_fragmented_frame(status))) { dev->stats.rx_dropped++; dev->stats.rx_length_errors++; rtl8169_mark_to_asic(desc, tp->rx_buf_sz); continue; }so it would appear to be some issue relating to fragmented frames.
However, based on the amount of packets received, it seems to be very strange.
I would have thought maybe it had something to do with jumbo packets, but all the machines on the net are using an mtu of 1500 currently.
Quoted 7 lines
anyways, any explanation, if its not a bug, would be appreciated. --
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/Did you try using iproute2 instead of ifconfig? I have the same problem with ifconfig, but iproute says that there's no problem:
ifconfig :eth0 Link encap:Ethernet HWaddr 00:1f:d0:ae:41:0e
inet addr:192.168.1.3 Bcast:192.168.1.255 Mask:255.255.255.0 UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:16100 errors:0 dropped:152365729778 overruns:0 frame:0 TX packets:15465 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:15693968 (14.9 MiB) TX bytes:2565833 (2.4 MiB) Interrupt:245 Base address:0xc000ip -stats link show eth0 :
Quoted 7 lines
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc
pfifo_faststate UNKNOWN qlen 1000link/ether 00:1f:d0:ae:41:0e brd ff:ff:ff:ff:ff:ff RX: bytes packets errors dropped overrun mcast 15677088 16028 0 0 0 0 TX: bytes packets errors dropped carrier collsns 2536480 15384 0 0 0 0
perhaps, it also show me no dropped packets, but that would indicate a bug in /proc/net/dev.
root@nas:~# cat /proc/net/dev ; sleep 1; cat /proc/net/dev
Inter-| Receive | Transmit
face |bytes packets errs drop fifo frame compressed multicast|bytes
packets errs drop fifo colls carrier compressed
lo: 6544 87 0 0 0 0 0 0
6544 87 0 0 0 0 0 0
eth0:3088491699 2376860 0 672445284 0 0 0 0
1288945906 1663182 0 0 0 0 0 0
Inter-| Receive | Transmit
face |bytes packets errs drop fifo frame compressed multicast|bytes
packets errs drop fifo colls carrier compressed
lo: 6544 87 0 0 0 0 0 0
6544 87 0 0 0 0 0 0
eth0:3088491983 2376864 0 802845154 0 0 0 0
1288948788 1663188 0 0 0 0 0 0Shaya Potter <[email protected]> :
[...]
Quoted 2 lines
perhaps, it also show me no dropped packets, but that would indicate a bug in
/proc/net/dev.
It is unrelated.
It should be fixed in mainline as 523a609496dbc3897e530db2a2f27650d125ea00 and in 2.6.27-stable as 6269b8494da80250422ed8ce4e6ee7126c0010aa.
Signature · 1 line
Ueimor
(Ccing l-k as it may be of wider interest)
Giangiacomo Mariotti <[email protected]> :
Quoted 13 lines
2008/12/11 Francois Romieu <[email protected]>:
Quoted 12 lines
Giangiacomo Mariotti <[email protected]> :
[...]Quoted 10 lines
Dec 7 10:13:56 debian-hell kernel: [ 4.064402] eth0: RTL8169 at 0xffffc2000062a000, 00:1f:d0:ae:41:0e, XID 281000c0 IRQ 1270 Dec 7 10:13:56 debian-hell kernel: [ 5.325793] eth1: RTL8169 at 0xffffc20000630000, 00:1f:d0:ae:41:10, XID 281000c0 IRQ 1269 Dec 8 06:09:31 debian-hell kernel: [ 6.253241] eth0: RTL8168d/8111d at 0xffffc2000064e000, 00:1f:d0:ae:41:0e, XID 281000c0 IRQ 1270 Dec 8 06:09:31 debian-hell kernel: [ 6.258123] eth1:RTL8168d/8111d at
0xffffc20000652000, 00:1f:d0:ae:41:10, XID281000c0IRQ 1269
[...]
Quoted 3 lines
On Dec 8, at 06, I booted 2.6.28-rc7, while on Dec 7, at 10, I booted 2.6.26-1-amd64(debian, based on 2.6.26.8). I can't find any log for 2.6.27.8.
Ok. Looking at your logs and at the r8169.c code, here is the story.
