* bnx2: link drops when idle on 2.6.36-rc3
@ 2010-09-06 10:09 Michael S. Tsirkin
2010-09-06 15:25 ` Michael Chan
0 siblings, 1 reply; 2+ messages in thread
From: Michael S. Tsirkin @ 2010-09-06 10:09 UTC (permalink / raw)
To: Yaniv Rosner, Michael Chan; +Cc: netdev, eilong, linux-kernel
I have an IBM server which after switching to 2.6.36-rc3, started experiencing
link drops, where link would go down apparently at random. The link can be
brought back up without issues.
I started seing this after switching to 2.6.36-rc3.
net-2.6 (0b5d404e349c0236b11466c0a4785520c0be6982) also has this issue,
2.6.34 seems to work fine. Did not try bisecting or testing 2.6.35 yet.
Even log in hardware monitor shows e.g.
SERVPROC 05/17/01, 20:13:28 LAN: Ethernet[0] interface is now active
SERVPROC 05/17/01, 20:09:10 LAN: Ethernet[0] interface is no longer active
SERVPROC 05/17/01, 19:40:06 LAN: Ethernet[0] interface is now active
SERVPROC 05/17/01, 19:36:42 LAN: Ethernet[0] interface is no longer active
The server is mostly idle when this happens. lspci output for the
device is below. There appears nothing interesting in dmesg.
I can open a bugzilla at kernel.org if needed, just need to test
2.6.35 first.
04:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5708 Gigabit Ethernet (rev 12)
Subsystem: IBM Device 0342
Control: I/O- Mem+ BusMaster+ SpecCycle+ MemWINV+ VGASnoop- ParErr+ Stepping- SERR+ FastB2B- DisINTx+
Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 64 (16000ns min), Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 51
Region 0: Memory at c8000000 (64-bit, non-prefetchable) [size=32M]
Capabilities: [40] PCI-X non-bridge device
Command: DPERE- ERO- RBC=512 OST=4
Status: Dev=04:00.0 64bit+ 133MHz+ SCD- USC- DC=simple DMMRBC=512 DMOST=8 DMCRS=32 RSCEM- 266MHz- 533MHz-
Capabilities: [48] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot+,D3cold+)
Status: D0 NoSoftRst- PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [50] Vital Product Data
Product Name: Broadcom NetXtreme II Ethernet Controller
Read-only fields:
[PN] Part number: BCM95706A0
[EC] Engineering changes: 220197-2
[SN] Serial number: 0123456789
[MN] Manufacture ID: 31 34 65 34
[RV] Reserved: checksum bad, 30 byte(s) reserved
End
Capabilities: [58] MSI: Enable+ Count=1/1 Maskable- 64bit+
Address: 00000000fee0800c Data: 41c9
Kernel driver in use: bnx2
Kernel modules: bnx2
Thanks!
--
MST
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: bnx2: link drops when idle on 2.6.36-rc3
2010-09-06 10:09 bnx2: link drops when idle on 2.6.36-rc3 Michael S. Tsirkin
@ 2010-09-06 15:25 ` Michael Chan
0 siblings, 0 replies; 2+ messages in thread
From: Michael Chan @ 2010-09-06 15:25 UTC (permalink / raw)
To: 'Michael S. Tsirkin', Yaniv Rosner
Cc: 'netdev@vger.kernel.org', Eilon Greenstein,
'linux-kernel@vger.kernel.org'
Michael S. Tsirkin wrote:
> I have an IBM server which after switching to 2.6.36-rc3, started
> experiencing
> link drops, where link would go down apparently at random. The link can
> be
> brought back up without issues.
> I started seing this after switching to 2.6.36-rc3.
> net-2.6 (0b5d404e349c0236b11466c0a4785520c0be6982) also has this issue,
> 2.6.34 seems to work fine. Did not try bisecting or testing 2.6.35 yet.
> Even log in hardware monitor shows e.g.
>
> SERVPROC 05/17/01, 20:13:28 LAN: Ethernet[0] interface is
> now active
> SERVPROC 05/17/01, 20:09:10 LAN: Ethernet[0] interface is
> no longer active
> SERVPROC 05/17/01, 19:40:06 LAN: Ethernet[0] interface is
> now active
> SERVPROC 05/17/01, 19:36:42 LAN: Ethernet[0] interface is
> no longer active
>
> The server is mostly idle when this happens. lspci output for the
> device is below. There appears nothing interesting in dmesg.
dmesg should print a linkdown message when link goes down. Please check.
Please also provide mii-tool -vvv output when the link is up and when the
link is down. Thanks.
> I can open a bugzilla at kernel.org if needed, just need to test
> 2.6.35 first.
>
>
> 04:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5708
> Gigabit Ethernet (rev 12)
> Subsystem: IBM Device 0342
> Control: I/O- Mem+ BusMaster+ SpecCycle+ MemWINV+ VGASnoop-
> ParErr+ Stepping- SERR+ FastB2B- DisINTx+
> Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort-
> <TAbort- <MAbort- >SERR- <PERR- INTx-
> Latency: 64 (16000ns min), Cache Line Size: 64 bytes
> Interrupt: pin A routed to IRQ 51
> Region 0: Memory at c8000000 (64-bit, non-prefetchable)
> [size=32M]
> Capabilities: [40] PCI-X non-bridge device
> Command: DPERE- ERO- RBC=512 OST=4
> Status: Dev=04:00.0 64bit+ 133MHz+ SCD- USC- DC=simple
> DMMRBC=512 DMOST=8 DMCRS=32 RSCEM- 266MHz- 533MHz-
> Capabilities: [48] Power Management version 2
> Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-
> ,D3hot+,D3cold+)
> Status: D0 NoSoftRst- PME-Enable- DSel=0 DScale=1 PME-
> Capabilities: [50] Vital Product Data
> Product Name: Broadcom NetXtreme II Ethernet Controller
> Read-only fields:
> [PN] Part number: BCM95706A0
> [EC] Engineering changes: 220197-2
> [SN] Serial number: 0123456789
> [MN] Manufacture ID: 31 34 65 34
> [RV] Reserved: checksum bad, 30 byte(s) reserved
> End
> Capabilities: [58] MSI: Enable+ Count=1/1 Maskable- 64bit+
> Address: 00000000fee0800c Data: 41c9
> Kernel driver in use: bnx2
> Kernel modules: bnx2
>
> Thanks!
>
> --
> MST
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-09-06 15:25 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-09-06 10:09 bnx2: link drops when idle on 2.6.36-rc3 Michael S. Tsirkin
2010-09-06 15:25 ` Michael Chan
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).