selftests: drv-net: rss: Add retries to test_rss_key_indir to reduce flakes

The test generates 16 flows, and verifies that traffic is distributed
across two queues via the NICs RSS indirection table. The likelihood of the
flows skewing to a single queue is high, so we retry sending traffic up to
3 times.

Alternatively, we could increase the number of generated flows. But
debug kernels may struggle to ramp this many flows.

During manual testing, the test passed for 10,000 consecutive runs.

Signed-off-by: Dimitri Daskalakis <dimitri.daskalakis1@gmail.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://patch.msgid.link/20260309204215.2110486-1-dimitri.daskalakis1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index d7cb3030636838e316ee025192388867dc07d3f0..51f4e7bc3e5d8bdc96c031866b8f2becdb291eff 100755 (executable)
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -166,9 +166,17 @@ def test_rss_key_indir(cfg):
     ksft_eq(1, max(data['rss-indirection-table']))
 
     # Check we only get traffic on the first 2 queues
-    cnts = _get_rx_cnts(cfg)
-    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
-    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    # Retry a few times in case the flows skew to a single queue.
+    attempts = 3
+    for attempt in range(attempts):
+        cnts = _get_rx_cnts(cfg)
+        GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+        cnts = _get_rx_cnts(cfg, prev=cnts)
+        if cnts[0] >= 5000 and cnts[1] >= 5000:
+            break
+        ksft_pr(f"Skewed queue distribution, attempt {attempt + 1}/{attempts}: " + str(cnts))
+
     # 2 queues, 20k packets, must be at least 5k per queue
     ksft_ge(cnts[0], 5000, "traffic on main context (1/2): " + str(cnts))
     ksft_ge(cnts[1], 5000, "traffic on main context (2/2): " + str(cnts))
@@ -178,9 +186,18 @@ def test_rss_key_indir(cfg):
     # Restore, and check traffic gets spread again
     reset_indir.exec()
 
-    cnts = _get_rx_cnts(cfg)
-    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
-    cnts = _get_rx_cnts(cfg, prev=cnts)
+    for attempt in range(attempts):
+        cnts = _get_rx_cnts(cfg)
+        GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+        cnts = _get_rx_cnts(cfg, prev=cnts)
+        if qcnt > 4:
+            if sum(cnts[:2]) < sum(cnts[2:]):
+                break
+        else:
+            if cnts[2] >= 3500:
+                break
+        ksft_pr(f"Skewed queue distribution, attempt {attempt + 1}/{attempts}: " + str(cnts))
+
     if qcnt > 4:
         # First two queues get less traffic than all the rest
         ksft_lt(sum(cnts[:2]), sum(cnts[2:]),