65 lines
2.9 KiB
Bash
65 lines
2.9 KiB
Bash
#!/bin/bash
|
|
# nvmf-connect — ExecStart for nvmf-connect.service (initramfs, TEST MODE).
|
|
#
|
|
# Why a systemd unit and not a dracut hook: this initramfs is systemd-driven and
|
|
# does NOT source dracut initqueue/online hooks when the ip=dhcp link comes up
|
|
# (verified on the bench — the online hook installs but never fires: no log, no
|
|
# connect). dracut's nvmf module also registers no autoconnect, and a job placed
|
|
# on the main initqueue is never re-executed once the loop blocks on events. A
|
|
# oneshot unit ordered Before=initrd-root-device.target, with its own
|
|
# wait-for-network + connect loop, deterministically connects the NVMe-oF root
|
|
# namespace so the by-id device appears and systemd-veritysetup can map
|
|
# /dev/mapper/root.
|
|
#
|
|
# rd.dot1x=0 (open-network test) ONLY — the unit's ConditionKernelCommandLine
|
|
# already gates this, but re-check so the script is safe to run directly. The
|
|
# secure path connects over macsec0 from dot1x-macsec-up.sh.
|
|
type getarg >/dev/null 2>&1 || . /lib/dracut-lib.sh
|
|
|
|
[ "$(getarg rd.dot1x=)" = "0" ] || exit 0
|
|
[ -e /run/dot1x/.nvmf-connected ] && exit 0
|
|
|
|
_disc=$(getarg rd.nvmf.discover=) # e.g. tcp,192.168.50.10,4420
|
|
[ -n "$_disc" ] || { echo "nvmf-connect: rd.nvmf.discover not set" >&2; exit 1; }
|
|
_trtype=${_disc%%,*}
|
|
_rest=${_disc#*,}
|
|
_traddr=${_rest%%,*}
|
|
_trsvcid=${_rest##*,}
|
|
|
|
# nvme_tcp is usually auto-loaded; ensure it so /dev/nvme-fabrics exists.
|
|
modprobe nvme_tcp 2>/dev/null
|
|
|
|
# Keep-alive / reconnect tuning for the ROOT device. These persist across
|
|
# switch-root (the in-kernel nvme-tcp controller and its opts survive).
|
|
# -k 30 keep-alive timeout (s). The 5s default means a KA every 2.5s; under
|
|
# kiosk CPU/memory pressure the nvme-tcp keep-alive work can be delayed
|
|
# past 5s, the target sees no KA and disconnects ("keep alive timeout").
|
|
# 30s gives a 15s emit interval and far more slack.
|
|
# -l -1 ctrl-loss-tmo = retry reconnection forever. This is the rootfs: the
|
|
# 600s default makes the host GIVE UP after a blip, after which root I/O
|
|
# fails permanently and the box wedges — strictly worse than retrying.
|
|
# -c 10 wait 10s between reconnect attempts.
|
|
_kato=30
|
|
_ctrl_loss_tmo=-1
|
|
_reconnect_delay=10
|
|
|
|
# Networking (ip=dhcp) is brought up in parallel, so poll-and-connect until a
|
|
# fabrics namespace appears or we time out. connect-all is idempotent.
|
|
_i=0
|
|
while [ "$_i" -lt 60 ]; do
|
|
nvme connect-all -t "$_trtype" -a "$_traddr" -s "$_trsvcid" \
|
|
-k "$_kato" -l "$_ctrl_loss_tmo" -c "$_reconnect_delay" 2>/dev/null
|
|
for _ns in /dev/nvme[0-9]*n[0-9]*; do
|
|
if [ -b "$_ns" ]; then
|
|
mkdir -p /run/dot1x
|
|
: > /run/dot1x/.nvmf-connected
|
|
echo "nvmf-connect: connected ${_trtype}/${_traddr}/${_trsvcid} ($_ns)"
|
|
exit 0
|
|
fi
|
|
done
|
|
sleep 1
|
|
_i=$((_i + 1))
|
|
done
|
|
echo "nvmf-connect: timed out connecting ${_trtype}/${_traddr}/${_trsvcid}" >&2
|
|
exit 1
|