IBM Books

IBM General Parallel File System for AIX: Administration and Programming Reference

mmchconfig Command

Name

mmchconfig - Changes GPFS configuration parameters.

Synopsis

mmchconfig Attribute=value [,Attribute=value...] [NodeName[,NodeName ...] ] [-C NodesetId ] [-i | -I]

Description

Use the mmchconfig command to change the GPFS configuration attributes on a single node, a list of nodes, or globally for the entire nodeset.

DFS export of a DMAPI enabled GPFS file system is not supported.

The Attribute=value flags must come before any operand.

When changing both maxblocksize and pagepool, these conventions must be followed or the command fails:

Results

The nodeset configuration is updated on each node in the GPFS nodeset.

Parameters

-C NodesetId
The identifier of the GPFS nodeset whose configuration parameters you want to change. If this option is not specified or a period (.) is used for the NodesetId, the configuration parameters are changed for the nodeset from which the mmchconfig command was issued. To determine the nodeset of the node you are running on, issue the mmlsnode -C . command.

In an SP environment, if this option is not specified and the command is issued from the CWS, the command fails.

NodeName[,NodeName ...]
A comma-separated list of nodes specified for customized configuration change. If NodeName is not specified, the results are propagated to all GPFS nodes. If a list of target nodes is specified, the configuration changes affect only the GPFS nodes listed. This parameter specification is valid only for the dataStructureDump, designation, dmapiEventTimeout, dmapiMountTimeout, dmapiSessionFailureTimeout, maxblocksize, maxFilesToCache, maxStatCache, and pagepool options.

The hostname or IP address used for a node must refer to the adapter port over which the GPFS daemons communicate. Alias interfaces are not allowed. Use the original address or a name that is resolved by the host command to that original address. You may specify a node using any of these forms:
Format Example
Short hostname k145n01
Long hostname k145n01.kgn.ibm.com
IP address 9.119.19.102

Options

Attribute
The name of the attribute to be changed to the specified value. More than one attribute and value pair, in a comma-separated list, can be changed with one invocation of the command.

autoload
Starts GPFS automatically whenever the nodes are rebooted. Valid values are yes or no.

dataStructureDump
Specifies a path for the storage of dumps. The default is to store dumps in /tmp/mmfs. Specify no to store no dumps.

It is suggested that you create a directory for the placement of certain problem determination information. This can be a symbolic link to another location if more space can be found there. It should not be placed in a GPFS file system as it might not be available should GPFS fail. If a problem should occur, GPFS may write 200MB or more of problem determination data into the directory. These files must be manually removed when any problem determination is complete. This should be done promptly so that a NOSPACE condition is not encountered during the next failure.

designation [client | manager]
Changes the node designation. The designation specifies whether or not the node should be included in the pool of nodes from which the File System Manager Node is chosen. For further information on the roles of a node as the File System Manager, see the IBM General Parallel File System for AIX: Concepts, Planning, and Installation Guide and search for File System Manager. All nodes in the nodeset may not be designated as client nodes.

dmapiEventTimeout
Controls the blocking of file operation threads of NFS and DFS, while in the kernel waiting for the handling of a DMAPI synchronous event. The parameter value is the maximum time, in milliseconds, the thread will block. When this time expires, the file operation returns ENOTREADY, and the event continues asynchronously. The NFS or DFS server is expected to repeatedly retry the operation, which eventually will find the response of the original event and continue. This mechanism applies only to read, write, and truncate event types, and only when such events come from NFS and DFS server threads. The time-out value is given in milliseconds. The value 0 indicates immediate time-out (fully asynchronous event). A value greater or equal 86400000 (which is 24 hours) is considered infinity (no time-out, fully synchronous event). The default value is 86400000.
Note:
DFS export of a DMAPI enabled GPFS file system is not supported.

