Node

The Node Object represents a GPFS client or server node in the cluster.

Node Objects support Callback Functions

Description

class arcapix.fs.gpfs.node.Node(name, quorumCandidate=False, managerCandidate=False, adminNodeName=None)

Represents a node in the GPFS Cluster.

Parameters:name (str) – Name of a new or existing node (default=localhost)

The following parameters only have to be specified when creating a new node:

Parameters:
  • quorumCandidate (bool) – Indicates whether the node is counted as a quorum node (default=False)
  • managerCandidate (bool) – Indicates whether the node is part of the node pool filesystem can be taken from If False the node will be a client node (default=False)
  • adminNodeName (str) – Name of the node used by GPFS admin commands when communicating between nodes
change(**kwargs)

Change attributes of this node.

Parameters:
  • license (str) – one of (server, client, fpo)
  • gateway (bool) – change whether this node is a gateway node
  • managerCandidate (bool) – change whether the node is a candidate to be a manager
  • quorumCandidate (bool) – change whether the node is a quorum node
  • adminNodeName (str) – change the name used by admin commands when communicating between nodes
  • cesEnabled (bool) – change whether Cluster Export Services (CES) is enabled on the node
  • cnfsEnabled (bool) – change whether CNFS functionality of a CNFS member node is enabled
  • snmpAgent (bool) – change whether the node is designated as an SNMP collector
  • perfmonNode (bool) – change whether the node is designated as a perfmon node

Per-node configs can also be changed via this method. Multiple configs can be changed at once.

Return type:Nothing
create()

Add a new node to the cluster

After you create a node, you should set its license using ‘Node.change(license=…)’

delete()

Remove the node from the cluster.

Note - node deleting is an asynchronous process.

startup(async=False, timeout=60)

Starts up GPFS on the specified node

Parameters:
  • async (bool) – If True, do not wait for startup (default=False).
  • timeout (int) – Time to wait for the node to start up if not async (in seconds) (default=60s)
Return type:

Nothing

Raises:

GPFSError if not async and the node isn’t back up within the timeout period

start(async=False, timeout=60)

Starts up GPFS on the specified node

Synonym from startup

Parameters:
  • async (bool) – If True, do not wait for startup (default=False).
  • timeout (int) – Time to wait for the node to start up if not async (in seconds) (default=60s)
Return type:

Nothing

Raises:

GPFSError if not async and the node isn’t back up within the timeout period

stop(unmountTimeout=None)

Shuts down GPFS on the specified node

Synonym for shutdown

Parameters:unmountTimeout (int) – Time to wait for filesystem(s) to unmount on the node. If unmount doesn’t complete within unmountTimeout, the GPFS daemon will shutdown anyway (default=63s).
Return type:Nothing
shutdown(unmountTimeout=None)

Shuts down GPFS on the specified node

Parameters:unmountTimeout (int) – Time to wait for filesystem(s) to unmount on the node. If unmount doesn’t complete within unmountTimeout, the GPFS daemon will shutdown anyway (default=63s).
Return type:Nothing
id

Standard internal identifier

Synonym for name

Return type:str
name

Returns the name of the node as returned by mmgetstate

Return type:str
fqdn

Returns the fully-qualified domain name of the node

Return type:str
shortname

Returns the shortname of the node

e.g. sn-01.example.com > sn-01

Return type:str
ip

Returns the IP address of the node

Return type:str
quorumCandidate

Returns whether the node is a quorum node

Return type:bool
state

Returns the state of the node.

One of [active, arbitrating, down, unknown]

Return type:str
nodeNumber

Returns the number of the node

Return type:str
gateway

Returns whether the node is a gateway node for the purposes of AFM

Return type:bool
managerCandidate

Returns whether the node is a candidate to be a manager node.

Return type:bool
snmpAgent

Returns whether the node is an SNMP collector node.

Return type:bool
perfmonNode

Returns whether the node is a performance monitoring node.

