For NAS workloads (CIFS/NFS), anything that involves metadata or manipulation of a file or folder. Procedure 6: READ - Read From file Procedure 8: CREATE - Create a file Procedure 9: MKDIR - Create a ...For NAS workloads (CIFS/NFS), anything that involves metadata or manipulation of a file or folder. Procedure 6: READ - Read From file Procedure 8: CREATE - Create a file Procedure 9: MKDIR - Create a directory Procedure 10: SYMLINK - Create a symbolic link Procedure 12: REMOVE - Remove a File Procedure 14: RENAME - Rename a File or Directory Procedure 21: COMMIT - Commit cached data on a server to stable storage How do I tell what "other" NFS iops are being processed within my volume?
Increased latency observed for "other" ops (specifically READDIR but can be seen on GETATTR and other metadata ops) on the FlexGroup parent Example: Normally a 6 node A800 cluster may see 10 GB/s writ...Increased latency observed for "other" ops (specifically READDIR but can be seen on GETATTR and other metadata ops) on the FlexGroup parent Example: Normally a 6 node A800 cluster may see 10 GB/s writes before hitting Data Processing latency, but throughput may only be 1-2 GB/s for writes Latency may be seen on a single constituent Reads or Writes can show a large increase in latency when there is a large increase in Read/Write workload within a single constituent.