For further information regarding DMAPI for GPFS, see IBM General Parallel File System for AIX: Data Management API Guide.

dmapiMountTimeout
Controls the blocking of mount operations, waiting for a disposition for the mount event to be set. This time-out is activated at most once on each node, by the first external mount of a file system which has DMAPI enabled, and only if there has never before been a mount disposition. Any mount operation on this node that starts while the time-out period is active will wait for the mount disposition. The parameter value is the maximum time, in seconds, that the mount operation will wait for a disposition. When this time expires and there is still no disposition for the mount event, the mount operation fails, returning the EIO error. The time-out value is given in full seconds. The value 0 indicates immediate time-out (immediate failure of the mount operation). A value greater or equal 86400 (which is 24 hours) is considered infinity (no time-out, indefinite blocking until the there is a disposition). The default value is 60.

For further information regarding DMAPI for GPFS, see IBM General Parallel File System for AIX: Data Management API Guide.

dmapiSessionFailureTimeout
Controls the blocking of file operation threads, while in the kernel, waiting for the handling of a DMAPI synchronous event that is enqueued on a session that has suffered a failure. The parameter value is the maximum time, in seconds, the thread will wait for the recovery of the failed session. When this time expires and the session has not yet recovered, the event is aborted and the file operation fails, returning the EIO error. The time-out value is given in full seconds. The value 0 indicates immediate time-out (immediate failure of the file operation). A value greater or equal 86400 (which is 24 hours) is considered infinity (no time-out, indefinite blocking until the session recovers). The default value is 0.

For further information regarding DMAPI for GPFS, see IBM General Parallel File System for AIX: Data Management API Guide.

-i
Specifies that the changes should take effect immediately and are permanent. This option is only valid for the dataStructureDump, dmapiEventTimeout, dmapiMountTimeout, dmapiSessionFailureTimeout, maxblocksize, and pagepool attributes.

-I
Specifies that the changes take effect immediately but do not persist when GPFS is restarted. This option is only valid for the dataStructureDump, dmapiEventTimeout, dmapiMountTimeout, dmapiSessionFailureTimeout, maxblocksize, and pagepool attributes.

maxblocksize
Changes the maximum file system block size. Valid values include 16K, 64K, 256K, 512K, and 1024K. The default value is 256K. This value should be specified with the character K, for example, 512K.

File systems with block sizes larger than the specified value cannot be created or mounted unless the blocksize is increased.

The maximum GPFS file system size that can be mounted is limited by the control structures in memory required to maintain the file system. These control structures, and consequently the maximum mounted file system size, are a function of the block size of the file system.

maxFilesToCache
Specifies the number of inodes to cache for recently used files that have been closed. Storing a file's inode in cache permits faster reaccess to the file. The default is 1000 but increasing this number may improve throughput for workloads with high file reuse. However, increasing this number excessively may cause paging at the File System Manager node.

maxStatCache
Specifies the number of inodes to keep in the stat cache. The stat cache maintains only enough inode information to perform a query on the file system. The default value is 4 × maxFilesToCache.

pagepool
Changes the size of the cache on each node. The default value is 20M. It can range from a minimum of 4M to a maximum of 512M per node. This value should be specified with the character M, for example, 60M.

release=LATEST
Change the GPFS configuration information to the latest format supported by the currently installed level of GPFS, thereby reducing the number of configuration files stored in the GPFS cluster data.

Perform this operation for each nodeset independently after all nodesets in either your SP partition or GPFS cluster have been migrated to the latest level of GPFS ( see the IBM General Parallel File System for AIX: Concepts, Planning, and Installation Guide and search for migration, coexistence, and compatibility for GPFS).

singleNodeQuorum
In a two-node nodeset, specifies whether or not to start the daemon if only one node is available (see the IBM General Parallel File System for AIX: Concepts, Planning, and Installation Guide and search for quorum). This flag is ignored if more than two nodes have been defined to the GPFS nodeset. Valid values are yes or no.