Performance monitoring nodes collect metrics and performance information and sends the information to one or more performance collection nodes

Return type:bool
adminNodeName

Returns the node interface name used by administration commands to communicate between nodes.

Return type:str
manager

Returns whether the node is the cluster manager node

Return type:bool
is_localhost()

Returns whether the node is localhost

Return type:bool
license

Returns the license allocated to the node

One of [fpo, server, client]

Return type:License object
requiredLicense

Returns the required license for this node

i.e. the license required for the roles the node is performing

One of [fpo, server, client]

Return type:str
atimeDeferredSeconds

Controls the update behavior of atime when the relatime option is enabled

Default:86400
Return type:int
autoload

Starts GPFS automatically whenever the nodes are rebooted

Return type:bool
callbacks

Returns a collection of the callbacks that are installed on this object

Return type:Callbacks
cnfsReboot

Specifies whether the node will reboot when CNFS monitoring detects an unrecoverable problem that can only be handled by node failover.

New in GPFS 4.1.0.4 - older versions return default

Default:True
Return type:bool
commandAudit

Controls the logging of audit messages for GPFS commands that change the configuration of the cluster. This attribute is not supported on Windows operating systems

One of [yes, no, syslogOnly]

New in GPFS 4.2.1 - older versions return default

Default:syslogOnly
Return type:str
dataDiskWaitTimeForRecovery

Specifies a period of time, in seconds, during which the recovery of dataOnly disks is suspended to give the disk subsystem a chance to correct itself

Allowed values are between 0 and 3600 seconds

Default:3600
Return type:int
dataStructureDump

Path for the storage of dumps

Return type:str
debugDataControl

Controls the amount of debug data that is collected

One of [none, light, medium, heavy, verbose]

New in GPFS 4.2.1 - older versions return default

Default:light
Return type:str
disableInodeUpdateOnFdatasync

Controls the inode update on fdatasync for mtime and atime updates

Default:False
Return type:bool
dmapiDataEventRetry

Controls how GPFS handles data events that are enabled again immediately after the event is handled by the DMAPI application

Default:2
Return type:int
dmapiEventTimeout

Controls the blocking of file operation threads of NFS, while in the kernel waiting for the handling of a DMAPI synchronous event

Valid range 0-86400000

Default:86400000
Return type:int
dmapiMountEvent

Controls the generation of the mount, preunmount, and unmount events

One of [all, SessionNode, RemoteNode]

Default:all
Return type:str
dmapiMountTimeout

Controls the blocking of mount operations, waiting for a disposition for the mount event to be set

Valid range is 0-86400

Default:60
Return type:int
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 experienced a failure

Allowed values are 0-86400

Default:0
Return type:int
fastestPolicyCmpThreshold

Indicates the disk comparison count threshold, above which GPFS forces selection of this disk as the preferred disk to read and update its current speed.

Valid values >= 3

New in GPFS 4.2.1 - older versions return default

Default:50
Return type:int
fastestPolicyMaxValidPeriod

Indicates the time period after which the disk’s current evaluation is considered invalid

Valid values >= 1

New in GPFS 4.2.1 - older versions return default

Default:600
Return type:int
fastestPolicyMinDiffPercent

A percentage value indicating how GPFS selects the fastest between two disks

Valid range 0-100

New in GPFS 4.2.1 - older versions return default

Default:50
Return type:int
fastestPolicyNumReadSamples

Controls how many read samples are taken to evaluate the disk’s recent speed.

Valid values are 3 through 100

New in GPFS 4.2.1 - older versions return default

Default:5
Return type:int
forceLogWriteOnFdatasync

Controls forcing log writes to disk

Default:True
Return type:bool
ignorePrefetchLUNCount

Setting the value of the ignorePrefetchLUNCount parameter to yes does not include the LUN count and uses the maxMBpS value to dynamically determine the number of threads to schedule the prefetchThreads value.

