Menu
▾
▴
RE: [E1000-devel] RX lockup problem
|
From: Ronciak, J. <joh...@in...> - 2006-02-08 17:00:19
|
> Is it possible for the cable to trigger this=20 > problem and still pass most of the traffic and=20 > yet the problem be solved by a down/up (renegotiation)? Yes it is. That's why I wanted you to switch the cables (or the NIC = interface ports) to the different switches. The length errors being = reports can easily be caused by bad cables, especially fiber ones. This = would show if problem follows the cable being used. Cheers, John ----------------------------------------------------------- "Those who would give up essential Liberty, to purchase a little = temporary Safety, deserve neither Liberty nor Safety.", Benjamin = Franklin 1755=20 > -----Original Message----- > From: e10...@li...=20 > [mailto:e10...@li...] On Behalf Of=20 > Jan-Patrick Perisse > Sent: Wednesday, February 08, 2006 8:43 AM > To: e10...@li... > Subject: RE: [E1000-devel] RX lockup problem >=20 >=20 >=20 > At 13:59 8/2/2006, Ronciak, John wrote: > >Do older versions of the e1000 driver change the behavior? >=20 > Yes, actually, it used to lock up the server. >=20 > > Did you try switching cables? >=20 > I am having a hard time to get another cable, but=20 > it is the next thing I will try. > Is it possible for the cable to trigger this=20 > problem and still pass most of the traffic and=20 > yet the problem be solved by a down/up (renegotiation)? >=20 >=20 > > Did you try to switch which interface went=20 > > to which switch (one that is currently=20 > > reporting errors to the Foundry switch and the other to the Cisco)? >=20 > Nope, but I changed the interface on the cisco and the same=20 > thing happens. >=20 >=20 > >This seems like a HW problem but I could be wrong. > > > >Please let us know what you find. > > > >Cheers, > >John > >----------------------------------------------------------- > >"Those who would give up essential Liberty, to=20 > >purchase a little temporary Safety, deserve=20 > >neither Liberty nor Safety.", Benjamin Franklin 1755 > > > > > > > -----Original Message----- > > > From: e10...@li... > > > [mailto:e10...@li...] On Behalf Of > > > Jan-Patrick Perisse > > > Sent: Wednesday, February 08, 2006 5:51 AM > > > To: e10...@li... > > > Subject: [E1000-devel] RX lockup problem > > > > > > > > > I have a server using the following driver: > > > driver: e1000 > > > version: 6.3.9-NAPI > > > firmware-version: N/A > > > bus-info: 03:08.0 > > > And the following kernel: > > > Linux gw 2.4.21-37.ELsmp #1 SMP > > > This server is a Dual Xeon HT and has an intel dual e1000=20 > onboard. I > > > added a dual e1000 fiber card: > > > 03:07.0 Ethernet controller: Intel Corp. 82546EB Gigabit Ethernet > > > Controller (Copper) (rev 01) > > > Subsystem: Intel Corp.: Unknown device 341a > > > Control: I/O+ Mem+ BusMaster+ SpecCycle-=20 > MemWINV- VGASnoop- > > > ParErr- Stepping- SERR+ FastB2B- > > > Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- > > > DEVSEL=3Dmedium >TAbort- <TAbort- <MAbort- >SERR- <PERR- > > > Latency: 64 (63750ns min), cache line size 10 > > > Interrupt: pin A routed to IRQ 9 > > > Region 0: Memory at fe680000 (64-bit, > > > non-prefetchable) [size=3D128K] > > > Region 4: I/O ports at 20c0 [size=3D64] > > > Capabilities: [dc] Power Management version 2 > > > Flags: PMEClk+ DSI+ D1- D2- AuxCurrent=3D0mA > > > PME(D0+,D1-,D2-,D3hot+,D3cold+) > > > Status: D0 PME-Enable- DSel=3D0 DScale=3D1 PME- > > > Capabilities: [e4] PCI-X non-bridge device. > > > Command: DPERE- ERO+ RBC=3D0 OST=3D0 > > > Status: Bus=3D0 