In an HACMP environment when using Fibre Channel disks, single-node quorum is not supported.


Table 4. Configuration attributes on the mmchconfig command

-i option allowed -I option allowed GPFS must be stopped on all nodes list of NodeNames allowed change takes effect
starting GPFS automatically (autoload) no no no no on reboot of the nodes
path for the storage of dumps (dataStructureDump) yes yes no yes if not immediately, upon restart of the daemon
node use designation (designation) no no no yes restart of the daemon
DMAPI attribute dmapiEventTimeout yes yes no yes if not immediately, upon restart of the daemon
DMAPI attribute dmapiMountTimeout yes yes no yes if not immediately, upon restart of the daemon
DMAPI attribute dmapiSessionFailureTimeout yes yes no yes if not immediately, upon restart of the daemon
maximum file system block size allowed (maxblocksize) yes yes no yes if not immediately, upon restart of the daemon
number of inodes to cache for recently used files (maxFilesToCache) no no no yes restart of the daemon
number of inodes to keep in stat cache (maxStatCache) no no no yes restart of the daemon
size of cache on each node (pagepool) yes yes no yes if not immediately, upon restart of the daemon
update how the configuration information is stored (release) no no no no immediately
quorum (singleNodeQuorum) no no yes no restart of the daemon

Exit status

0
Successful completion.

1
A failure has occurred.

Security

You must have root authority to run the mmchconfig command.

In an SP environment:

  1. Verify the authentication method set for SP security services:
    1. If your authentication method is set to compatibility, Kerberos authentication is required. Issue the k4init command.
    2. If your authentication method is set to DCE, dce_login authentication is required.
    3. If your authentication method is set to NONE/std, there must be an entry in the /etc/sysctl.mmcmd.acl file on every node in the nodeset for the root user at every other node in the nodeset.

    For further information, see the latest IBM Parallel System Support Programs for AIX: Administration Guide, IBM Parallel System Support Programs for AIX: Command and Technical Reference, and RS/6000: Planning Volume 2, Control Workstation and Software Environment manuals at www.rs6000.ibm.com/resource/aix_resource/sp_books/pssp. Search for information on sysctl.

  2. You may issue the mmchconfig command from any node running GPFS or the CWS when using the -C option.
  3. If you are executing the mmchconfig command from the CWS on a multi-partitioned system, the SP_NAME environment variable must be properly set. It is suggested that you use a separate window for each partition and set the environment variable accordingly. For further information, see the IBM Parallel System Support Programs for AIX: Administration Guide and search for understanding system partitioning.

In an HACMP environment:

  1. When using rcp and rsh for remote communication, a properly configured /.rhosts file must exist in the root user's home directory on each node in the GPFS cluster. If you have designated the use of a different remote communication program on either the mmcrcluster or the mmchcluster command, you must insure:
    1. Proper authorization is granted to all nodes in the GPFS cluster.
    2. The nodes in the GPFS cluster can communicate without the use of a password.
  2. You may issue the mmchconfig command from any node in the GPFS cluster.

Examples

To change the size of the pagepool to 256M, enter: 

mmchconfig pagepool=256M

To confirm the change, enter: 

mmlsconfig -C .

The system displays information similar to: 

Configuration data for nodeset set1:  
-----------------------------------  
pagepool 256M                        
dataStructureDump /log/mmfs          
multinode yes                        
autoload no                          
useSingleNodeQuorum no               
wait4RVSD no                         
 
clusterType SP                      
maxblocksize 512K
group Gpfs.set1                       
recgroup GpfsRec.set1                 
useDiskLease no                      
                                     
File systems in nodeset set1:         
----------------------------         
/dev/fs1

See also

mmaddnode Command

mmconfig Command

mmdelnode Command

mmlsconfig Command

mmlsnode Command

Location

/usr/lpp/mmfs/bin

[ Top of Page | Previous Page | Next Page | Table of Contents | Index ]