Mongos will retry the _shardsvrReshardCollection command on the primary shard of the database only a finite number of times. If the current primary of that replica set is shut down (or steps down and goes into rollback) more than the number of retries from mongos, then the command error response will cause the test to fail.
[js_test:resharding_fuzzer-120e1-1630670495216-2] d20021| 2021-09-03T12:09:07.675+00:00 I REPL 21358 [BackgroundSync] "Replica set state transition","attr":{"newState":"ROLLBACK","oldState":"SECONDARY"}
...
[js_test:resharding_fuzzer-120e1-1630670495216-2] s20032| 2021-09-03T12:09:07.679+00:00 D1 ASSERT 23074 [conn46] "User assertion","attr":{"error":"InterruptedDueToReplStateChange: operation was interrupted","file":"src/mongo/s/commands/cluster_reshard_collection_cmd.cpp","line":80}
...
[js_test:resharding_fuzzer-120e1-1630670495216-2] s20032| 2021-09-03T12:09:07.680+00:00 D1 ASSERT 23074 [conn46] "User assertion","attr":{"error":"InterruptedDueToReplStateChange: operation was interrupted","file":"src/mongo/util/future_impl.h","line":1087}
[js_test:resharding_fuzzer-120e1-1630670495216-2] s20032| 2021-09-03T12:09:07.680+00:00 D1 SHARDING 22772 [conn46] "Exception thrown while processing command","attr":{"db":"admin","headerId":5142,"error":"InterruptedDueToReplStateChange: operation was interrupted"}
[js_test:resharding_fuzzer-120e1-1630670495216-2] s20032| 2021-09-03T12:09:07.681+00:00 I COMMAND 51803 [conn46] "Slow query","attr":{"type":"command","ns":"test_reshard.reshard_coll","appName":"MongoDB Shell","command":{"reshardCollection":"test_reshard.reshard_coll","key":{"recipient":1,"slot":1},"_presetReshardedChunks":[{"min":{"recipient":{"$minKey":1},"slot":{"$minKey":1}},"max":{"recipient":"recipient0","slot":{"$minKey":1}},"recipientShardId":"shard0"},{"min":{"recipient":"recipient0","slot":{"$minKey":1}},"max":{"recipient":"recipient0","slot":10},"recipientShardId":"shard0"},{"min":{"recipient":"recipient0","slot":10},"max":{"recipient":"recipient0","slot":20},"recipientShardId":"shard0"},{"min":{"recipient":"recipient0","slot":20},"max":{"recipient":"recipient0","slot":30},"recipientShardId":"shard0"},{"min":{"recipient":"recipient0","slot":30},"max":{"recipient":"recipient0","slot":40},"recipientShardId":"shard0"},{"min":{"recipient":"recipient0","slot":40},"max":{"recipient":"recipient1","slot":{"$minKey":1}},"recipientShardId":"shard0"},{"min":{"recipient":"recipient1","slot":{"$minKey":1}},"max":{"recipient":"recipient1","slot":10},"recipientShardId":"shard1"},{"min":{"recipient":"recipient1","slot":10},"max":{"recipient":"recipient1","slot":20},"recipientShardId":"shard1"},{"min":{"recipient":"recipient1","slot":20},"max":{"recipient":"recipient1","slot":30},"recipientShardId":"shard1"},{"min":{"recipient":"recipient1","slot":30},"max":{"recipient":"recipient1","slot":40},"recipientShardId":"shard1"},{"min":{"recipient":"recipient1","slot":40},"max":{"recipient":"recipient2","slot":{"$minKey":1}},"recipientShardId":"shard1"},{"min":{"recipient":"recipient2","slot":{"$minKey":1}},"max":{"recipient":"recipient2","slot":10},"recipientShardId":"shard2"},{"min":{"recipient":"recipient2","slot":10},"max":{"recipient":"recipient2","slot":20},"recipientShardId":"shard2"},{"min":{"recipient":"recipient2","slot":20},"max":{"recipient":"recipient2","slot":30},"recipientShardId":"shard2"},{"min":{"recipient":"recipient2","slot":30},"max":{"recipient":"recipient2","slot":40},"recipientShardId":"shard2"},{"min":{"recipient":"recipient2","slot":40},"max":{"recipient":"recipient3","slot":{"$minKey":1}},"recipientShardId":"shard2"},{"min":{"recipient":"recipient3","slot":{"$minKey":1}},"max":{"recipient":{"$maxKey":1},"slot":{"$maxKey":1}},"recipientShardId":"shard0"}],"lsid":{"id":{"$uuid":"702b58ee-193c-41f9-b0ae-342688d9eced"}},"$db":"admin"},"numYields":0,"ok":0,"errMsg":"operation was interrupted","errName":"InterruptedDueToReplStateChange","errCode":11602,"reslen":241,"readConcern":{"level":"local","provenance":"implicitDefault"},"remote":"10.122.50.122:34602","protocol":"op_msg","durationMillis":34486}
...
[js_test:resharding_fuzzer-120e1-1630670495216-2] "errmsg" : "operation was interrupted",
[js_test:resharding_fuzzer-120e1-1630670495216-2] "codeName" : "HostUnreachable",
- is depended on by
-
SERVER-53351 Add resharding fuzzer task with step-ups enabled for shards
-
- Closed
-