From b7fa5b5f34c0650d7cb67238524768a1d6284d22 Mon Sep 17 00:00:00 2001 From: Kenneth Cain Date: Wed, 19 Aug 2026 16:51:46 -0400 Subject: [PATCH 1/3] DAOS-19396 pool: mind pool_discard() dss_rpc_send() errors Experimental product code change on release/2.6 branch to *not* proceed to pool map update step of ds_pool_update_handler() for reintegration operations when the previous pool_discard() step got an error in dss_rpc_send() (e.g., a -DER_TIMEDOUT failure). This gives retries either by the MS host daos_engine dsc_pool_client or by the test program itself (re-issuing the dmg pool reintegrate command) a chance to wait out and possibly recover from whatever communication failures are occurring among some engines and the reintegrating engine. Signed-off-by: Kenneth Cain --- src/pool/srv_pool.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/pool/srv_pool.c b/src/pool/srv_pool.c index f55d2b7dcb1..49c2fabf519 100644 --- a/src/pool/srv_pool.c +++ b/src/pool/srv_pool.c @@ -7626,6 +7626,12 @@ pool_discard(crt_context_t ctx, struct pool_svc *svc, struct pool_target_addr_li ptdi_in->ptdi_addrs.ca_count = list->pta_number; uuid_copy(ptdi_in->ptdi_uuid, svc->ps_pool->sp_uuid); rc = dss_rpc_send(rpc); + /* No corpc aggregation callback is registered, so ptdo_rc cannot report a send error. */ + if (rc != 0) { + DL_ERROR(rc, DF_UUID ": dss_rpc_send POOL_TGT_DISCARD", + DP_UUID(svc->ps_pool->sp_uuid)); + D_GOTO(decref, rc); + } ptdi_out = crt_reply_get(rpc); D_ASSERT(ptdi_out != NULL); @@ -7634,6 +7640,7 @@ pool_discard(crt_context_t ctx, struct pool_svc *svc, struct pool_target_addr_li D_ERROR(DF_UUID": pool discard failed: rc: %d\n", DP_UUID(svc->ps_pool->sp_uuid), rc); +decref: crt_req_decref(rpc); out: From 27052dd145df736af0b884c8fa64b2967fdde5fc Mon Sep 17 00:00:00 2001 From: Kenneth Cain Date: Fri, 4 Sep 2026 12:06:42 -0400 Subject: [PATCH 2/3] add a rebuild_ec subtest 9 only test for CI repeat testing with/without a fix patch Skip-unit-tests: true Skip-fault-injection-test: true Test-tag: test_daos_rebuild_ec_subtest9 Test-repeat: 10 Signed-off-by: Kenneth Cain --- src/tests/ftest/daos_test/suite.py | 17 +++++++++++++++++ src/tests/ftest/daos_test/suite.yaml | 5 +++++ 2 files changed, 22 insertions(+) diff --git a/src/tests/ftest/daos_test/suite.py b/src/tests/ftest/daos_test/suite.py index f02d882f4ce..c2ce89eb66b 100644 --- a/src/tests/ftest/daos_test/suite.py +++ b/src/tests/ftest/daos_test/suite.py @@ -1,5 +1,6 @@ """ (C) Copyright 2018-2024 Intel Corporation. + (C) Copyright 2026 Hewlett Packard Enterprise Development LP SPDX-License-Identifier: BSD-2-Clause-Patent """ @@ -381,6 +382,22 @@ def test_daos_rebuild_ec(self): """ self.run_subtest() + def test_daos_rebuild_ec_subtest9(self): + """Jira ID: DAOS-1568 + + Test Description: + Run daos_test -S --subtests="9" + + Use cases: + Core tests for daos_test + + :avocado: tags=all,pr,daily_regression + :avocado: tags=hw,medium,provider + :avocado: tags=daos_test,daos_core_test + :avocado: tags=DaosCoreTest,test_daos_rebuild_ec_subtest9 + """ + self.run_subtest() + def test_daos_aggregate_ec(self): """Jira ID: DAOS-1568 diff --git a/src/tests/ftest/daos_test/suite.yaml b/src/tests/ftest/daos_test/suite.yaml index 15c3c40b8d7..06bac9c9e98 100644 --- a/src/tests/ftest/daos_test/suite.yaml +++ b/src/tests/ftest/daos_test/suite.yaml @@ -29,6 +29,7 @@ timeouts: test_daos_oid_allocator: 640 test_daos_checksum: 500 test_daos_rebuild_ec: 7200 + test_daos_rebuild_ec_subtest9: 600 test_daos_aggregate_ec: 200 test_daos_degraded_ec: 1900 test_daos_dedup: 220 @@ -109,6 +110,7 @@ daos_tests: test_daos_oid_allocator: 