New in GPFS 4.2.1 - older versions return default

Default:False
Return type:bool
lrocData

Controls whether user data is populated into the local read-only cache

New in GPFS 4.1.0.4 - older versions return default

Default:True
Return type:bool
lrocDataMaxFileSize

Limits the data that may be saved in the local read-only cache to only the data from small files.

New in GPFS 4.1.0.4 - older versions return default

Default:0
Return type:int
lrocDataStubFileSize

Limits the data that may be saved in the local read-only cache to only the data from the first portion of all files

New in GPFS 4.1.0.4 - older versions return default

Default:0
Return type:int
lrocDirectories

Controls whether directory blocks is populated into the local read-only cache

New in GPFS 4.1.0.4 - older versions return default

Default:True
Return type:bool
lrocInodes

Controls whether inodes from open files is populated into the local read-only cache

New in GPFS 4.1.0.4 - older versions return default

Default:True
Return type:bool
maxBufferDescs

Each buffer descriptor caches maximum block size data for a file.

Valid values are from 512 to 10,000,000

New in GPFS 4.2.1 - older versions return default

Default:10 * maxFilesToCache up to pagepool size/16 KB
Return type:int
maxDownDisksForRecovery

Specifies the maximum number of disks that may experience a failure and still be subject to an automatic recovery attempt

Valid values are between 0 and 300

New in GPFS 4.2.1 - older versions return default

Default:16
Return type:int
maxFailedNodesForRecovery

Specifies the maximum number of nodes that may be unavailable before automatic disk recovery actions are cancelled.

Valid values are between 0 and 300

New in GPFS 4.2.1 - older versions return default

Default:3
Return type:int
maxFcntlRangesPerFile

Specifies the number of fcntl locks that are allowed per file

Allowed range 10 to 200000

Default:200
Return type:int
maxFilesToCache

Specifies the number of inodes to cache for recently used files that have been closed.

Default:4000
Return type:int
maxMBpS

Specifies an estimate of how many megabytes of data can be transferred per second into or out of a single node

Default:2048
Return type:int
maxStatCache

Specifies the number of inodes to keep in the stat cache

Return type:int
maxblocksize

Changes the maximum file system block size.

Valid block sizes are 64 KiB, 128 KiB, 256 KiB, 512 KiB, 1 MiB, 2 MiB, 4 MiB, 8 MiB, and 16 MiB.

Default:1M
Return type:str
metadataDiskWaitTimeForRecovery

Specifies a period of time, in seconds, during which the recovery of metadata disks is suspended to give the disk subsystem a chance to correct itself

Valid values are between 0 and 3600 seconds.

Default:2400
Return type:int
minDiskWaitTimeForRecovery

Specifies a period of time, in seconds, during which the recovery of disks is suspended to give the disk subsystem a chance to correct itself

Valid values 0-3600

New in GPFS 4.2.1 - older versions return default

Default:1800
Return type:int
mmapRangeLock

Specifies POSIX or non-POSIX mmap byte-range semantics

Default:True
Return type:bool
mmfsLogTimeStampISO8601

Controls the time stamp format for GPFS log entries

New in GPFS 4.2.2 - older versions return default

Default:True
Return type:bool
nfsPrefetchStrategy

Defines a window of the number of blocks around the current position that are treated as fuzzy-sequential access.

Valid values are between 0 and 10

New in GPFS 4.2.1 - older versions return default

Default:0
Return type:int
noSpaceEventInterval

Specifies the time interval between calling a callback script of two noDiskSpace events of a file system.

Default:120
Return type:int
nsdBufSpace

This option specifies the percentage of the page pool reserved for the network transfer of NSD requests

Valid range 10-70

Default:30
Return type:int
nsdCksumTraditional

Enables checksum data-integrity checking between a traditional NSD client node and its NSD server

New in GPFS 5.0.1 - older versions return default

Default:False
Return type:bool
nsdDumpBuffersOnCksumError

Enables the dumping of the data buffer to a file when a checksum error occurs.