Dev=3D0 Func=3D0 64bit-=20 > 133MHz- SCD- USC-, > > > DC=3Dsimple, DMMRBC=3D0, DMOST=3D0, DMCRS=3D0, RSCEM- =20 > Capabilities: [f0] > > > Message Signalled Interrupts: 64bit+ Queue=3D0/0 Enable- > > > Address: 0000000000000000 Data: 0000 > > > > > > 03:07.1 Ethernet controller: Intel Corp. 82546EB Gigabit Ethernet > > > Controller (Copper) (rev 01) > > > Subsystem: Intel Corp.: Unknown device 341a > > > Control: I/O+ Mem+ BusMaster+ SpecCycle-=20 > MemWINV+ VGASnoop- > > > ParErr- Stepping- SERR+ FastB2B- > > > Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- > > > DEVSEL=3Dmedium >TAbort- <TAbort- <MAbort- >SERR- <PERR- > > > Latency: 64 (63750ns min), cache line size 10 > > > Interrupt: pin B routed to IRQ 9 > > > Region 0: Memory at fe6a0000 (64-bit, > > > non-prefetchable) [size=3D128K] > > > Region 4: I/O ports at 2080 [size=3D64] > > > Capabilities: [dc] Power Management version 2 > > > Flags: PMEClk+ DSI+ D1- D2- AuxCurrent=3D0mA > > > PME(D0+,D1-,D2-,D3hot+,D3cold+) > > > Status: D0 PME-Enable- DSel=3D0 DScale=3D1 PME- > > > Capabilities: [e4] PCI-X non-bridge device. > > > Command: DPERE- ERO+ RBC=3D0 OST=3D0 > > > Status: Bus=3D0 Dev=3D0 Func=3D0 64bit-=20 > 133MHz- SCD- USC-, > > > DC=3Dsimple, DMMRBC=3D0, DMOST=3D0, DMCRS=3D0, RSCEM- =20 > Capabilities: [f0] > > > Message Signalled Interrupts: 64bit+ Queue=3D0/0 Enable- > > > Address: 0000000000000000 Data: 0000 > > > > > > 03:08.0 Ethernet controller: Intel Corp. 82546EB Gigabit Ethernet > > > Controller (Fiber) (rev 01) > > > Subsystem: Intel Corp. PRO/1000 MF Dual Port=20 > Server Adapter > > > Control: I/O+ Mem+ BusMaster+ SpecCycle-=20 > MemWINV+ VGASnoop- > > > ParErr- Stepping- SERR+ FastB2B- > > > Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- > > > DEVSEL=3Dmedium >TAbort- <TAbort- <MAbort- >SERR- <PERR- > > > Latency: 64 (63750ns min), cache line size 10 > > > Interrupt: pin A routed to IRQ 9 > > > Region 0: Memory at fe6c0000 (64-bit, > > > non-prefetchable) [size=3D128K] > > > Region 4: I/O ports at 2040 [size=3D64] > > > Capabilities: [dc] Power Management version 2 > > > Flags: PMEClk- DSI+ D1- D2- AuxCurrent=3D0mA > > > PME(D0+,D1-,D2-,D3hot+,D3cold+) > > > Status: D0 PME-Enable- DSel=3D0 DScale=3D1 PME- > > > Capabilities: [e4] PCI-X non-bridge device. > > > Command: DPERE- ERO+ RBC=3D0 OST=3D0 > > > Status: Bus=3D0 Dev=3D0 Func=3D0 64bit-=20 > 133MHz- SCD- USC-, > > > DC=3Dsimple, DMMRBC=3D0, DMOST=3D0, DMCRS=3D0, RSCEM- =20 > Capabilities: [f0] > > > Message Signalled Interrupts: 64bit+ Queue=3D0/0 Enable- > > > Address: 0000000000000000 Data: 0000 > > > > > > 03:08.1 Ethernet controller: Intel Corp. 82546EB Gigabit Ethernet > > > Controller (Fiber) (rev 01) > > > Subsystem: Intel Corp. PRO/1000 MF Dual Port=20 > Server Adapter > > > Control: I/O+ Mem+ BusMaster+ SpecCycle-=20 > MemWINV+ VGASnoop- > > > ParErr- Stepping- SERR+ FastB2B- > > > Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- > > > DEVSEL=3Dmedium >TAbort- <TAbort- <MAbort- >SERR- <PERR- > > > Latency: 64 (63750ns min), cache line size 10 > > > Interrupt: pin B routed to IRQ 9 > > > Region 0: Memory at fe6e0000 (64-bit, > > > non-prefetchable) [size=3D128K] > > > Region 4: I/O ports at 2000 [size=3D64] > > > Capabilities: [dc] Power Management version 2 > > > Flags: PMEClk- DSI+ D1- D2- AuxCurrent=3D0mA > > > PME(D0+,D1-,D2-,D3hot+,D3cold-) > > > Status: D0 PME-Enable- DSel=3D0 DScale=3D1 PME- > > > Capabilities: [e4] PCI-X non-bridge device. > > > Command: DPERE- ERO+ RBC=3D0 OST=3D0 > > > Status: Bus=3D0 Dev=3D0 Func=3D0 64bit-=20 > 