请教chunksize stripesize num_nodes num_disks_per_node replication_factor num_targets_per_disk min_targets_per_disk ChainCount之间的关系

部署方式是2节点。每个节点1块盘。

节点1部署admin_cli monitor mgmtd meta storage client
节点2部署storage

启动storage_main.service后报错：

节点1 storage_main-err.log:
[2025-10-17T17:05:11.277910640+08:00 DefaultPool6: 4224 TargetMap.cc:39 ERROR] chain ChainId(900100001) not found
[2025-10-17T17:05:11.277932953+08:00 DefaultPool6: 4224 TargetMap.cc:49 ERROR] target TargetId(101000100101) not found

节点2
[2025-10-17T17:05:11.290577982+08:00 DefaultPool3: 2418 TargetMap.cc:39 ERROR] chain ChainId(900100001) not found
[2025-10-17T17:05:11.290637160+08:00 DefaultPool3: 2418 TargetMap.cc:49 ERROR] target TargetId(101000200101) not found

node1检查chain:
root@node1:/var/log/3fs# /opt/3fs/bin/admin_cli -cfg /opt/3fs/etc/admin_cli.toml --config.mgmtd_client.mgmtd_server_addresses '["RDMA://192.168.1.1:8000"]' "list-chains"
ChainId ReferencedBy ChainVersion Status PreferredOrder Target Target
900100001 1 1 SERVING [] 101000100101(SERVING-UPTODATE) 101000200101(SERVING-UPTODATE)

root@node1:/var/log/3fs# cd /storage/data0/3fs/
root@node1:/storage/data0/3fs# ls
101000100101 engine

node2检查chain：
root@node2:/storage/data0/3fs# /opt/3fs/bin/admin_cli -cfg /opt/3fs/etc/admin_cli.toml --config.mgmtd_client.mgmtd_server_addresses '["RDMA://192.168.1.1:8000"]' "list-chains"
ChainId ReferencedBy ChainVersion Status PreferredOrder Target Target
900100001 1 1 SERVING [] 101000100101(SERVING-UPTODATE) 101000200101(SERVING-UPTODATE)

root@node2:/storage/data0/3fs# ls
101000200101 engine
root@node2:/storage/data0/3fs# pwd
/storage/data0/3fs

修改stripesize 即16就不报错了。但不清楚具体关系。
/opt/3fs/bin/admin_cli -cfg /opt/3fs/etc/admin_cli.toml "init-cluster --mgmtd /opt/3fs/etc/mgmtd_main.toml 1 1048576 16"

有的资料里还提到了group(add_group/active_group/full_group), group似乎是多个chunk的组合？ 比target粒度小？