DAOS-13380 engine: test tgt_nr

src/control/server/ctl_storage_rpc_test.go

@@ -1569,7 +1569,10 @@ func TestServer_CtlSvc_StorageScan_PostEngineStart(t *testing.T) {
 			var engineCfgs []*engine.Config
 			for i, sc := range tc.storageCfgs {
 				log.Debugf("storage cfg contains bdevs %v for engine %d", sc.Bdevs(), i)
-				engineCfgs = append(engineCfgs, engine.MockConfig().WithStorage(sc...))
+				engineCfgs = append(engineCfgs,
+					engine.MockConfig().
+						WithStorage(sc...).
+						WithTargetCount(tc.engineTargetCount[i]))
 			}
 			sCfg := config.DefaultServer().WithEngines(engineCfgs...)
 			cs := mockControlService(t, log, sCfg, csbmbc, tc.smbc, tc.smsc)
@@ -1625,7 +1628,6 @@ func TestServer_CtlSvc_StorageScan_PostEngineStart(t *testing.T) {
 				}
 				te.setDrpcClient(newMockDrpcClient(dcc))
 				te._superblock.Rank = ranklist.NewRankPtr(uint32(idx + 1))
-				te.setTargetCount(tc.engineTargetCount[idx])
 				for _, tc := range te.storage.GetBdevConfigs() {
 					tc.Bdev.DeviceRoles.OptionBits = storage.OptionBits(storage.BdevRoleAll)
 				}

src/control/server/instance.go

@@ -338,14 +338,6 @@ func (ei *EngineInstance) setHugepageSz(hpSizeMb int) {
 	ei.runner.GetConfig().HugepageSz = hpSizeMb
 }
 
-// setTargetCount updates target count in engine config.
-func (ei *EngineInstance) setTargetCount(numTargets int) {
-	ei.Lock()
-	defer ei.Unlock()
-
-	ei.runner.GetConfig().TargetCount = numTargets
-}
-
 // GetTargetCount returns the target count set for this instance.
 func (ei *EngineInstance) GetTargetCount() int {
 	ei.RLock()

src/control/server/instance_exec.go

@@ -90,12 +90,6 @@ func (ei *EngineInstance) finishStartup(ctx context.Context, ready *srvpb.Notify
 	if err := ei.handleReady(ctx, ready); err != nil {
 		return err
 	}
-	// update engine target count to reflect allocated number of targets, not number requested
-	// when starting
-	// NOTE: Engine mem_size passed on engine invocation is based on the number of targets
-	//       requested in config so if number of targets allocated doesn't match the number of
-	//       targets requested the mem_size value may be inappropriate.
-	ei.setTargetCount(int(ready.GetNtgts()))
 
 	ei.ready.SetTrue()
 

src/engine/init.c

@@ -40,8 +40,7 @@
 static char		modules[MAX_MODULE_OPTIONS + 1];
 
 /**
- * Number of target threads the user would like to start
- * 0 means default value, see dss_tgt_nr_get();
+ * Number of target threads the user would like to start.
  */
 static unsigned int	nr_threads;
 
@@ -250,56 +249,51 @@ modules_load(void)
 	return rc;
 }
 
+static unsigned int
+ncores_needed(unsigned int tgt_nr, unsigned int nr_helpers)
+{
+	return DAOS_TGT0_OFFSET + tgt_nr + nr_helpers;
+}
+
 /**
- * Get the appropriate number of main XS based on the number of cores and
- * passed in preferred number of threads.
+ * Check if the #targets and #nr_xs_helpers is valid to start server, the #nr_xs_helpers possibly
+ * be reduced.
  */
 static int
-dss_tgt_nr_get(unsigned int ncores, unsigned int nr, bool oversubscribe)
+dss_tgt_nr_check(unsigned int ncores, unsigned int tgt_nr, bool oversubscribe)
 {
-	int tgt_nr;
-
 	D_ASSERT(ncores >= 1);
 
