[Bug 265714] igc(4) drops link under high traffic

[email protected]
Newsgroups gmane.os.freebsd.devel.net
Message-ID <[email protected]/bugzilla/>
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=265714

--- Comment #65 from Kevin Bowling <[email protected]> ---
(In reply to Tomasz "CeDeROM" CEDRO from comment #64)
I think the sysctl dump is post recovery?  The only clue is missed_packets,
maybe indicating an RX stall.  It would help to capture two snapshots a few
seconds apart before resetting while another host sends traffic: vmstat -i |
grep igc, netstat -I igc0 -bd, and the sysctl dumps.

Please also run these before, during, and after:

pciconf -lc igc0

and the following script:

/bin/sh <<'EOF'
cap=$(pciconf -lc igc0 |
    sed -n 's/.*ecap 001e\[\([0-9A-Fa-f][0-9A-Fa-f]*\)\].*/\1/p')

if [ -z "$cap" ]; then
    echo "L1PM capability 001e not found"
    exit 1
fi

off=$((0x${cap} + 8))
set -- $(pciconf -r igc0 "$off")
ctl1=$1

printf 'L1PM capability offset: 0x%s\n' "$cap"
printf 'L1PM CTL1 offset:      0x%x\n' "$off"
printf 'L1PM CTL1 value:       0x%s\n' "$ctl1"

if [ $((0x${ctl1} & 0x4)) -eq 0 ]; then
    echo 'I226 ASPM L1.2 enable: CLEAR (workaround active)'
else
    echo 'I226 ASPM L1.2 enable: SET (workaround absent/lost)'
fi
EOF

-- 
You are receiving this mail because:
You are the assignee for the bug.
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.