[PATCH] app/test: rewrite telemetry test in python

[Bruce Richardson]

On Fri, Jul 24, 2026 at 01:15:41PM -0700, Stephen Hemminger wrote:
> The test_telemetry.sh was failing with test timeout.
> This was caused by the overhead of spawning a fresh dpdk-telemetry.py
> for every command it walked. With every endpoint queried three times,
> that is several hundred Python interpreter startups per run.
> 
> Replace the shell script with a python test that opens the telemetry
> socket once and issues every command over that single connection.
> 
> Each reply is parsed as JSON and checked directly in Python.
> This also drops the jq dependency.
> 
> Bugzilla ID: 1972
> Fixes: 9da71dc4f96e ("test: add test case for scripted telemetry commands")
> Cc: stable at dpdk.org
> 
> Signed-off-by: Stephen Hemminger <stephen at networkplumber.org>
> ---
>  app/test/suites/meson.build       |   2 +-
>  app/test/suites/test_telemetry.py | 129 ++++++++++++++++++++++++++++++
>  app/test/suites/test_telemetry.sh |  30 -------
>  3 files changed, 130 insertions(+), 31 deletions(-)
>  create mode 100755 app/test/suites/test_telemetry.py
>  delete mode 100755 app/test/suites/test_telemetry.sh
> 
> diff --git a/app/test/suites/meson.build b/app/test/suites/meson.build
> index 786c459c24..ec1de99154 100644
> --- a/app/test/suites/meson.build
> +++ b/app/test/suites/meson.build
> @@ -145,7 +145,7 @@ if not is_windows and dpdk_conf.has('RTE_LIB_TELEMETRY')
>          test_args += ['--vdev=rawdev_skeleton0']
>      endif
>      test_args += ['-a', '0000:00:00.0']
> -    test('telemetry_all', find_program('test_telemetry.sh'),
> +    test('telemetry_all', find_program('test_telemetry.py'),
>              args: test_args,
>              timeout : timeout_seconds_fast,
>              is_parallel : false,
> diff --git a/app/test/suites/test_telemetry.py b/app/test/suites/test_telemetry.py
> new file mode 100755
> index 0000000000..f37eccabcc
> --- /dev/null
> +++ b/app/test/suites/test_telemetry.py
> @@ -0,0 +1,129 @@
> +#!/usr/bin/env python3
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright (c) 2022 Red Hat, Inc.
> +
> +"""Exercise every telemetry command exported by an application.
> +
> +Spawns the DPDK test binary (passed as arguments), waits for its telemetry
> +socket to appear, then walks every command reported by "/", calling each one
> +with no parameter and with dummy parameters "0" and "z". Every reply is parsed
> +as JSON and checked, so a malformed, empty or missing response fails the test
> +immediately and names the offending command, rather than relying on a shell
> +pipeline not erroring.
> +
> +A single connection is reused for the whole walk: the previous shell version
> +spawned a fresh dpdk-telemetry.py (Python interpreter + new connection) per
> +command, which scaled with process-startup cost and timed out under load.
> +"""
> +
> +import json
> +import os
> +import socket
> +import subprocess
> +import sys
> +import time
> +
> +SOCKET_NAME = "dpdk_telemetry.v2"
> +
> +
> +def runtime_dir():
> +    """DPDK runtime dir for the default 'rte' file-prefix, matching EAL."""
> +    run = os.environ.get("RUNTIME_DIRECTORY")
> +    if not run:
> +        run = (
> +            "/var/run"
> +            if os.getuid() == 0
> +            else os.environ.get("XDG_RUNTIME_DIR", "/tmp")
> +        )
> +    return os.path.join(run, "dpdk", "rte")
> +
> +
> +def wait_for_socket(path, proc, timeout=10):
> +    """Wait for the telemetry socket, failing fast if the app dies first."""
> +    deadline = time.time() + timeout
> +    while time.time() < deadline:
> +        if os.path.exists(path):
> +            return
> +        if proc.poll() is not None:
> +            raise RuntimeError(
> +                "application exited (code %d) before telemetry socket appeared"
> +                % proc.returncode
> +            )
> +        time.sleep(0.05)
> +    raise RuntimeError("timed out waiting for telemetry socket %s" % path)
> +
> +
> +class TelemetryClient:
> +    def __init__(self, path):
> +        self.sock = socket.socket(socket.AF_UNIX, socket.SOCK_SEQPACKET)
> +        self.sock.connect(path)
> +        info = json.loads(self.sock.recv(1024))
> +        self.buf_len = info["max_output_len"]
> +
> +    def command(self, cmd):
> +        self.sock.send(cmd.encode())
> +        reply = self.sock.recv(self.buf_len).decode()
> +        try:
> +            return json.loads(reply)
> +        except json.JSONDecodeError as e:
> +            raise AssertionError(
> +                "invalid JSON reply for %r: %s (raw: %r)" % (cmd, e, reply)
> +            )
> +
> +    def close(self):
> +        self.sock.close()
> +
> +
> +def check_reply(cmd, reply):
> +    """A telemetry reply must be a dict keyed by the command name."""
> +    if not isinstance(reply, dict) or list(reply.keys()) != [cmd.split(",")[0]]:
> +        raise AssertionError("unexpected reply for %r: %r" % (cmd, reply))
> +
> +
> +def walk(client):
> +    listing = client.command("/")
> +    check_reply("/", listing)
> +    count = 0
> +    for cmd in listing["/"]:
> +        for arg in ("", ",0", ",z"):
> +            full = cmd + arg
> +            reply = client.command(full)
> +            check_reply(full, reply)
> +            count += 1
> +    return count
> +