 	/* at most 2 helper XS per target */
-	if (dss_tgt_offload_xs_nr > 2 * nr)
-		dss_tgt_offload_xs_nr = 2 * nr;
-	else if (dss_tgt_offload_xs_nr == 0)
+	if (dss_tgt_offload_xs_nr > 2 * tgt_nr) {
+		D_PRINT("#nr_xs_helpers(%d) cannot exceed 2 times #targets (2 x %d = %d).\n",
+			dss_tgt_offload_xs_nr, tgt_nr, 2 * tgt_nr);
+		dss_tgt_offload_xs_nr = 2 * tgt_nr;
+	} else if (dss_tgt_offload_xs_nr == 0) {
 		D_WARN("Suggest to config at least 1 helper XS per DAOS engine\n");
+	}
 
-	/* Each system XS uses one core, and  with dss_tgt_offload_xs_nr
-	 * offload XS. Calculate the tgt_nr as the number of main XS based
-	 * on number of cores.
-	 */
-retry:
-	tgt_nr = ncores - DAOS_TGT0_OFFSET - dss_tgt_offload_xs_nr;
-	if (tgt_nr <= 0)
-		tgt_nr = 1;
-
-	/* If user requires less target threads then set it as dss_tgt_nr,
-	 * if user oversubscribes, then:
-	 *      . if oversubscribe is enabled, use the required number
-	 *      . if oversubscribe is disabled(default),
-	 *        use the number calculated above
-	 * Note: oversubscribing  may hurt performance.
-	 */
-	if (nr >= 1 && ((nr < tgt_nr) || oversubscribe)) {
-		tgt_nr = nr;
-		if (dss_tgt_offload_xs_nr > 2 * tgt_nr)
-			dss_tgt_offload_xs_nr = 2 * tgt_nr;
-	} else if (dss_tgt_offload_xs_nr > 2 * tgt_nr) {
-		dss_tgt_offload_xs_nr--;
-		goto retry;
+	if (oversubscribe) {
+		if (ncores_needed(tgt_nr, dss_tgt_offload_xs_nr) > ncores)
+			D_PRINT("Force to start engine with %d targets %d xs_helpers on %d cores("
+				"%d cores reserved for system service).\n",
+				tgt_nr, dss_tgt_offload_xs_nr, ncores, DAOS_TGT0_OFFSET);
+		goto out;
 	}
 
-	if (tgt_nr != nr)
-		D_PRINT("%d target XS(xstream) requested (#cores %d); "
-			"use (%d) target XS\n", nr, ncores, tgt_nr);
+	if (ncores_needed(tgt_nr, dss_tgt_offload_xs_nr) > ncores) {
+		D_ERROR("cannot start engine with %d targets %d xs_helpers on %d cores, may try "
+			"with DAOS_TARGET_OVERSUBSCRIBE=1 or reduce #targets/#nr_xs_helpers("
+			"%d cores reserved for system service).\n",
+			tgt_nr, dss_tgt_offload_xs_nr, ncores, DAOS_TGT0_OFFSET);
+		return -DER_INVAL;
+	}
 
+out:
 	if (dss_tgt_offload_xs_nr % tgt_nr != 0)
 		dss_helper_pool = true;
 
-	return tgt_nr;
+	return 0;
 }
 
 static int
@@ -321,35 +315,30 @@ dss_topo_init()
 	depth = hwloc_get_type_depth(dss_topo, HWLOC_OBJ_NUMANODE);
 	numa_node_nr = hwloc_get_nbobjs_by_depth(dss_topo, depth);
 	d_getenv_bool("DAOS_TARGET_OVERSUBSCRIBE", &tgt_oversub);
+	dss_tgt_nr = nr_threads;
 