1 test_daos_checksum: 1 test_daos_rebuild_ec: 1 + test_daos_rebuild_ec_subtest9: 1 test_daos_aggregate_ec: 1 test_daos_degraded_ec: 1 test_daos_dedup: 1 @@ -137,6 +139,7 @@ daos_tests: test_daos_oid_allocator: DAOS_OID_Allocator test_daos_checksum: DAOS_Checksum test_daos_rebuild_ec: DAOS_Rebuild_EC + test_daos_rebuild_ec_subtest9: DAOS_Rebuild_EC_Subtest9 test_daos_aggregate_ec: DAOS_Aggregate_EC test_daos_degraded_ec: DAOS_Degraded_EC test_daos_dedup: DAOS_Dedup @@ -167,6 +170,7 @@ daos_tests: test_daos_oid_allocator: O test_daos_checksum: z test_daos_rebuild_ec: S + test_daos_rebuild_ec_subtest9: S test_daos_aggregate_ec: Z test_daos_degraded_ec: X test_daos_dedup: U @@ -175,6 +179,7 @@ daos_tests: args: test_daos_ec_io: -l"EC_4P2G1" test_daos_rebuild_ec: -s5 + test_daos_rebuild_ec_subtest9: -s5 --subtests="9" test_daos_md_replication: -s5 test_daos_degraded_mode: -s7 test_daos_drain_simple: -s3 From e372cb19e01ae5c56dafaa8c969ef7d701b74ab8 Mon Sep 17 00:00:00 2001 From: Kenneth Cain Date: Tue, 29 Sep 2026 08:10:00 -0400 Subject: [PATCH 3/3] Revert "add a rebuild_ec subtest 9 only test" This reverts commit 27052dd145df736af0b884c8fa64b2967fdde5fc. Features: pool --- src/tests/ftest/daos_test/suite.py | 17 ----------------- src/tests/ftest/daos_test/suite.yaml | 5 ----- 2 files changed, 22 deletions(-) diff --git a/src/tests/ftest/daos_test/suite.py b/src/tests/ftest/daos_test/suite.py index c2ce89eb66b..f02d882f4ce 100644 --- a/src/tests/ftest/daos_test/suite.py +++ b/src/tests/ftest/daos_test/suite.py @@ -1,6 +1,5 @@ """ (C) Copyright 2018-2024 Intel Corporation. - (C) Copyright 2026 Hewlett Packard Enterprise Development LP SPDX-License-Identifier: BSD-2-Clause-Patent """ @@ -382,22 +381,6 @@ def test_daos_rebuild_ec(self): """ self.run_subtest() - def test_daos_rebuild_ec_subtest9(self): - """Jira ID: DAOS-1568 - - Test Description: - Run daos_test -S --subtests="9" - - Use cases: - Core tests for daos_test - - :avocado: tags=all,pr,daily_regression - :avocado: tags=hw,medium,provider - :avocado: tags=daos_test,daos_core_test - :avocado: tags=DaosCoreTest,test_daos_rebuild_ec_subtest9 - """ - self.run_subtest() - def test_daos_aggregate_ec(self): """Jira ID: DAOS-1568 diff --git a/src/tests/ftest/daos_test/suite.yaml b/src/tests/ftest/daos_test/suite.yaml index 06bac9c9e98..15c3c40b8d7 100644 --- a/src/tests/ftest/daos_test/suite.yaml +++ b/src/tests/ftest/daos_test/suite.yaml @@ -29,7 +29,6 @@ timeouts: test_daos_oid_allocator: 640 test_daos_checksum: 500 test_daos_rebuild_ec: 7200 - test_daos_rebuild_ec_subtest9: 600 test_daos_aggregate_ec: 200 test_daos_degraded_ec: 1900 test_daos_dedup: 220 @@ -110,7 +109,6 @@ daos_tests: test_daos_oid_allocator: 1 test_daos_checksum: 1 test_daos_rebuild_ec: 1 - test_daos_rebuild_ec_subtest9: 1 test_daos_aggregate_ec: 1 test_daos_degraded_ec: 1 test_daos_dedup: 1 @@ -139,7 +137,6 @@ daos_tests: test_daos_oid_allocator: DAOS_OID_Allocator test_daos_checksum: DAOS_Checksum test_daos_rebuild_ec: DAOS_Rebuild_EC - test_daos_rebuild_ec_subtest9: DAOS_Rebuild_EC_Subtest9 test_daos_aggregate_ec: DAOS_Aggregate_EC test_daos_degraded_ec: DAOS_Degraded_EC test_daos_dedup: DAOS_Dedup @@ -170,7 +167,6 @@ daos_tests: test_daos_oid_allocator: O test_daos_checksum: z test_daos_rebuild_ec: S - test_daos_rebuild_ec_subtest9: S test_daos_aggregate_ec: Z test_daos_degraded_ec: X test_daos_dedup: U @@ -179,7 +175,6 @@ daos_tests: args: test_daos_ec_io: -l"EC_4P2G1" test_daos_rebuild_ec: -s5 - test_daos_rebuild_ec_subtest9: -s5 --subtests="9" test_daos_md_replication: -s5 test_daos_degraded_mode: -s7 test_daos_drain_simple: -s3