New in GPFS 5.0.1 - older versions return default

Default:False
Return type:bool
nsdInlineWriteMax

Specifies the maximum transaction size that can be sent as embedded data in an NSD-write RPC

Valid values are between 0 and 8M

New in GPFS 4.2.1 - older versions return default

Default:1024
Return type:int
nsdMaxWorkerThreads

Sets the maximum number of NSD threads that can be involved in NSD I/O operations on an NSD server to the storage system to which the server is connected

Valid values are between 8 and 8192

New in GPFS 4.2.1 - older versions return default

Default:512
Return type:int
nsdMinWorkerThreads

Sets a lower bound on number of active NSD I/O threads on an NSD server node that executes I/O operations against NSDs

Valid values are between 1 and 8192

New in GPFS 4.2.1 - older versions return default

Default:16
Return type:int
nsdMultiQueue

Sets the number of NSD queues.

Valid values are between 2 and 512

New in GPFS 4.2.1 - older versions return default

Default:256
Return type:int
nsdRAIDBufferPoolSizePct

This option specifies the percentage of the page pool that is used for the GPFS Native RAID vdisk buffer pool

Valid range 10-90

Default:50
Return type:int
nsdRAIDTracks

specifies the number of tracks in the GPFS Native RAID buffer pool, or 0 if this node does not have a GPFS Native RAID vdisk buffer pool

Valid values are: 0; 256 or greater.

New in GPFS 4.1.0.4 - older versions return None

Return type:int
nsdServerWaitTimeForMount

When mounting a file system whose disks depend on NSD servers, this option specifies the number of seconds to wait for those servers to come up

Valid values are between 0 and 1200 seconds

Default:300
Return type:int
nsdServerWaitTimeWindowOnMount

Specifies a window of time (in seconds) during which a mount can wait for NSD servers

Valid values are between 1 and 1200 seconds

Default:600
Return type:int
numaMemoryInterleave

In a Linux NUMA environment, the default memory policy is to allocate memory from the local NUMA node of the CPU from which the allocation request was made.

This parameter is used to change to an interleave memory policy for GPFS

New in GPFS 4.1.0.4 - older versions return default

Default:False
Return type:bool
onAfmFilesetExpired

Returns a Callbacks collection, the members of which will be triggered when the contents of a fileset expire. (Global Event)

Supported on: Cluster, Nodeclass, Node, Fileset

onAfmFilesetUnexpired

Returns a Callbacks collection, the members of which will be triggered when the contents of a fileset become unexpired. (Global Event)

Supported on: Cluster, Nodeclass, Node, Fileset

onAfmHomeConnected

Returns a Callbacks collection, the members of which will be triggered when a gateway node connects to the home NFS server of the fileset that it is serving. (Local Event)

Supported on: Cluster, Nodeclass, Node

onAfmHomeDisconnected

Returns a Callbacks collection, the members of which will be triggered when a gateway node gets disconnected from the home NFS server of the fileset that it is serving. (Local Event)

Supported on: Cluster, Nodeclass, Node

onAfmManualResyncComplete

Returns a Callbacks collection, the members of which will be triggered when a manual resync is completed. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem, Fileset

onAfmPrepopEnd

Returns a Callbacks collection, the members of which will be triggered when all the files specified by a prefetch operation have been cached successfully. (Local Event)

Supported on: Cluster, Nodeclass, Node, Fileset

onAfmRecoveryEnd

Returns a Callbacks collection, the members of which will be triggered when AFM recovery ends. (Local Event)

Supported on: Cluster, Nodeclass, Node

onAfmRecoveryStart

Returns a Callbacks collection, the members of which will be triggered when AFM recovery starts. (Local Event)

Supported on: Cluster, Nodeclass, Node

onClusterManagerTakeover

Returns a Callbacks collection, the members of which will be triggered when a new cluster manager node has been elected. (Global Event)