 	/* if no NUMA node was specified, or NUMA data unavailable */
 	/* fall back to the legacy core allocation algorithm */
 	if (dss_numa_node == -1 || numa_node_nr <= 0) {
 		D_PRINT("Using legacy core allocation algorithm\n");
-		dss_tgt_nr = dss_tgt_nr_get(dss_core_nr, nr_threads,
-					    tgt_oversub);
-
 		if (dss_core_offset >= dss_core_nr) {
-			D_ERROR("invalid dss_core_offset %u "
-				"(set by \"-f\" option),"
-				" should within range [0, %u]",
+			D_ERROR("invalid dss_core_offset %u (set by \"-f\" option), should within "
+				"range [0, %u]\n",
 				dss_core_offset, dss_core_nr - 1);
 			return -DER_INVAL;
 		}
-		return 0;
+
+		return dss_tgt_nr_check(dss_core_nr, dss_tgt_nr, tgt_oversub);
 	}
 
 	if (dss_numa_node > numa_node_nr) {
-		D_ERROR("Invalid NUMA node selected. "
-			"Must be no larger than %d\n",
-			numa_node_nr);
+		D_ERROR("Invalid NUMA node selected. Must be no larger than %d\n", numa_node_nr);
 		return -DER_INVAL;
 	}
 
 	numa_obj = hwloc_get_obj_by_depth(dss_topo, depth, dss_numa_node);
 	if (numa_obj == NULL) {
-		D_ERROR("NUMA node %d was not found in the topology",
-			dss_numa_node);
+		D_ERROR("NUMA node %d was not found in the topology\n", dss_numa_node);
 		return -DER_INVAL;
 	}
 
@@ -381,17 +370,15 @@ dss_topo_init()
 	hwloc_bitmap_asprintf(&cpuset, core_allocation_bitmap);
 	free(cpuset);
 
-	dss_tgt_nr = dss_tgt_nr_get(dss_num_cores_numa_node, nr_threads,
-				    tgt_oversub);
 	if (dss_core_offset >= dss_num_cores_numa_node) {
-		D_ERROR("invalid dss_core_offset %d (set by \"-f\" option), "
-			"should within range [0, %d]", dss_core_offset,
-			dss_num_cores_numa_node - 1);
+		D_ERROR("invalid dss_core_offset %d (set by \"-f\" option), should within range "
+			"[0, %d]\n",
+			dss_core_offset, dss_num_cores_numa_node - 1);
 		return -DER_INVAL;
 	}
-
 	D_PRINT("Using NUMA core allocation algorithm\n");
-	return 0;
+
+	return dss_tgt_nr_check(dss_num_cores_numa_node, dss_tgt_nr, tgt_oversub);
 }
 
 static ABT_mutex		server_init_state_mutex;

src/tests/ftest/control/daos_agent_config.py

@@ -3,7 +3,7 @@
 
   SPDX-License-Identifier: BSD-2-Clause-Patent
 """
-from apricot import TestWithServers
+from apricot import TestWithServers, skipForTicket
 from agent_utils import include_local_host
 from exception_utils import CommandFailure
 
@@ -23,6 +23,7 @@ def __init__(self, *args, **kwargs):
         self.setup_start_agents = False
         self.setup_start_servers = False
 
+    @skipForTicket("DAOS-13380")
     def test_daos_agent_config_basic(self):
         """
         JIRA ID: DAOS-1508

src/tests/ftest/control/daos_control_config.py

@@ -5,7 +5,7 @@
 """
 
 
-from apricot import TestWithServers
+from apricot import TestWithServers, skipForTicket
 from exception_utils import CommandFailure
 
 
@@ -16,6 +16,7 @@ class DaosControlConfigTest(TestWithServers):
     :avocado: recursive
     """
 
