Dev/refactor create seal shard

.github/workflows/conan_build.yml

@@ -5,9 +5,11 @@ on:
   push:
     branches:
       - stable/v4.x
+      - dev/refactor_create_seal_shard
   pull_request:
     branches:
       - stable/v4.x
+      - dev/refactor_create_seal_shard
 
 jobs:
   Build:

.github/workflows/version_change_check.yml

@@ -5,7 +5,7 @@ on:
     types: [opened, edited, synchronize]
     branches:
       - stable/v4.x
-
+      - dev/refactor_create_seal_shard
 jobs:
   check-file:
     runs-on: ubuntu-latest

.jenkins/Jenkinsfile

@@ -65,6 +65,9 @@ pipeline {
                     conan create ${BUILD_MISSING} -s:h build_type=RelWithDebInfo -o sisl/*:malloc_impl=tcmalloc ${CONAN_FLAGS} . ; \
                     "
             }
+             post {
+                       failure { script { sleep 3600000  } }
+                   }
         }
 
         stage("Deploy") {
@@ -82,7 +85,7 @@ pipeline {
                expression { (env.BRANCH_NAME == "${TARGET_BRANCH}") }
                expression { (!"${upstream_triggered}") || ("${upstream_triggered}" == "") }
             } }
-        
+
             stages {
                 stage('StorageManager') {
                     steps {

conanfile.py

@@ -10,7 +10,7 @@
 
 class HomeObjectConan(ConanFile):
     name = "homeobject"
-    version = "4.1.18"
+    version = "4.2.3"
 
     homepage = "https://github.com/eBay/HomeObject"
     description = "Blob Store built on HomeStore"

src/include/homeobject/shard_manager.hpp

@@ -35,13 +35,14 @@ struct ShardInfo {
     shard_id_t id;
     pg_id_t placement_group;
     State state;
-    uint64_t lsn; // created_lsn
+    uint64_t create_lsn;
     uint64_t created_time;
     uint64_t last_modified_time;
     uint64_t available_capacity_bytes;
     uint64_t total_capacity_bytes;
     std::optional< peer_id_t > current_leader{std::nullopt};
     uint8_t meta[meta_length]{};
+    uint64_t sealed_lsn{INT64_MAX}; // appended after all v2 fields for forward compat
 
     auto operator<=>(ShardInfo const& rhs) const { return id <=> rhs.id; }
     auto operator==(ShardInfo const& rhs) const { return id == rhs.id; }
@@ -57,7 +58,8 @@ class ShardManager : public Manager< ShardError > {
 
     virtual AsyncResult< ShardInfo > get_shard(shard_id_t id, trace_id_t tid = 0) const = 0;
     virtual AsyncResult< InfoList > list_shards(pg_id_t id, trace_id_t tid = 0) const = 0;
-    virtual AsyncResult< ShardInfo > create_shard(pg_id_t pg_owner, uint64_t size_bytes, std::string meta, trace_id_t tid = 0) = 0;
+    virtual AsyncResult< ShardInfo > create_shard(pg_id_t pg_owner, uint64_t size_bytes, std::string meta,
+                                                  trace_id_t tid = 0) = 0;
     virtual AsyncResult< ShardInfo > seal_shard(shard_id_t id, trace_id_t tid = 0) = 0;
 };
 

src/lib/homestore_backend/CMakeLists.txt

@@ -45,6 +45,7 @@ settings_gen_cpp(
     hs_backend_config.fbs
     resync_pg_data.fbs
     resync_shard_data.fbs
+    legacy_resync_shard_data.fbs
     resync_blob_data.fbs
   )
 