Supported on: Cluster, Nodeclass, Node

onDeadlockDetected

Returns a Callbacks collection, the members of which will be triggered when a node detects a potential deadlock. (Local Event)

Supported on: Cluster, Nodeclass, Node

onDeadlockOverload

Returns a Callbacks collection, the members of which will be triggered when a cluster is overloaded on the node detecting the overload condition. (Local Event)

Supported on: Cluster, Nodeclass, Node

onDiskFailure

Returns a Callbacks collection, the members of which will be triggered on the file system manager node when the disk status in the files system changes to down. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem

onFilesetLimitExceeded

Returns a Callbacks collection, the members of which will be triggered when the file system manager detects that a fileset quota has been exceeded. (Local event)

Note

GPFS recommends using the softQuotaExceeded event instead.

Supported on: Cluster, Nodeclass, Node, Fileset

onLowDiskSpace

Returns a Callbacks collection, the members of which will be triggered when the file system manager detects that disk space is running below the low threshold that is specified in the current policy rule. (Local Event)

Note

This event is triggered every two minutes until the condition is solved.

Supported on: Cluster, Nodeclass, Node, Pool

onMmProtocolTraceFileChange

Returns a Callbacks collection, the members of which will be triggered on each CES node to check for required tracing tasks when the trace file is changed within the CCR. Allows traces to be started, stopped, and monitored across a cluster. (Local Event)

Supported on: Cluster, Nodeclass, Node

onMount

Returns a Callbacks collection, the members of which will be triggered when a file system is mounted successfully. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem

onNoDiskSpace

Returns a Callbacks collection, the members of which will be triggered when the file system encounters a disk that ran out of space. (Local event)

Note

This event is triggered every two minutes until the condition is solved.

Supported on: Cluster, Nodeclass, Node, Fileset, Pool

onNodeJoin

Returns a Callbacks collection, the members of which will be triggered when one or more nodes join the cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onNodeLeave

Returns a Callbacks collection, the members of which will be triggered when one or more nodes leave the cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onPreMount

Returns a Callbacks collection, the members of which will be triggered when a file system is about to be mounted. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem

onPreShutdown

Returns a Callbacks collection, the members of which will be triggered when GPFS detects a failure and is about to shut down. (Local Event)

Supported on: Cluster, Nodeclass, Node

onPreStartup

Returns a Callbacks collection, the members of which will be triggered after the GPFS daemon completes its internal initialization and joins the cluster, but before the node runs recovery for any VFS mount points that were already mounted, and before the node starts accepting user initiated sessions. (Local Event)

Supported on: Cluster, Nodeclass, Node

onPreUnmount

Returns a Callbacks collection, the members of which will be triggered when a file system is about to be unmounted. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem

onQuorumLoss

Returns a Callbacks collection, the members of which will be triggered when a quorum has been lost in the GPFS cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onQuorumNodeJoin

Returns a Callbacks collection, the members of which will be triggered when one or more quorum nodes join the cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onQuorumNodeLeave

Returns a Callbacks collection, the members of which will be triggered when one or more quorum nodes leave the cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onQuorumReached

Returns a Callbacks collection, the members of which will be triggered when a quorum has been established in the GPFS cluster. This event is triggered only on the elected cluster manager node, not on all the nodes in the cluster. (Global Event)

Supported on: Cluster, Nodeclass, Node

onSendRequestToNodes

Returns a Callbacks collection, the members of which will be triggered when a node sends a request for collecting expel-related debug data to some nodes. (Local Event)

Supported on: Cluster, Nodeclass, Node

onShutdown

Returns a Callbacks collection, the members of which will be triggered when GPFS completes the shutdown. (Local Event)

Supported on: Cluster, Nodeclass, Node

onSnapshotCreated

Returns a Callbacks collection, the members of which will be triggered after a snapshot is created, and run before the file system is resumed. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem, Fileset

onSoftQuotaExceeded

Returns a Callbacks collection, the members of which will be triggered when the file system manager detects that a soft quota limit (for either files or blocks) has been exceeded. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem, Fileset

onStartup

Returns a Callbacks collection, the members of which will be triggered after a successful GPFS startup and when the node is ready for user initiated sessions. (Local Event)