+    @skipForTicket("DAOS-13380")
     def test_daos_control_config_basic(self):
         """
         JIRA ID: DAOS-1508

src/tests/ftest/control/daos_system_query.yaml

@@ -7,6 +7,7 @@ server_config:
   engines:
     0:
       pinned_numa_node: 0
+      targets: 4
       nr_xs_helpers: 1
       fabric_iface_port: 31416
       log_file: daos_server0.log

src/tests/ftest/control/dmg_pool_query_test.yaml

@@ -8,7 +8,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
-      targets: 8
+      targets: 4
       storage: auto
   system_ram_reserved: 64
 pool:
@@ -26,8 +26,8 @@ ior:
 
 exp_vals:
   pool_status: 0
-  total_targets: 8
-  active_targets: 8
+  total_targets: 4
+  active_targets: 4
   total_engines: 1
   disabled_targets: 0
   version: 1

src/tests/ftest/control/dmg_server_set_logmasks.yaml

@@ -6,6 +6,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
+      targets: 4
       storage:
         0:
           class: ram

src/tests/ftest/control/ms_resilience.py

@@ -8,7 +8,7 @@
 
 from ClusterShell.NodeSet import NodeSet
 
-from apricot import TestWithServers
+from apricot import TestWithServers, skipForTicket
 from run_utils import stop_processes
 
 
@@ -323,6 +323,7 @@ def test_ms_resilience_2(self):
         # Run test cases
         self.verify_retained_quorum(2)
 
+    @skipForTicket("DAOS-13380")
     def test_ms_resilience_3(self):
         """
         JIRA ID: DAOS-3798
@@ -340,6 +341,7 @@ def test_ms_resilience_3(self):
         # Run test case
         self.verify_regained_quorum(1)
 
+    @skipForTicket("DAOS-13380")
     def test_ms_resilience_4(self):
         """
         JIRA ID: DAOS-3798

src/tests/ftest/control/version.py

@@ -6,7 +6,7 @@
 import re
 import json
 
-from apricot import TestWithServers
+from apricot import TestWithServers, skipForTicket
 from general_utils import run_pcmd, report_errors
 from server_utils_base import DaosServerCommandRunner
 
@@ -26,6 +26,7 @@ def __init__(self, *args, **kwargs):
         self.setup_start_servers = False
         self.setup_start_agents = False
 
+    @skipForTicket("DAOS-13380")
     def test_version(self):
         """Verify version number for dmg, daos, daos_server, and daos_agent against RPM.
 

src/tests/ftest/dfuse/daos_build.py

@@ -9,6 +9,7 @@
 
 from dfuse_test_base import DfuseTestBase
 from run_utils import run_remote
+from apricot import skipForTicket
 
 
 class DaosBuild(DfuseTestBase):
@@ -49,6 +50,7 @@ def test_dfuse_daos_build_wt(self):
         """
         self.run_build_test("writethrough")
 
+    @skipForTicket("DAOS-13380")
     def test_dfuse_daos_build_wt_il(self):
         """This test builds DAOS on a dfuse filesystem.
 

src/tests/ftest/harness/core_files.yaml

@@ -5,6 +5,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
+      targets: 4
       storage:
         0:
           class: ram

src/tests/ftest/pool/create_all_vm.yaml

@@ -32,7 +32,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
-      targets: 5
+      targets: 4
       nr_xs_helpers: 0
       storage:
         0:

src/tests/ftest/pool/query_attribute.yaml

@@ -6,7 +6,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
-      targets: 8
+      targets: 4
       nr_xs_helpers: 0
       storage:
         0:

src/tests/ftest/server/daos_server_config.yaml

@@ -164,11 +164,6 @@ server_config_val: !mux
       - "nr_xs_helpers"
       - -10000
       - "PASS"
-  targets_negative:
-    config_val:
-      - "targets"
-      - -1
-      - "PASS"
   targets_str:
     config_val:
       - "targets"

src/tests/ftest/telemetry/dkey_akey_enum_punch.yaml

@@ -7,7 +7,7 @@ server_config:
   engines_per_host: 1
   engines:
     0:
-      targets: 8
+      targets: 4
       nr_xs_helpers: 0
       storage:
         0:

utils/nlt_server.yaml

@@ -14,6 +14,7 @@ engines:
       - DAOS_MD_CAP=1024
       - DAOS_STRICT_SHUTDOWN=1
       - CRT_CTX_SHARE_ADDR=0
+      - DAOS_TARGET_OVERSUBSCRIBE=1
       - ABT_STACK_OVERFLOW_CHECK=mprotect
     storage:
       -