Parallel file system with extended file attributes

• US 5,940,841 A
• Filed: 07/11/1997
• Issued: 08/17/1999
• Est. Priority Date: 07/11/1997
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Johnson, Eugene, Schmuck, Frank B., Engelsiepen, Thomas E.
• Primary Examiner(s): Lintz, Paul R.
• Assistant Examiner(s): Colbert, Ella
• Application Number:
  US08/893,735
• Time in Patent Office: 767 Days
• Field of Search: 707/202, 707/8, 707/103
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 16/1858 Parallel file systems, i.e. file systems supporting multiple processors
• CPC Class Codes: Y10S 707/99938 Concurrency, e.g. lock management in shared database
• CPC Class Codes: Y10S 707/99953 Recoverability
• CPC Class Codes: Y10S 707/99956 File allocation

Abstract

A computer system having a shared disk file system running on on multiple computers each having their own instance of an operating system and being coupled for parallel data sharing access to files residing on network attached shared disks. Method are provided for use as a parallel file system in a shared disk environment by use of scalable directory service for the system with a stable cursor, a segmented allocation map. Dynamic prefetch and cached balance pools for multiple accesses improve the system. Extended file attributes are used for implementation of Access Control Lists in a parallel file system. Improvements to caching and cache performance developments balance pools for multiple accesses. A metadata node manages file metadata for parallel read and write actions. For our system, tokens are used for metadata node selection and identification, and we have enhanced token modes for controlling file size, as well as smart caching of byte range tokens using file access patterns and a byte range lock algorithm using a byte range token interface. Locking techniques reduce the overhead of a token manager which is also used in the file system recovery if a computer participating in the management of shared disks becomes unavailable or failed. Synchronous and asynchronous takeover of a metadata node occurs for correction of metadata which was under modification and a new computer node to be metadata node for that file. Locks are not constantly required to allocate new blocks on behalf of a user. We have provided recoverable local shares for Quote Management. A quota server and a quote client are provided for each file system, and a quotacheck utility allows parallel environments with minimal interference to other applications which require the use of quotas.

Claims

1. In a computer system having a shared disk file system running on multiple computers each having their own instance of an operating system and being coupled for data sharing with network attached shared disks, the method of:

providing extended file attributes for support of Access Control Lists of the kind known in the Unix environment for a file system, where each file system includes an attribute file, attribute references, an attribute index, and an attribute garbage collector for sharing of physical attribute storage among all files that have attributes with identical values by storage of all attribute data in said attribute file.

2. The method for a computer system according to claim 1, wherein an attribute reference is stored in an inode of a file and contains the location of an entry that holds attribute data for said file in the attribute file, and said attribute reference is represented as an offset of the entry in the attribute file.

3. The method for a computer system according to claim 2, wherein files with identical attribute values contain the same attribute reference values in their inodes.

4. The method for a computer system according to claim 2, wherein the method includes attribute sharing by inheritance by setting extended attributes for a new file when it is created by setting its extended attributes to the same values as an existing file from which said new file is derived such that said new file had attributes determined by its inheritance.

5. The method for a computer system according to claim 4, wherein said inheritance is obtained by copying the attribute reference from the inode of the file or directory from which the attribute is inherited so as to determine for said new file an inherited attribute which shares the same physical storage as the attribute from which it is inherited.

6. The method for a computer system according to claim 2, wherein the method includes attribute sharing by attribute value lookup by changing or setting an extended attribute for a file to a value that is not inherited from another file by utilizing an attribute index to determine whether an entry with the same value already exists in said attribute file.

7. The method for a computer system according to claim 6, wherein to set or change an attribute value, a hash function is applied to the attribute data for the attribute file and the resulting hash value used as an index in a hash table so that a list of attribute references will be found that refer to entries in said attribute file with attribute date that hash to the same hash value, and wherein when new attribute data is to be stored it is compared against all data in said attribute file so that if a match if found, an attribute reference referring to the existing entry is stored in the files inode, while if no match is found, a new entry containing the new attribute value is added to the attribute file and an attribute reference to the new entry is stored in the file'"'"'s inode as well as in the hash table so that future attribute updates using the same attribute will find the new entry.

8. The method for a computer system according to claim 6, wherein new attribute values are converted to a canonical form before storing or looking them tip.

9. The method for a computer system according to claim 1, wherein garbage collection synchronizes with a lookup operation which is used for changing of a file attribute.

10. The method for a computer system according to claim 9, wherein

said garbage collection is started by first monitoring the total size of attribute data and starting the garbage collection only after the amount of attribute data has grown by a predetermined factor so as to prevent the attribute file from growing if the amount of active attribute data stays constant.