Re: sky2 hangs without any messages

Hi Stephen,

Tino Keitel [off-list ref] wrote:

quoted

in the last 2 days, I had 2 outages of the NIC of my Mac mini Core Duo.
I checked the kernel log but I found nothing sky2 related. After
reloading the module, the interface worked again.

There is a reproducible hang (due to missed IRQ) in sky2.  It is more reproducible
with slower CPU's like Mac Mini.

This feels like the same problem I hit once every ~2 days on my server
platform or laptop [1]: both Yukon-ECs, rev 1 and 2, running NFSv4
over TCP over a gig-e switch, ia32, PCI-E.

Observations:

1. problem happens with both rev-1 and 2 Yukon-ECs, so less likely a silicon bug
2. reproducible with 1500 MTU on both ends
3. reproducible with and without receive offloading disabled (ie
'ethtool -K gig0 rx off') [check with tx offload too?]
4. reproducible with two different gig-e switches and different cables
5. reproducible with MSI interrupts [check with legacy interrupts?]

Is there anything that I can do to help debug this missing IRQ hang?
I'm thinking of moving to the vendor driver [2] to see if the issue is
entirely avoidable in software.

Thanks,
  Daniel

--- [1]

sky2 0000:02:00.0: v1.14 addr 0xd6000000 irq 16 Yukon-EC (0xb6) rev 2
sky2 gig0: addr 00:16:b6:70:d8:3d
sky2 gig0: enabling interface
sky2 gig0: ram buffer 48K
sky2 gig0: Link is up at 1000 Mbps, full duplex, flow control both
<NFS hang observed>
NETDEV WATCHDOG: gig0: transmit timed out
sky2 gig0: tx timeout
sky2 gig0: transmit ring 424 .. 401 report=427 done=427
sky2 gig0: disabling interface
sky2 gig0: enabling interface
sky2 gig0: ram buffer 48K
sky2 gig0: Link is up at 1000 Mbps, full duplex, flow control both
<NFS resumes after a few minutes>

$ grep gig0 /proc/interrupts
218:      27297          0   PCI-MSI-edge      gig0

--- [2]

http://www.syskonnect.de/e_en/products/adapters/pcie_server/sk-9exx/software/linux/driver/install-8_31.tar.bz2
-- 
Daniel J Blueman