Supported on: Cluster, Nodeclass, Node

onTiebreakerCheck

Returns a Callbacks collection, the members of which will be triggered when a quorum node detects loss of network connectivity but before GPFS runs the algorithm that decides if the node will remain in the cluster. This event is generated only in configurations that use quorum nodes with tiebreaker disks. (Local Event)

Supported on: Cluster, Nodeclass, Node

onUnmount

Returns a Callbacks collection, the members of which will be triggered when a file system is unmounted successfully. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem

onUsageUnderSoftQuota

Returns a Callbacks collection, the members of which will be triggered when the file system manager detects that quota usage has dropped below soft limits and grace time is reset. (Local Event)

Supported on: Cluster, Nodeclass, Node, Filesystem, Fileset

pagepool

Changes the size of the cache on each node

The default value is either one-third of the physical memory on the node or 1G, whichever is smaller

Return type:str
pagepoolMaxPhysMemPct

Percentage of physical memory that can be assigned to the page pool.

Valid values are 10 through 90 percent

Default:75
Return type:int
panicOnIOHang

Controls whether the GPFS daemon panics the node kernel when a local I/O request is pending in the kernel for more than five minutes.

This attribute applies only to disks that the node is directly attached to.

New in GPFS 5.0.2 - older versions return False

Default:False
Return type:bool
pitWorkerThreadsPerNode

Controls the maximum number of threads to be involved in parallel processing on each node that is serving as a Parallel Inode Traversal (PIT) worker.

The range of accepted values is 0 to 8192

New in GPFS 4.2.1 - older versions return None

Return type:int
prefetchPct

Limit on the page pool space that is to be used for prefetch and write-behind buffers for active sequential streams

Valid values are between 0 and 60

New in GPFS 4.2.1 - older versions return default

Default:20
Return type:int
prefetchThreads

Controls the maximum possible number of threads dedicated to prefetching data for files that are read sequentially, or to handle sequential write-behind.

Default:72
Return type:int
readReplicaPolicy

Specifies the location from which the FPO policy is to read replicas.

New in GPFS 4.2.1 - older versions return None

Return type:str
restripeOnDiskFailure

Specifies whether a restripe will be performed on disk failures

Return type:bool
rpcPerfNumberDayIntervals

Controls the number of days that aggregated RPC data is saved

Valid range 4-60

New in GPFS 4.1.0.4 - older versions return default

Default:30
Return type:int
rpcPerfNumberHourIntervals

Controls the number of hours that aggregated RPC data is saved.

Allowed valeus are 4, 6, 8, 12, or 24.

New in GPFS 4.1.0.4 - older versions return default

Default:24
Return type:int
rpcPerfNumberMinuteIntervals

Controls the number of minutes that aggregated RPC data is saved

Allowed values 4, 5, 6, 10, 12, 15, 20, 30, or 60

New in GPFS 4.1.0.4 - older versions return default

Default:60
Return type:int
rpcPerfNumberSecondIntervals

Controls the number of seconds that aggregated RPC data is saved

Allowed values are 4, 5, 6, 10, 12, 15, 20, 30, or 60

New in GPFS 4.1.0.4 - older versions return default

Default:60
Return type:int
rpcPerfRawExecBufferSize

Specifies the number of bytes to save in the buffer that stores raw RPC execution statistics

New in GPFS 4.1.0.4 - older versions return default

Default:2
Return type:int
rpcPerfRawStatBufferSize

Specifies the number of bytes to save in the buffer that stores raw RPC performance statistics

New in GPFS 4.1.0.4 - older versions return default

Default:6
Return type:int
seqDiscardThreshold

Specifies what has to be done with the page pool buffer after it is consumed or flushed by write-behind threads

New in GPFS 4.2.1 - older versions return default

Default:1M
Return type:str
subnets

Specifies subnets used to communicate between nodes in a GPFS cluster or a remote GPFS cluster.