@@ -55,28 +56,28 @@ add_subdirectory(tests)
 add_executable(homestore_test_pg)
 target_sources(homestore_test_pg PRIVATE $<TARGET_OBJECTS:homestore_tests_pg>)
 target_link_libraries(homestore_test_pg PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
-add_test(NAME HomestoreTestPg COMMAND homestore_test_pg -csv error --executor immediate --config_path ./
+add_test(NAME HomestoreTestPg COMMAND homestore_test_pg --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance:0
         --override_config homestore_config.consensus.max_grpc_message_size:138412032)
 
 add_executable(homestore_test_shard)
 target_sources(homestore_test_shard PRIVATE $<TARGET_OBJECTS:homestore_tests_shard>)
 target_link_libraries(homestore_test_shard PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
-add_test(NAME HomestoreTestShard COMMAND homestore_test_shard -csv error --executor immediate --config_path ./
+add_test(NAME HomestoreTestShard COMMAND homestore_test_shard --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance:0
         --override_config homestore_config.consensus.max_grpc_message_size:138412032)
 
 add_executable(homestore_test_blob)
 target_sources(homestore_test_blob PRIVATE $<TARGET_OBJECTS:homestore_tests_blob>)
 target_link_libraries(homestore_test_blob PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
-add_test(NAME HomestoreTestBlob COMMAND homestore_test_blob -csv error --executor immediate --config_path ./
+add_test(NAME HomestoreTestBlob COMMAND homestore_test_blob --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance:0
         --override_config homestore_config.consensus.max_grpc_message_size:138412032)
 
 add_executable(homestore_test_misc)
 target_sources(homestore_test_misc PRIVATE $<TARGET_OBJECTS:homestore_tests_misc>)
 target_link_libraries(homestore_test_misc PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
-add_test(NAME HomestoreTestMisc COMMAND homestore_test_misc -csv error --executor immediate --config_path ./
+add_test(NAME HomestoreTestMisc COMMAND homestore_test_misc --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=0
         --override_config homestore_config.consensus.max_grpc_message_size=138412032
         --override_config hs_backend_config.enable_gc=false)
@@ -86,7 +87,7 @@ add_executable(homestore_test_dynamic)
 target_sources(homestore_test_dynamic PRIVATE $<TARGET_OBJECTS:homestore_tests_dynamic>)
 target_link_libraries(homestore_test_dynamic PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
 add_test(NAME HomestoreTestReplaceMember
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=0
         --override_config homestore_config.generic.repl_dev_cleanup_interval_sec=5
         --override_config homestore_config.consensus.max_grpc_message_size=138412032
@@ -95,7 +96,7 @@ add_test(NAME HomestoreTestReplaceMember
         --gtest_filter=HomeObjectFixture.ReplaceMember)
 # To test both baseline & incremental resync functionality, we use 13 to minimize the likelihood of it being a divisor of the total LSN (currently 30)
 add_test(NAME HomestoreTestReplaceMemberWithBaselineResync
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=13
         --override_config homestore_config.consensus.num_reserved_log_items=13
         --override_config homestore_config.resource_limits.raft_logstore_reserve_threshold=13
@@ -106,7 +107,7 @@ add_test(NAME HomestoreTestReplaceMemberWithBaselineResync
         --override_config homestore_config.consensus.laggy_threshold=2000
         --gtest_filter=HomeObjectFixture.ReplaceMember)
 add_test(NAME HomestoreTestBaselineResync
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=13
         --override_config homestore_config.consensus.num_reserved_log_items=13
         --override_config homestore_config.resource_limits.raft_logstore_reserve_threshold=13
@@ -117,7 +118,7 @@ add_test(NAME HomestoreTestBaselineResync
         --override_config homestore_config.consensus.laggy_threshold=2000
         --gtest_filter=HomeObjectFixture.BaselineResync*)
 add_test(NAME HomestoreResyncTestWithFollowerRestart
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=13
         --override_config homestore_config.consensus.num_reserved_log_items=13
         --override_config homestore_config.resource_limits.raft_logstore_reserve_threshold=13
@@ -128,7 +129,7 @@ add_test(NAME HomestoreResyncTestWithFollowerRestart
         --override_config homestore_config.consensus.laggy_threshold=2000
         --gtest_filter=HomeObjectFixture.RestartFollower*)
 add_test(NAME HomestoreResyncTestWithLeaderRestart
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config homestore_config.consensus.snapshot_freq_distance=13
         --override_config homestore_config.consensus.num_reserved_log_items=13
         --override_config homestore_config.resource_limits.raft_logstore_reserve_threshold=13
@@ -139,7 +140,7 @@ add_test(NAME HomestoreResyncTestWithLeaderRestart
         --override_config homestore_config.consensus.laggy_threshold=2000
         --gtest_filter=HomeObjectFixture.RestartLeader*)
 #add_test(NAME HomestoreReplaceMemberRollbackTest
-#        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+#        COMMAND homestore_test_dynamic --executor immediate --config_path ./
 #        --override_config homestore_config.consensus.snapshot_freq_distance=13
 #        --override_config homestore_config.consensus.num_reserved_log_items=13
 #        --override_config homestore_config.resource_limits.raft_logstore_reserve_threshold=13
@@ -152,16 +153,41 @@ add_test(NAME HomestoreResyncTestWithLeaderRestart
 