1. On December 7, the r8169.c driver identifies your network card as an (old) "RTL8169" i.e. RTL_GIGA_MAC_VER_01 in r8169.c. This is the default choice when there is no specific match for the XID. You can check this in r8169.c::rtl8169_get_mac_version. Below RTL_GIGA_MAC_VER_06, the driver assumes that the device includes a "RxMissed" register (see r8169.c::rtl8169_rx_missed). This assumption is false for your device
- as it is on nearly all new 816x flavors nowadays - and you will experience a broken rx missed counter in ifconfig's output.
2. On December 8, the r8169 driver identifies your network card as a more modern "RTL8168d/8111d" i.e. RTL_GIGA_MAC_VER_25. As far as I know, it should be the adequate choice given the XID. r8169.c::rtl8169_rx_missed will not try to access the non-existant RxMissed register and your stats should be fine.
While the fix for the RxMissed register access is in the stable branch, it is useless if the adapter is (mis-)detected as an old RTL8169.
So, currently, your rx missed counters should be broken on anything older than 2.6.28-rc1. If they were vanilla kernel (I have not checked the content of Debian's kernel), Dec 7 should be broken and Dec 8 should be ok.
Does the explanation above match your observations ?
Btw I should probably push new RTL_GIGA_MAC_VER_XX into -stable.
Signature · 1 line
Ueimor
Quoted 41 lines · Francois Romieu
(Ccing l-k as it may be of wider interest)
Giangiacomo Mariotti <[email protected]> :
Quoted 13 lines
2008/12/11 Francois Romieu <[email protected]>:
Quoted 12 lines
Giangiacomo Mariotti <[email protected]> :
[...]Quoted 10 lines
Dec 7 10:13:56 debian-hell kernel: [ 4.064402] eth0: RTL8169 at 0xffffc2000062a000, 00:1f:d0:ae:41:0e, XID 281000c0 IRQ 1270 Dec 7 10:13:56 debian-hell kernel: [ 5.325793] eth1: RTL8169 at 0xffffc20000630000, 00:1f:d0:ae:41:10, XID 281000c0 IRQ 1269 Dec 8 06:09:31 debian-hell kernel: [ 6.253241] eth0: RTL8168d/8111d at 0xffffc2000064e000, 00:1f:d0:ae:41:0e, XID 281000c0 IRQ 1270 Dec 8 06:09:31 debian-hell kernel: [ 6.258123] eth1:RTL8168d/8111d at
0xffffc20000652000, 00:1f:d0:ae:41:10, XID281000c0IRQ 1269[...]
Quoted 3 lines
On Dec 8, at 06, I booted 2.6.28-rc7, while on Dec 7, at 10, I booted 2.6.26-1-amd64(debian, based on 2.6.26.8). I can't find any log for 2.6.27.8.
Ok. Looking at your logs and at the
r8169.ccode, here is the story.1. On December 7, the
r8169.cdriver identifies your network card as an (old) "RTL8169" i.e.RTL_GIGA_MAC_VER_01inr8169.c. This is the default choice when there is no specific match for the XID. You can check this inr8169.c::rtl8169_get_mac_version. BelowRTL_GIGA_MAC_VER_06, the driver assumes that the device includes a "RxMissed" register (seer8169.c::rtl8169_rx_missed). This assumption is false for your device
- as it is on nearly all new 816x flavors nowadays - and you will experience a broken rx missed counter in ifconfig's output.2. On December 8, the r8169 driver identifies your network card as a more modern "RTL8168d/8111d" i.e.
RTL_GIGA_MAC_VER_25. As far as I know, it should be the adequate choice given the XID.r8169.c::rtl8169_rx_missedwill not try to access the non-existant RxMissed register and your stats should be fine.While the fix for the RxMissed register access is in the stable branch, it is useless if the adapter is (mis-)detected as an old RTL8169.
Quoted 7 lines
So, currently, your rx missed counters should be broken on anything older than 2.6.28-rc1. If they were vanilla kernel (I have not checked the content of Debian's kernel), Dec 7 should be broken and Dec 8 should be ok.
Does the explanation above match your observations ?
Yes.
Quoted 5 lines
Btw I should probably push new
RTL_GIGA_MAC_VER_XXinto -stable.--
Ueimor