obmp-docker/cml/proxmox_bmp_config.py

#!/usr/bin/env python3
"""Apply the OpenBMP `bmp server 1` config to the Proxmox CML lab routers.

IOS-XR BMP configuration is not exposed via the device's NETCONF YANG schema
on this release, so this applies config over the SSH CLI. It is idempotent —
re-applying an identical block commits no changes.

PROX-R9K-03 was built without `bmp-activate` on its BGP neighbor-group; this
script adds it (the other 8 routers already have it from the re-addressing).

Usage:
    pip install paramiko
    python3 cml/proxmox_bmp_config.py            # all 9 routers
    python3 cml/proxmox_bmp_config.py r9k-05     # one router (smoke test)

Verify afterwards in OpenBMP:
    docker exec -i obmp-psql psql -U openbmp -d openbmp \\
      -c "SELECT name, ip_address, bgp_id, isconnected FROM routers ORDER BY name;"
"""

import os
import sys
import time
import paramiko


def _env_default(key, default, dotenv=".env"):
    """Resolve a value from os.environ or the repo-root .env, else default."""
    v = os.environ.get(key)
    if v:
        return v
    try:
        with open(dotenv) as fh:
            for line in fh:
                s = line.strip()
                if s and not s.startswith("#") and s.startswith(f"{key}="):
                    return s.split("=", 1)[1].strip().strip('"').strip("'")
    except FileNotFoundError:
        pass
    return default


# --- BMP collector ---------------------------------------------------------
# Resolved from $HOST_IP or the HOST_IP= line in repo-root .env.
COLLECTOR_HOST = _env_default("HOST_IP", "10.40.40.202")
COLLECTOR_PORT = "5000"

# `bmp server 1` block — flat formal form, identical to the ESXi lab.
# Each line is self-contained and applied at the (config)# prompt; a bare
# "bmp server 1" is deliberately omitted (it would drop into the bmp submode
# and the remaining flat lines would then be invalid).
BMP_LINES = [
    f"bmp server 1 host {COLLECTOR_HOST} port {COLLECTOR_PORT}",
    "bmp server 1 description OpenBMP-Collector",
    "bmp server 1 update-source MgmtEth0/RP0/CPU0/0",
    "bmp server 1 initial-delay 60",
    "bmp server 1 stats-reporting-period 300",
    "bmp server 1 initial-refresh delay 60 spread 30",
]

# Only PROX-R9K-03 needs this — its BMP-MONITORED neighbor-group was built
# without bmp-activate. AS 65021 is the Proxmox lab.
BMP_ACTIVATE_LINE = "router bgp 65021 neighbor-group BMP-MONITORED bmp-activate server 1"

# --- router inventory ------------------------------------------------------
# (name, mgmt_ip, user, password, needs_bmp_activate)
ROUTERS = [
    ("PROX-R9K-CORE-01", "10.100.1.100", "admin", "cisco", False),
    ("PROX-R9K-CORE-02", "10.100.1.200", "admin", "cisco", False),
    ("PROX-R9K-01",      "10.100.1.1",   "webui", "cisco", False),
    ("PROX-R9K-02",      "10.100.1.2",   "webui", "cisco", False),
    ("PROX-R9K-03",      "10.100.1.3",   "webui", "cisco", True),
    ("PROX-R9K-04",      "10.100.1.4",   "webui", "cisco", False),
    ("PROX-R9K-05",      "10.100.1.5",   "webui", "cisco", False),
    ("PROX-R9K-06",      "10.100.1.6",   "webui", "cisco", False),
    ("PROX-R9K-07",      "10.100.1.7",   "admin", "cisco", False),
]


def _drain(shell, settle=1.0, limit=15.0, until=None):
    """Read from the shell.

    If `until` is given, keep reading until that substring appears (or `limit`
    elapses). Otherwise return once output stops arriving for `settle` seconds.
    """
    out = ""
    start = time.time()
    while time.time() - start < limit:
        time.sleep(settle)
        if shell.recv_ready():
            out += shell.recv(65535).decode(errors="replace")
            if until and until in out:
                break
        elif until is None:
            break
        elif until in out:
            break
    return out


def apply_router(name, ip, user, pwd, needs_activate):
    """Apply the BMP config to one router. Returns True on success."""
    print(f"\n=== {name} ({ip}) ===")
    lines = list(BMP_LINES)
    if needs_activate:
        lines.append(BMP_ACTIVATE_LINE)

    try:
        ssh = paramiko.SSHClient()
        ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
        ssh.connect(ip, username=user, password=pwd, timeout=15,
                    look_for_keys=False, allow_agent=False)
        shell = ssh.invoke_shell(width=220, height=1000)
        time.sleep(2)
        shell.recv(65535)  # banner

        # "(config)#" is the universal IOS-XR config-prompt suffix — used as
        # the wait marker so the device hostname is irrelevant.
        CFG = "(config)#"

        shell.send("terminal length 0\n")
        _drain(shell, 0.5, 5)

        # Enter config mode. IOS-XR may print an active-session banner first,
        # so wait specifically for the (config) prompt.
        shell.send("configure terminal\n")
        out = _drain(shell, 0.4, 15, until=CFG)
        if CFG not in out:
            print(f"  FAIL: could not enter config mode\n  {out[-200:]}")
            ssh.close()
            return False

        # Send config lines, paced.
        for line in lines:
            shell.send(line + "\n")
            time.sleep(0.4)
        _drain(shell, 0.3, 8, until=CFG)

        # Confirm the candidate actually holds changes before committing.
        shell.send("show configuration\n")
        cand = _drain(shell, 0.3, 10, until=CFG)
        if "bmp server" not in cand:
            print("  OK: no changes (config already present) — nothing to commit")
            shell.send("abort\n")
            _drain(shell, 0.5, 5)
            ssh.close()
            return True

        shell.send("commit\n")
        result = _drain(shell, 0.3, 25, until=CFG)
        if "fail" in result.lower() or "error" in result.lower():
            print(f"  FAIL: commit error\n  {result[-300:]}")
            shell.send("abort\n")
            _drain(shell, 0.5, 5)
            ssh.close()
            return False

        # Leave config mode and fully drain (settle-based, no marker) so the
        # verify output is clean — not contaminated by echoed config lines.
        shell.send("end\n")
        _drain(shell, 1.0, 10)

        shell.send("show run formal bmp\n")
        verify = _drain(shell, 1.0, 12)
        ok = f"host {COLLECTOR_HOST} port {COLLECTOR_PORT}" in verify
        print(f"  {'OK' if ok else 'FAIL'}: bmp server 1 "
              f"{'present' if ok else 'NOT found'} in running config")
        ssh.close()
        return ok

    except Exception as e:
        print(f"  FAIL: {e}")
        return False


def main():
    target = sys.argv[1].lower() if len(sys.argv) > 1 else None
    results = {}
    for name, ip, user, pwd, needs_activate in ROUTERS:
        if target and target not in name.lower():
            continue
        results[name] = apply_router(name, ip, user, pwd, needs_activate)

    print(f"\n{'='*48}\n  SUMMARY")
    for name, ok in results.items():
        print(f"  {name:22s} {'OK' if ok else 'FAILED'}")
    sys.exit(0 if all(results.values()) else 1)


if __name__ == "__main__":
    main()