Return type:str
syncBuffsPerIteration

This parameter is used to expedite buffer flush and the rename operations that are done by MapReduce jobs

New in GPFS 4.2.1 - older versions return default

Default:100
Return type:int
systemLogLevel

Specifies the minimum severity level for messages sent to the system log

One of [alert, critical, error, warning, notice, configuration, informational, detail, debug]

New in GPFS 4.1.0.4 - older versions return None

Return type:str
unmountOnDiskFail

Controls how the daemon responds when it detects a disk failure

One of [yes, no, meta]

Return type:str
verbsPorts

Specifies the InfiniBand device names and port numbers used for RDMA transfers between an NSD client and server

Return type:list of str
verbsRdma

Enables or disables InfiniBand RDMA using the Verbs API for data transfers between an NSD client and NSD server

One of [enable, disable]

Return type:str
verbsRdmaCm

Enables or disables the RDMA Connection Manager (RDMA CM or RDMA_CM) using the RDMA_CM API for establishing connections between an NSD client and NSD server

One of [enable, disable]

Return type:str
verbsRdmaPkey

Specifies an InfiniBand partition key for a connection between the specified node and an Infiniband server that is included in an InfiniBand partition

New in GPFS 4.2.3 - older versions return None

verbsRdmaRoCEToS

Specifies the Type of Service (ToS) value for clusters using RDMA over Converged Ethernet (RoCE).

Acceptable values for this parameter are 0, 8, 16, and 24

New in GPFS 4.1.0.4 - older versions return default

Default:-1
Return type:int
verbsRdmaSend

Enables or disables the use of InfiniBand RDMA rather than TCP for most GPFS daemon-to-daemon communication

One of [enable, disable]

Return type:str
verbsRdmasPerConnection

Sets the maximum number of simultaneous RDMA data transfer requests allowed per connection

Obsolete since GPFS 5.0.0 - older versions return default

Default:0
Return type:int
verbsRdmasPerNode

Sets the maximum number of simultaneous RDMA data transfer requests allowed per node

Obsolete since 5.0.0 - older versions return default

Default:0
Return type:int
verbsRecvBufferCount

Defines the number of RDMA recv buffers created for each RDMA connection that is enabled for RDMA send when verbsRdmaSend is enabled

New in GPFS 5.0.0 - older versions return default

Default:128
Return type:int
verbsRecvBufferSize

Defines the size, in bytes, of the RDMA send and recv buffers that are used for RDMA connections that are enabled for RDMA send when verbsRdmaSend is enabled

New in GPFS 5.0.0 - older versions return default

Default:4096
Return type:int
verbsSendBufferMemoryMB

Sets the amount of page pool memory (in MiB) to reserve as dedicated buffer space for use by the verbsRdmaSend feature

Obsolete since GPFS 5.0.0 - older versions return default

Default:0
Return type:int:
worker1Threads

Controls the maximum number of concurrent file operations at any one instant.

Default:48
Return type:int
workerThreads

Controls an integrated group of variables that tune file system performance

The valid range is 1-8192

New in GPFS 4.2.1 - older versions return default

Default:48
Return type:int
writebehindThreshold

Specifies the point at which GPFS starts flushing new data out of the page pool for a file that is being written sequentially

New in GPFS 4.2.1 - older versions return default

Default:512K
Return type:str

Examples

Utilising Node from the Cluster Object

>>> from arcapix.fs.gpfs import Cluster
>>>
>>> # Load the cluster
... mycluster = Cluster()
>>>
>>> # Start all nodes in the cluster
... for n in mycluster.nodes.values():
...     n.startup()

Utilising Node directly

>>> from arcapix.fs.gpfs import Node
>>>
>>> # Load a node directly
... n = Node('pixstor-sn-01')
>>>
>>> # Start the node
... n.startup()