Not necessary to fix in this patch, but this iteration can be improved
using a few heuristics. For example, each node of type /*dev/list should
take no parameters and return a list of devices that can be passed to the
equivalent /*dev/info and /*dev/stats or xstats nodes. This existing simple
logic can then be used as a fallback for anything not meeting that
pattern.

For this whole shell to python replacement:
Acked-by: Bruce Richardson <bruce.richardson at intel.com>


> +
> +def main():
> +    if len(sys.argv) < 2:
> +        print("usage: %s <dpdk-app> [eal args...]" % sys.argv[0], file=sys.stderr)
> +        return 1
> +
> +    sock_path = os.path.join(runtime_dir(), SOCKET_NAME)
> +    proc = subprocess.Popen(sys.argv[1:], stdin=subprocess.PIPE)
> +    try:
> +        wait_for_socket(sock_path, proc)
> +        client = TelemetryClient(sock_path)
> +        try:
> +            count = walk(client)
> +        finally:
> +            client.close()
> +        print("telemetry: walked %d commands" % count)
> +    finally:
> +        # tell the interactive prompt to exit, then ensure the app is gone
> +        try:
> +            proc.stdin.write(b"quit\n")
> +            proc.stdin.flush()
> +            proc.stdin.close()
> +        except (BrokenPipeError, OSError):
> +            pass
> +        try:
> +            proc.wait(timeout=5)
> +        except subprocess.TimeoutExpired:
> +            proc.terminate()
> +            proc.wait()
> +
> +    return 0 if proc.returncode == 0 else proc.returncode
> +
> +
> +if __name__ == "__main__":
> +    sys.exit(main())
> diff --git a/app/test/suites/test_telemetry.sh b/app/test/suites/test_telemetry.sh
> deleted file mode 100755
> index 3c5b629b63..0000000000
> --- a/app/test/suites/test_telemetry.sh
> +++ /dev/null
> @@ -1,30 +0,0 @@
> -#!/bin/sh -e
> -# SPDX-License-Identifier: BSD-3-Clause
> -# Copyright (c) 2022 Red Hat, Inc.
> -
> -which jq || {
> -    echo "No jq available, skipping test."
> -    exit 77
> -}
> -
> -rootdir=$(readlink -f $(dirname $(readlink -f $0))/../../..)
> -tmpoutput=$(mktemp -t dpdk.test_telemetry.XXXXXX)
> -trap "cat $tmpoutput; rm -f $tmpoutput" EXIT
> -
> -call_all_telemetry() {
> -    telemetry_script=$rootdir/usertools/dpdk-telemetry.py
> -    echo >$tmpoutput
> -    echo "Telemetry commands log:" >>$tmpoutput
> -    echo / | $telemetry_script | jq -r '.["/"][]' | while read cmd
> -    do
> -        for input in $cmd $cmd,0 $cmd,z
> -        do
> -            echo Calling $input >> $tmpoutput
> -            echo $input | $telemetry_script >> $tmpoutput 2>&1
> -        done
> -    done
> -}
> -
> -! set -o | grep -q errtrace || set -o errtrace
> -! set -o | grep -q pipefail || set -o pipefail
> -(sleep 1 && call_all_telemetry && echo quit) | $@
> -- 
> 2.53.0
>