133MHz- SCD- USC-, > > > DC=3Dsimple, DMMRBC=3D0, DMOST=3D0, DMCRS=3D0, RSCEM- =20 > Capabilities: [f0] > > > Message Signalled Interrupts: 64bit+ Queue=3D0/0 Enable- > > > Address: 0000000000000000 Data: 0000 > > > Right now, the copper cards are disconnected and one=20 > fiber interface > > > is connected to each network. > > > I have about 20Mbit/s traffic with peaks of 35. > > > One end is connected to a foundry switch and gives me no > > > problem at all. > > > The other end is connected to a cisco 5505 switch and gives > > > me the following: > > > NIC statistics: > > > rx_packets: 753533926 > > > tx_packets: 799286536 > > > rx_bytes: 815368397 > > > tx_bytes: 581540964 > > > rx_errors: 11217908 > > > tx_errors: 0 > > > rx_dropped: 0 > > > tx_dropped: 0 > > > multicast: 31 > > > collisions: 0 > > > rx_length_errors: 1571250 > > > rx_over_errors: 0 > > > rx_crc_errors: 8848081 > > > rx_frame_errors: 0 > > > rx_fifo_errors: 0 > > > rx_no_buffer_count: 121 > > > rx_missed_errors: 0 > > > tx_aborted_errors: 0 > > > tx_carrier_errors: 0 > > > tx_fifo_errors: 0 > > > tx_heartbeat_errors: 0 > > > tx_window_errors: 0 > > > tx_abort_late_coll: 0 > > > tx_deferred_ok: 0 > > > tx_single_coll_ok: 0 > > > tx_multi_coll_ok: 0 > > > tx_timeout_count: 0 > > > rx_long_length_errors: 44 > > > rx_short_length_errors: 1163147 > > > rx_align_errors: 0 > > > tx_tcp_seg_good: 0 > > > tx_tcp_seg_failed: 0 > > > rx_flow_control_xon: 0 > > > rx_flow_control_xoff: 0 > > > tx_flow_control_xon: 0 > > > tx_flow_control_xoff: 0 > > > rx_long_byte_count: 202678831309 > > > rx_csum_offload_good: 724225561 > > > rx_csum_offload_errors: 37195 > > > rx_header_split: 0 > > > alloc_rx_buff_failed: 0 > > > Lots of CRC errors, but packets get through fine. The=20 > switch doesn't > > > report any errors at all. > > > Every day or two, the interface stops receiving packets.=20 > TX works OK. > > > down and up seems to solve the problem until it happens again. > > > Need any more info? > > > > > > > > > > > > > > > -- > > > Esta mensagem foi verificada pelo sistema de antiv=EDrus e > > > acredita-se estar livre de perigo. > > > > > > > > > > > > ------------------------------------------------------- > > > This SF.net email is sponsored by: Splunk Inc. Do you grep > > > through log files > > > for problems? Stop! Download the new AJAX search engine=20 > that makes > > > searching your log files as easy as surfing the web. > > > DOWNLOAD SPLUNK! > > > = http://sel.as-us.falkag.net/sel?cmd=3Dlnk&kid=3D103432&bid=3D230486& > >dat=3D121642 > >_______________________________________________ > >E1000-devel mailing list > >E10...@li... > >https://lists.sourceforge.net/lists/listinfo/e1000-devel > > > >-- > >Esta mensagem foi verificada pelo sistema de antiv=EDrus e > > acredita-se estar livre de perigo. >=20 > Jan-Patrick P=E9riss=E9 > AEON TECHNOLOGIES > (21) 2705-3139 / 2705-3028 > http://www.aeontech.com.br >=20 >=20 >=20 >=20 >=20 > --=20 > Esta mensagem foi verificada pelo sistema de antiv=EDrus e > acredita-se estar livre de perigo. >=20 >=20 >=20 > ------------------------------------------------------- > This SF.net email is sponsored by: Splunk Inc. Do you grep=20 > through log files > for problems? Stop! Download the new AJAX search engine that makes > searching your log files as easy as surfing the web. =20 > DOWNLOAD SPLUNK! > http://sel.as-us.falkag.net/sel?cmd=3Dk&kid=103432&bid#0486&dat=121642 > _______________________________________________ > E1000-devel mailing list > E10...@li... > https://lists.sourceforge.net/lists/listinfo/e1000-devel >=20 |