From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 685944718A; Mon, 5 Jan 2026 18:56:53 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id CDBC740678; Mon, 5 Jan 2026 18:56:24 +0100 (CET) Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.11]) by mails.dpdk.org (Postfix) with ESMTP id 4A7024064F for ; Mon, 5 Jan 2026 18:56:20 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1767635781; x=1799171781; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=UKE+t1fHeW79H68pukxahQ1+G7DE6OJKsyVSicXWYH0=; b=IyU9Ffec7hW1dtiC9wPdZDKimOFtTOLgLLCBd+GAyqqM8iExJir2inpW vkWe9nE2oOky1QxCttTQIU3R/8LeHQgEFiVKnxsUA9pHxVqc+4xmdZWyk yPsHtEUufPlz/aB4PMfO6gTMhE3Qhz95yRgvfDuPcx3ehSm6TFAqi1JVC UQB+JSbUmEfcZnTAGYz9hqW/LxqunblOtPHvQ4l2Bk+vTMsi+8gPPG5Se dD/2FQnFvKMKThZskopvHifQd0tTKG9VHYp3iKEVCh7FMYCYgkUbWZ4k7 dPfZcLIUdW6tKf/Q2ZisUn5CTT/yKikhWEIM8FqIe370qYNCpJL7C5Dmg g==; X-CSE-ConnectionGUID: R0SVIRUISYebNxI16lMwDg== X-CSE-MsgGUID: 2VoImzGqTQm/VvzCkEPtnw== X-IronPort-AV: E=McAfee;i="6800,10657,11662"; a="79308865" X-IronPort-AV: E=Sophos;i="6.21,204,1763452800"; d="scan'208";a="79308865" Received: from orviesa001.jf.intel.com ([10.64.159.141]) by orvoesa103.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 05 Jan 2026 09:56:21 -0800 X-CSE-ConnectionGUID: Ravix4eaQbKglL93CTOvxw== X-CSE-MsgGUID: sCudipfSRwSWGOjhg2o7/Q== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.21,204,1763452800"; d="scan'208";a="239928779" Received: from silpixa00401385.ir.intel.com ([10.20.224.226]) by orviesa001.jf.intel.com with ESMTP; 05 Jan 2026 09:56:19 -0800 From: Bruce Richardson To: dev@dpdk.org Cc: Bruce Richardson Subject: [PATCH v2 7/7] usertools/telemetry-watcher: support reconnection Date: Mon, 5 Jan 2026 17:56:05 +0000 Message-ID: <20260105175605.52689-8-bruce.richardson@intel.com> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20260105175605.52689-1-bruce.richardson@intel.com> References: <20251210165532.103450-1-bruce.richardson@intel.com> <20260105175605.52689-1-bruce.richardson@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Allow the watcher binary to run even when there is no DPDK process running. In that case, wait for a suitable process to start and begin monitoring then. In case of disconnection, keep trying to reconnect and resume once reconnection succeeds. Signed-off-by: Bruce Richardson --- usertools/dpdk-telemetry-watcher.py | 52 ++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 12 deletions(-) diff --git a/usertools/dpdk-telemetry-watcher.py b/usertools/dpdk-telemetry-watcher.py index 6beb67d29a..5c568c1e88 100755 --- a/usertools/dpdk-telemetry-watcher.py +++ b/usertools/dpdk-telemetry-watcher.py @@ -85,6 +85,12 @@ def create_telemetry_process(telemetry_script, args_list): text=True, bufsize=1, # Line buffered ) + + # Get and display the connected application name + if not print_connected_app(process): + return None + process.script = telemetry_script # Store script path for reference + process.args = args_list # Store args for reference return process except FileNotFoundError: print(f"Error: Python interpreter or script not found", file=sys.stderr) @@ -102,15 +108,32 @@ def query_telemetry(process, command): command: The telemetry command to send (e.g., "/info" or "/ethdev/stats,0") Returns: - dict: The parsed JSON response with the command wrapper stripped, + (process, dict): The process handle, in case of reconnection, and the + parsed JSON response with the command wrapper stripped, or None if there was an error """ + # Handle case where process is None + if process is None: + return (None, None) + # Send the command process.stdin.write(f"{command}\n") process.stdin.flush() - # Read the JSON response + # Read the JSON response, reconnecting if necessary response = process.stdout.readline() + while not response: + script = process.script + args_list = process.args + process = None + print("Application disconnected, retrying...", file=sys.stderr) + while not process: + time.sleep(1) + process = create_telemetry_process(script, args_list) + process.stdin.write(f"{command}\n") + process.stdin.flush() + response = process.stdout.readline() + try: data = json.loads(response) # When run non-interactively, the response is wrapped with the command @@ -119,11 +142,11 @@ def query_telemetry(process, command): # The response should have exactly one key which is the command if len(data) == 1: # Extract the value, ignoring the key - return next(iter(data.values())) + return (process, next(iter(data.values()))) else: - return data + return (process, data) except (json.JSONDecodeError, KeyError): - return None + return (None, None) def print_connected_app(process): @@ -132,11 +155,12 @@ def print_connected_app(process): Args: process: The subprocess.Popen handle to the telemetry process """ - info = query_telemetry(process, "/info") + process, info = query_telemetry(process, "/info") if info and "pid" in info: app_name = get_app_name(info["pid"]) if app_name: print(f'Connected to application: "{app_name}"') + return process def expand_shortcuts(process, stat_specs): @@ -169,7 +193,7 @@ def expand_shortcuts(process, stat_specs): field = field_map.get(field, field) # Get list of ethernet devices - port_list = query_telemetry(process, "/ethdev/list") + process, port_list = query_telemetry(process, "/ethdev/list") if not isinstance(port_list, list): print(f"Error: Failed to get ethernet device list", file=sys.stderr) return None @@ -216,7 +240,7 @@ def validate_stats(process, stat_specs): return None, None # Query the stat once to validate it exists and is numeric - data = query_telemetry(process, command) + process, data = query_telemetry(process, command) if not isinstance(data, dict): print(f"Error: Command '{command}' did not return a dictionary", file=sys.stderr) return None, None @@ -276,7 +300,9 @@ def monitor_stats(process, args): current_values = [] total = 0 for i, (spec, command, field) in enumerate(parsed_specs): - data = query_telemetry(process, command) + process, data = query_telemetry(process, command) + if not data: + continue current_value = data[field] current_values.append(current_value) @@ -387,9 +413,11 @@ def main(): # Run dpdk-telemetry.py with pipes for stdin and stdout process = create_telemetry_process(telemetry_script, args_list) - - # Get and display the connected application name - print_connected_app(process) + if not process: + print("Waiting for connection to DPDK application...", file=sys.stderr) + while not process: + time.sleep(1) + process = create_telemetry_process(telemetry_script, args_list) # Monitor the requested statistics monitor_stats(process, args) -- 2.51.0