 # GC tests
 add_test(NAME FetchDataWithOriginatorGC
-        COMMAND homestore_test_dynamic -csv error --executor immediate --config_path ./
+        COMMAND homestore_test_dynamic --executor immediate --config_path ./
         --override_config hs_backend_config.enable_gc=true
         --override_config hs_backend_config.gc_enable_read_verify=true
         --gtest_filter=HomeObjectFixture.FetchDataWithOriginatorGC)
 
 add_executable(homestore_test_gc)
 target_sources(homestore_test_gc PRIVATE $<TARGET_OBJECTS:homestore_tests_gc>)
 target_link_libraries(homestore_test_gc PUBLIC homeobject_homestore ${COMMON_TEST_DEPS})
-add_test(NAME HomestoreTestGC COMMAND homestore_test_gc -csv error --executor immediate --config_path ./
+add_test(NAME HomestoreTestGC COMMAND homestore_test_gc --executor immediate --config_path ./
         --override_config hs_backend_config.enable_gc=true
         --override_config hs_backend_config.gc_enable_read_verify=true
-        --override_config hs_backend_config.gc_garbage_rate_threshold=0 
-        --override_config hs_backend_config.gc_scan_interval_sec=5)
+        --override_config hs_backend_config.gc_garbage_rate_threshold=0
+        --override_config hs_backend_config.gc_scan_interval_sec=5
+        --gtest_filter=-HomeObjectFixture.StalePChunkRouteAfterGC:-HomeObjectFixture.StaleBlobRouteAfterSealAndGC)
+
+# Shard-race repro tests: require chunks_per_pg=1 (forces vchunk reuse after seal) and gc_garbage_rate_threshold=0.
+# Run together since they share the same config requirements.
+add_test(NAME HomestoreTestGC_ShardRaceTests
+        COMMAND homestore_test_gc --executor immediate --config_path ./
+        --chunks_per_pg 1
+        --override_config hs_backend_config.enable_gc=true
+        --override_config hs_backend_config.gc_garbage_rate_threshold=0
+        --override_config hs_backend_config.gc_scan_interval_sec=5
+        --gtest_filter=HomeObjectFixture.StalePChunkRouteAfterGC:HomeObjectFixture.StaleBlobRouteAfterSealAndGC)
+
+# All tests share disk, port, and shared-memory resources, so run them serially to avoid parallel conflicts.
+set_tests_properties(
+    HomestoreTestBlob
+    HomestoreTestMisc
+    HomestoreTestReplaceMember
+    HomestoreTestReplaceMemberWithBaselineResync
+    HomestoreTestBaselineResync
+    HomestoreResyncTestWithFollowerRestart
+    HomestoreResyncTestWithLeaderRestart
+    FetchDataWithOriginatorGC
+    HomestoreTestGC
+    HomestoreTestGC_ShardRaceTests
+    PROPERTIES RUN_SERIAL TRUE)