diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2025-12-01 17:18:43 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2025-12-01 17:18:43 -0800 |
| commit | cbc19b3229f1d509b45816a5afd42cc34c03d284 (patch) | |
| tree | e4401ff564f172f2a4a695ae3bca2b5d71f1452a | |
| parent | 4a18b6cd7c5703219a8256956904c47c0e7beade (diff) | |
| parent | 5cc1bddcfeb298fe7e67952a50894de8afa46db5 (diff) | |
| download | net-next-main.tar.gz | |
Carolina Jubran says:
====================
selftests: drv-net: Fix issues in devlink_rate_tc_bw.py
This series fixes issues in the devlink_rate_tc_bw.py selftest and
introduces a new Iperf3Runner that helps with measurement handling.
====================
Link: https://patch.msgid.link/20251130091938.4109055-1-cjubran@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
5 files changed, 157 insertions, 112 deletions
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 7c819fdfa10720..9c163ba6feee57 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -20,6 +20,7 @@ TEST_GEN_FILES := \ TEST_PROGS = \ csum.py \ devlink_port_split.py \ + devlink_rate_tc_bw.py \ devmem.py \ ethtool.sh \ ethtool_extended_state.sh \ diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py index ead6784d19104c..4e4faa9275bbc8 100755 --- a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -21,21 +21,21 @@ Test Cases: ---------- 1. test_no_tc_mapping_bandwidth: - Verifies that without TC mapping, bandwidth is NOT distributed according to - the configured 80/20 split between TC4 and TC3 - - This test should fail if bandwidth matches the 80/20 split without TC + the configured 20/80 split between TC3 and TC4 + - This test should fail if bandwidth matches the 20/80 split without TC mapping - - Expected: Bandwidth should NOT be distributed as 80/20 + - Expected: Bandwidth should NOT be distributed as 20/80 2. test_tc_mapping_bandwidth: - Configures TC mapping using mqprio qdisc - Verifies that with TC mapping, bandwidth IS distributed according to the - configured 80/20 split between TC3 and TC4 - - Expected: Bandwidth should be distributed as 80/20 + configured 20/80 split between TC3 and TC4 + - Expected: Bandwidth should be distributed as 20/80 Bandwidth Distribution: ---------------------- -- TC3 (VLAN 101): Configured for 80% of total bandwidth -- TC4 (VLAN 102): Configured for 20% of total bandwidth +- TC3 (VLAN 101): Configured for 20% of total bandwidth +- TC4 (VLAN 102): Configured for 80% of total bandwidth - Total bandwidth: 1Gbps - Tolerance: +-12% @@ -64,43 +64,40 @@ from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from lib.py import NetDrvEpEnv, DevlinkFamily from lib.py import NlError from lib.py import cmd, defer, ethtool, ip +from lib.py import Iperf3Runner class BandwidthValidator: """ - Validates bandwidth totals and per-TC shares against expected values - with a tolerance. + Validates total bandwidth and individual shares with tolerance + relative to the overall total. """ - def __init__(self): + def __init__(self, shares): self.tolerance_percent = 12 - self.expected_total_gbps = 1.0 - self.total_min_expected = self.min_expected(self.expected_total_gbps) - self.total_max_expected = self.max_expected(self.expected_total_gbps) - self.tc_expected_percent = { - 3: 20.0, - 4: 80.0, - } + self.expected_total = sum(shares.values()) + self.bounds = {} + + for name, exp in shares.items(): + self.bounds[name] = (self.min_expected(exp), self.max_expected(exp)) def min_expected(self, value): """Calculates the minimum acceptable value based on tolerance.""" - return value - (value * self.tolerance_percent / 100) + return value - (self.expected_total * self.tolerance_percent / 100) def max_expected(self, value): """Calculates the maximum acceptable value based on tolerance.""" - return value + (value * self.tolerance_percent / 100) - - def bound(self, expected, value): - """Returns True if value is within expected tolerance.""" - return self.min_expected(expected) <= value <= self.max_expected(expected) + return value + (self.expected_total * self.tolerance_percent / 100) - def tc_bandwidth_bound(self, value, tc_ix): + def bound(self, values): """ - Returns True if the given bandwidth value is within tolerance - for the TC's expected bandwidth. + Return True if all given values fall within tolerance. """ - expected = self.tc_expected_percent[tc_ix] - return self.bound(expected, value) + for name, value in values.items(): + low, high = self.bounds[name] + if not low <= value <= high: + return False + return True def setup_vf(cfg, set_tc_mapping=True): @@ -116,8 +113,8 @@ def setup_vf(cfg, set_tc_mapping=True): except Exception as exc: raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc try: - cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") - defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True) + defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True) except Exception as exc: raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc @@ -139,8 +136,8 @@ def setup_vlans_on_vf(vf_ifc): Sets up two VLAN interfaces on the given VF, each mapped to a different TC. """ vlan_configs = [ - {"vlan_id": 101, "tc": 3, "ip": "198.51.100.2"}, - {"vlan_id": 102, "tc": 4, "ip": "198.51.100.10"}, + {"vlan_id": 101, "tc": 3, "ip": "198.51.100.1"}, + {"vlan_id": 102, "tc": 4, "ip": "198.51.100.9"}, ] for config in vlan_configs: @@ -224,13 +221,13 @@ def setup_devlink_rate(cfg): raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc -def setup_remote_server(cfg): +def setup_remote_vlans(cfg): """ - Sets up VLAN interfaces and starts iperf3 servers on the remote side. + Sets up VLAN interfaces on the remote side. """ remote_dev = cfg.remote_ifname vlan_ids = [101, 102] - remote_ips = ["198.51.100.1", "198.51.100.9"] + remote_ips = ["198.51.100.2", "198.51.100.10"] for vlan_id, ip_addr in zip(vlan_ids, remote_ips): vlan_dev = f"{remote_dev}.{vlan_id}" @@ -238,14 +235,13 @@ def setup_remote_server(cfg): f"type vlan id {vlan_id}", host=cfg.remote) cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote) cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote) - cmd(f"iperf3 -s -1 -B {ip_addr}",background=True, host=cfg.remote) defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote) def setup_test_environment(cfg, set_tc_mapping=True): """ Sets up the complete test environment including VF creation, VLANs, - bridge configuration, devlink rate setup, and the remote server. + bridge configuration and devlink rate setup. """ vf_ifc = setup_vf(cfg, set_tc_mapping) ksft_pr(f"Created VF interface: {vf_ifc}") @@ -256,51 +252,39 @@ def setup_test_environment(cfg, set_tc_mapping=True): setup_bridge(cfg) setup_devlink_rate(cfg) - setup_remote_server(cfg) - time.sleep(2) + setup_remote_vlans(cfg) -def run_iperf_client(server_ip, local_ip, barrier, min_expected_gbps=0.1): +def measure_bandwidth(cfg, server_ip, client_ip, barrier): """ - Runs a single iperf3 client instance, binding to the given local IP. - Waits on a barrier to synchronize with other threads. + Synchronizes with peers and runs an iperf3-based bandwidth measurement + between the given endpoints. Returns average Gbps. """ + runner = Iperf3Runner(cfg, server_ip=server_ip, client_ip=client_ip) try: barrier.wait(timeout=10) except Exception as exc: raise KsftFailEx("iperf3 barrier wait timed") from exc - iperf_cmd = ["iperf3", "-c", server_ip, "-B", local_ip, "-J"] - result = subprocess.run(iperf_cmd, capture_output=True, text=True, - check=True) - try: - output = json.loads(result.stdout) - bits_per_second = output["end"]["sum_received"]["bits_per_second"] - gbps = bits_per_second / 1e9 - if gbps < min_expected_gbps: - ksft_pr( - f"iperf3 bandwidth too low: {gbps:.2f} Gbps " - f"(expected ≥ {min_expected_gbps} Gbps)" - ) - return None - return gbps - except json.JSONDecodeError as exc: - ksft_pr(f"Failed to parse iperf3 JSON output: {exc}") - return None + bw_gbps = runner.measure_bandwidth(reverse=True) + except Exception as exc: + raise KsftFailEx("iperf3 bandwidth measurement failed") from exc + + return bw_gbps -def run_bandwidth_test(): +def run_bandwidth_test(cfg): """ - Launches iperf3 client threads for each VLAN/TC pair and collects results. + Runs parallel bandwidth measurements for each VLAN/TC pair and collects results. """ - def _run_iperf_client_thread(server_ip, local_ip, results, barrier, tc_ix): - results[tc_ix] = run_iperf_client(server_ip, local_ip, barrier) + def _run_measure_bandwidth_thread(local_ip, remote_ip, results, barrier, tc_ix): + results[tc_ix] = measure_bandwidth(cfg, local_ip, remote_ip, barrier) vf_vlan_data = [ # (local_ip, remote_ip, TC) - ("198.51.100.2", "198.51.100.1", 3), - ("198.51.100.10", "198.51.100.9", 4), + ("198.51.100.1", "198.51.100.2", 3), + ("198.51.100.9", "198.51.100.10", 4), ] results = {} @@ -309,8 +293,8 @@ def run_bandwidth_test(): for local_ip, remote_ip, tc_ix in vf_vlan_data: thread = threading.Thread( - target=_run_iperf_client_thread, - args=(remote_ip, local_ip, results, start_barrier, tc_ix) + target=_run_measure_bandwidth_thread, + args=(local_ip, remote_ip, results, start_barrier, tc_ix) ) thread.start() threads.append(thread) @@ -320,10 +304,11 @@ def run_bandwidth_test(): for tc_ix, tc_bw in results.items(): if tc_bw is None: - raise KsftFailEx("iperf3 client failed; cannot evaluate bandwidth") + raise KsftFailEx("iperf3 failed; cannot evaluate bandwidth") return results + def calculate_bandwidth_percentages(results): """ Calculates the percentage of total bandwidth received by TC3 and TC4. @@ -364,59 +349,48 @@ def verify_total_bandwidth(bw_data, validator): """ total = bw_data['total_bw'] - if validator.bound(validator.expected_total_gbps, total): + if validator.bound({"total": total}): return - if total < validator.total_min_expected: + low, high = validator.bounds["total"] + + if total < low: raise KsftSkipEx( f"Total bandwidth {total:.2f} Gbps < minimum " - f"{validator.total_min_expected:.2f} Gbps; " - f"parent tx_max ({validator.expected_total_gbps:.1f} G) " + f"{low:.2f} Gbps; " + f"parent tx_max ({validator.expected_total:.1f} G) " f"not reached, cannot validate share" ) raise KsftFailEx( f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling " - f"{validator.total_max_expected:.2f} Gbps " - f"(VF tx_max set to {validator.expected_total_gbps:.1f} G)" + f"{high:.2f} Gbps " + f"(VF tx_max set to {validator.expected_total:.1f} G)" ) -def check_bandwidth_distribution(bw_data, validator): - """ - Checks whether the measured TC3 and TC4 bandwidth percentages - fall within their expected tolerance ranges. - - Returns: - bool: True if both TC3 and TC4 percentages are within bounds. - """ - tc3_valid = validator.tc_bandwidth_bound(bw_data['tc3_percentage'], 3) - tc4_valid = validator.tc_bandwidth_bound(bw_data['tc4_percentage'], 4) - - return tc3_valid and tc4_valid - - def run_bandwidth_distribution_test(cfg, set_tc_mapping): """ - Runs parallel iperf3 tests for both TCs and collects results. + Runs parallel bandwidth measurements for both TCs and collects results. """ setup_test_environment(cfg, set_tc_mapping) - bandwidths = run_bandwidth_test() + bandwidths = run_bandwidth_test(cfg) bw_data = calculate_bandwidth_percentages(bandwidths) test_name = "with TC mapping" if set_tc_mapping else "without TC mapping" print_bandwidth_results(bw_data, test_name) - verify_total_bandwidth(bw_data, cfg.bw_validator) + verify_total_bandwidth(bw_data, cfg.traffic_bw_validator) - return check_bandwidth_distribution(bw_data, cfg.bw_validator) + return cfg.tc_bw_validator.bound({"tc3": bw_data['tc3_percentage'], + "tc4": bw_data['tc4_percentage']}) def test_no_tc_mapping_bandwidth(cfg): """ - Verifies that bandwidth is not split 80/20 without traffic class mapping. + Verifies that bandwidth is not split 20/80 without traffic class mapping. """ - pass_bw_msg = "Bandwidth is NOT distributed as 80/20 without TC mapping" - fail_bw_msg = "Bandwidth matched 80/20 split without TC mapping" + pass_bw_msg = "Bandwidth is NOT distributed as 20/80 without TC mapping" + fail_bw_msg = "Bandwidth matched 20/80 split without TC mapping" is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout if run_bandwidth_distribution_test(cfg, set_tc_mapping=False): @@ -430,13 +404,13 @@ def test_no_tc_mapping_bandwidth(cfg): def test_tc_mapping_bandwidth(cfg): """ - Verifies that bandwidth is correctly split 80/20 between TC3 and TC4 + Verifies that bandwidth is correctly split 20/80 between TC3 and TC4 when traffic class mapping is set. """ if run_bandwidth_distribution_test(cfg, set_tc_mapping=True): - ksft_pr("Bandwidth is distributed as 80/20 with TC mapping") + ksft_pr("Bandwidth is distributed as 20/80 with TC mapping") else: - raise KsftFailEx("Bandwidth did not match 80/20 split with TC mapping") + raise KsftFailEx("Bandwidth did not match 20/80 split with TC mapping") def main() -> None: @@ -451,9 +425,9 @@ def main() -> None: ) if not cfg.pci: raise KsftSkipEx("Could not get PCI address of the interface") - cfg.require_cmd("iperf3", local=True, remote=True) - cfg.bw_validator = BandwidthValidator() + cfg.traffic_bw_validator = BandwidthValidator({"total": 1}) + cfg.tc_bw_validator = BandwidthValidator({"tc3": 20, "tc4": 80}) cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth] diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index 0c61debf86fb8b..766bfc4ad84284 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -28,7 +28,7 @@ try: ksft_setup, ksft_variants, KsftNamedVariant from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none - from drivers.net.lib.py import GenerateTraffic, Remote + from drivers.net.lib.py import GenerateTraffic, Remote, Iperf3Runner from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", @@ -44,7 +44,8 @@ try: "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", "ksft_not_none", "ksft_not_none", - "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"] + "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote", + "Iperf3Runner"] except ModuleNotFoundError as e: print("Failed importing `net` library from kernel sources") print(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index d9d035634a3130..8b75faa9af6d06 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -44,10 +44,11 @@ try: "ksft_not_none", "ksft_not_none"] from .env import NetDrvEnv, NetDrvEpEnv - from .load import GenerateTraffic + from .load import GenerateTraffic, Iperf3Runner from .remote import Remote - __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"] + __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote", + "Iperf3Runner"] except ModuleNotFoundError as e: print("Failed importing `net` library from kernel sources") print(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index c4e808407cc448..f181fa2d38fca0 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -2,21 +2,89 @@ import re import time +import json from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen -class GenerateTraffic: - def __init__(self, env, port=None): - env.require_cmd("iperf3", local=True, remote=True) +class Iperf3Runner: + """ + Sets up and runs iperf3 traffic. + """ + def __init__(self, env, port=None, server_ip=None, client_ip=None): + env.require_cmd("iperf3", local=True, remote=True) self.env = env - self.port = rand_port() if port is None else port - self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + self.server_ip = server_ip + self.client_ip = client_ip + + def _build_server(self): + cmdline = f"iperf3 -s -1 -p {self.port}" + if self.server_ip: + cmdline += f" -B {self.server_ip}" + return cmdline + + def _build_client(self, streams, duration, reverse): + host = self.env.addr if self.server_ip is None else self.server_ip + cmdline = f"iperf3 -c {host} -p {self.port} -P {streams} -t {duration} -J" + if self.client_ip: + cmdline += f" -B {self.client_ip}" + if reverse: + cmdline += " --reverse" + return cmdline + + def start_server(self): + """ + Starts an iperf3 server with optional bind IP. + """ + cmdline = self._build_server() + proc = cmd(cmdline, background=True) wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", - background=True, host=env.remote) + return proc + + def start_client(self, background=False, streams=1, duration=10, reverse=False): + """ + Starts the iperf3 client with the configured options. + """ + cmdline = self._build_client(streams, duration, reverse) + return cmd(cmdline, background=background, host=self.env.remote) + + def measure_bandwidth(self, reverse=False): + """ + Runs an iperf3 measurement and returns the average bandwidth (Gbps). + Discards the first and last few reporting intervals and uses only the + middle part of the run where throughput is typically stable. + """ + self.start_server() + result = self.start_client(duration=10, reverse=reverse) + + if result.ret != 0: + raise RuntimeError("iperf3 failed to run successfully") + try: + out = json.loads(result.stdout) + except json.JSONDecodeError as exc: + raise ValueError("Failed to parse iperf3 JSON output") from exc + + intervals = out.get("intervals", []) + samples = [i["sum"]["bits_per_second"] / 1e9 for i in intervals] + if len(samples) < 10: + raise ValueError(f"iperf3 returned too few intervals: {len(samples)}") + # Discard potentially unstable first and last 3 seconds. + stable = samples[3:-3] + + avg = sum(stable) / len(stable) + + return avg + + +class GenerateTraffic: + def __init__(self, env, port=None): + self.env = env + self.runner = Iperf3Runner(env, port) + + self._iperf_server = self.runner.start_server() + self._iperf_client = self.runner.start_client(background=True, streams=16, duration=86400) # Wait for traffic to ramp up if not self._wait_pkts(pps=1000): @@ -61,7 +129,7 @@ class GenerateTraffic: def _wait_client_stopped(self, sleep=0.005, timeout=5): end = time.monotonic() + timeout - live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + live_port_pattern = re.compile(fr":{self.runner.port:04X} 0[^6] ") while time.monotonic() < end: data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout |