gpfs:gpfs_healthcheck
GPFS health
mmhealth thresholds (+GUI +REST) monitors the usage:
$ mmhealth thresholds list ### Threshold Rules ### rule_name metric error warn direction filterBy groupBy sensitivity ---------------------------------------------------------------------------------------------------------------------------- InodeCapUtil_Rule Fileset_inode 90.0 80.0 high gpfs_cluster_name,gpfs_fs_name,gpfs_fset_name 300 DataCapUtil_Rule DataPool_capUtil 97.0 90.0 high gpfs_cluster_name,gpfs_fs_name,gpfs_diskpool_name 300 ..
List all events
[root@prscale-a-01 ~]# mmhealth node eventlog 2021-06-09 14:47:43.228189 CEST unmounted_fs_check WARNING The filesystem gpfs02lv is probably needed, but not mounted 2021-06-09 14:47:48.256313 CEST disk_found INFO The disk GPFS_NSD_A_D1_0001 was found 2021-06-09 14:52:28.475693 CEST fs_remount_mount INFO The filesystem gpfs02lv was mounted normal
Clear the events:
[root@prscale-a-01 ~]# mmhealth node eventlog --clear
Clear ALL messages on the Web (GUI) interface
[root@prscale-a-01 ~]# /usr/lpp/mmfs/gui/cli/lshealth --reset
Already resolved errors that continue to be displayed in mmhealth and the GUI:
How to remove them (and this annoying TIPS):
mmdsh -N <NODE or all> mmsysmonc clearDB mmdsh -N <NODE or all> mmsysmoncontrol restart mmhealth event hide <EventName>
Check cluster health
[root@prscale-a-01 ~]# mmhealth cluster show Component Total Failed Degraded Healthy Other ---------------------------------------------------------------------------------------------------------------- NODE 3 0 0 0 3 GPFS 3 0 0 0 3 NETWORK 3 0 0 3 0 FILESYSTEM 3 0 0 3 0 DISK 21 0 0 21 0 CES 2 0 0 2 0 CESIP 1 0 0 1 0 FILESYSMGR 2 0 0 2 0 GUI 2 0 0 2 0 PERFMON 3 0 0 3 0 THRESHOLD 3 0 0 3 0
More compact
[root@prscale-a-01 ~]# mmhealth cluster show -Y mmhealth:Summary:HEADER:version:reserved:reserved:component:entityname:total:failed:degraded:healthy:other: mmhealth:Summary:0:1:::NODE:NODE:3:0:0:0:3: mmhealth:Summary:0:1:::GPFS:GPFS:3:0:0:0:3: mmhealth:Summary:0:1:::NETWORK:NETWORK:3:0:0:3:0: mmhealth:Summary:0:1:::FILESYSTEM:FILESYSTEM:3:0:0:3:0: mmhealth:Summary:0:1:::DISK:DISK:43:0:0:43:0: mmhealth:Summary:0:1:::CES:CES:2:0:0:2:0: mmhealth:Summary:0:1:::CESIP:CESIP:1:0:0:1:0: mmhealth:Summary:0:1:::CLOUDGATEWAY:CLOUDGATEWAY:2:0:0:2:0: mmhealth:Summary:0:1:::FILESYSMGR:FILESYSMGR:2:0:0:2:0: mmhealth:Summary:0:1:::GUI:GUI:2:0:0:2:0: mmhealth:Summary:0:1:::PERFMON:PERFMON:3:0:0:3:0: mmhealth:Summary:0:1:::THRESHOLD:THRESHOLD:3:0:0:3:0:
Per node
[root@prscale-a-01 ~]# mmhealth node show Node name: prscale-a-01 Node status: TIPS Status Change: 2 days ago Component Status Status Change Reasons ---------------------------------------------------------------------------------------------------------------------------------- GPFS TIPS 2 days ago callhome_not_enabled, gpfs_maxfilestocache_small, total_memory_small NETWORK HEALTHY 4 days ago - FILESYSTEM HEALTHY 4 days ago - DISK HEALTHY 4 days ago - CES HEALTHY 4 days ago - CESIP HEALTHY 4 days ago - CLOUDGATEWAY HEALTHY 4 days ago - FILESYSMGR HEALTHY 4 days ago - GUI HEALTHY 4 days ago - PERFMON HEALTHY 4 days ago - THRESHOLD HEALTHY 4 days ago - [root@prscale-a-01 ~]# mmhealth node show -y Option with missing argument Additional messages: invalid option: -y [root@prscale-a-01 ~]# mmhealth node show -Y mmhealth:Event:HEADER:version:reserved:reserved:node:component:entityname:entitytype:event:arguments:activesince:identifier:ishidden: mmhealth:State:HEADER:version:reserved:reserved:node:component:entityname:entitytype:status:laststatuschange: mmhealth:State:0:1:::prscale-a-01:NODE:prscale-a-01:NODE:TIPS:2021-10-03 03%3A55%3A43.152676 CEST: mmhealth:State:0:1:::prscale-a-01:CES:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A50%3A34.180949 CEST: mmhealth:State:0:1:::prscale-a-01:BLOCK:prscale-a-01:NODE:DISABLED:2021-10-01 09%3A23%3A59.486199 CEST: mmhealth:State:0:1:::prscale-a-01:NFS:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A50%3A34.180949 CEST: mmhealth:State:0:1:::prscale-a-01:AUTH_OBJ:prscale-a-01:NODE:DISABLED:2021-10-01 09%3A24%3A17.174618 CEST: mmhealth:State:0:1:::prscale-a-01:CESNETWORK:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A49%3A03.938605 CEST: mmhealth:State:0:1:::prscale-a-01:CESNETWORK:ens192:NIC:HEALTHY:2021-10-01 09%3A24%3A05.346180 CEST: mmhealth:State:0:1:::prscale-a-01:OBJECT:prscale-a-01:NODE:DISABLED:2021-10-01 09%3A24%3A05.421280 CEST: mmhealth:State:0:1:::prscale-a-01:SMB:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A48%3A18.924751 CEST: mmhealth:State:0:1:::prscale-a-01:AUTH:prscale-a-01:NODE:DISABLED:2021-10-01 09%3A24%3A02.017860 CEST: mmhealth:State:0:1:::prscale-a-01:HDFS_NAMENODE:prscale-a-01:NODE:DISABLED:2021-10-01 09%3A24%3A17.295829 CEST: mmhealth:State:0:1:::prscale-a-01:CLOUDGATEWAY:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A25%3A08.337661 CEST: mmhealth:State:0:1:::prscale-a-01:CLOUDGATEWAY:tct_tiering1-vault_backup_01:TCT_SERVICE:HEALTHY:2021-10-01 09%3A24%3A33.013963 CEST: mmhealth:State:0:1:::prscale-a-01:CLOUDGATEWAY:vault_backup_01/:TCT_CSAP:HEALTHY:2021-10-01 09%3A24%3A33.023072 CEST: mmhealth:State:0:1:::prscale-a-01:CESIP:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A35%3A32.969821 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A52%3A49.707704 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_A_CES_0001:NSD:HEALTHY:2021-10-01 09%3A52%3A49.715357 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_M_A_0001:NSD:HEALTHY:2021-10-01 09%3A24%3A14.576509 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_M_A_0002:NSD:HEALTHY:2021-10-01 09%3A24%3A14.596580 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_M_A_0003:NSD:HEALTHY:2021-10-01 09%3A24%3A14.618590 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0001:NSD:HEALTHY:2021-10-01 09%3A24%3A14.637984 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_M_A_0004:NSD:HEALTHY:2021-10-01 09%3A24%3A14.656978 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0002:NSD:HEALTHY:2021-10-01 09%3A24%3A14.673522 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0003:NSD:HEALTHY:2021-10-01 09%3A24%3A14.692509 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0004:NSD:HEALTHY:2021-10-01 09%3A24%3A14.711926 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0005:NSD:HEALTHY:2021-10-01 09%3A24%3A14.742578 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0006:NSD:HEALTHY:2021-10-01 09%3A24%3A14.761914 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0007:NSD:HEALTHY:2021-10-01 09%3A24%3A14.788854 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0008:NSD:HEALTHY:2021-10-01 09%3A24%3A14.808564 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0009:NSD:HEALTHY:2021-10-01 09%3A24%3A14.830882 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0010:NSD:HEALTHY:2021-10-01 09%3A24%3A14.852833 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0011:NSD:HEALTHY:2021-10-01 09%3A24%3A14.876191 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_D_A_0012:NSD:HEALTHY:2021-10-01 09%3A24%3A14.888040 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0005:NSD:HEALTHY:2021-10-01 09%3A24%3A14.915370 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0006:NSD:HEALTHY:2021-10-01 09%3A24%3A14.931229 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0007:NSD:HEALTHY:2021-10-01 09%3A24%3A14.942819 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0008:NSD:HEALTHY:2021-10-01 09%3A24%3A14.956576 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0009:NSD:HEALTHY:2021-10-01 09%3A24%3A14.970095 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS03_NSD_M_A_0010:NSD:HEALTHY:2021-10-01 09%3A24%3A14.993296 CEST: mmhealth:State:0:1:::prscale-a-01:DISK:GPFS_NSD_A_D1_0001:NSD:HEALTHY:2021-10-01 09%3A24%3A15.019350 CEST: mmhealth:State:0:1:::prscale-a-01:GUI:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A53%3A32.099884 CEST: mmhealth:State:0:1:::prscale-a-01:THRESHOLD:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A24%3A01.090924 CEST: mmhealth:State:0:1:::prscale-a-01:THRESHOLD:MemFree_Rule:THRESHOLD_RULE:HEALTHY:2021-10-01 09%3A24%3A32.160416 CEST: mmhealth:State:0:1:::prscale-a-01:THRESHOLD:SMBConnPerNode_Rule:THRESHOLD_RULE:HEALTHY:2021-10-01 09%3A29%3A32.474178 CEST: mmhealth:State:0:1:::prscale-a-01:THRESHOLD:active_thresh_monitor:THRESHOLD_MONITOR:HEALTHY:2021-10-01 09%3A35%3A32.982353 CEST: mmhealth:State:0:1:::prscale-a-01:THRESHOLD:SMBConnTotal_Rule:THRESHOLD_RULE:HEALTHY:2021-10-01 09%3A38%3A48.166426 CEST: mmhealth:State:0:1:::prscale-a-01:PERFMON:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A24%3A17.345148 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSTEM:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A48%3A17.866719 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSTEM:cesSharedRootlv:FILESYSTEM:HEALTHY:2021-10-01 09%3A48%3A17.879658 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSTEM:gpfs01lv:FILESYSTEM:HEALTHY:2021-10-01 09%3A48%3A17.893977 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSTEM:gpfs02lv:FILESYSTEM:HEALTHY:2021-10-01 09%3A24%3A17.503234 CEST: mmhealth:State:0:1:::prscale-a-01:GPFS:prscale-a-01:NODE:TIPS:2021-10-03 03%3A55%3A43.146453 CEST: mmhealth:Event:0:1:::prscale-a-01:GPFS:prscale-a-01:NODE:callhome_not_enabled::2021-10-01 09%3A24%3A16.102766 CEST::no: mmhealth:Event:0:1:::prscale-a-01:GPFS:prscale-a-01:NODE:gpfs_maxfilestocache_small::2021-10-01 09%3A24%3A16.139998 CEST::no: mmhealth:Event:0:1:::prscale-a-01:GPFS:prscale-a-01:NODE:total_memory_small::2021-10-01 09%3A24%3A16.169878 CEST::no: mmhealth:State:0:1:::prscale-a-01:NETWORK:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A24%3A17.308930 CEST: mmhealth:State:0:1:::prscale-a-01:NETWORK:ens192:NIC:HEALTHY:2021-10-01 09%3A24%3A17.323203 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSMGR:prscale-a-01:NODE:HEALTHY:2021-10-01 09%3A24%3A19.114252 CEST: mmhealth:State:0:1:::prscale-a-01:FILESYSMGR:gpfs02lv:FILESYSTEMMGMT:HEALTHY:2021-10-01 09%3A24%3A19.137516 CEST:
Check Protocols components
[root@prscale-a-01 ~]# mmces state show -a -Y mmces:stateShow:HEADER:version:reserved:reserved:NODE:AUTH:BLOCK:NETWORK:HDFS_NAMENODE:AUTH_OBJ:NFS:OBJ:SMB:CES: mmces:stateShow:0:1:::prscale-a-01:DISABLED:DISABLED:HEALTHY:DISABLED:DISABLED:HEALTHY:DISABLED:HEALTHY:HEALTHY: mmces:stateShow:0:1:::prscale-b-01:DISABLED:DISABLED:HEALTHY:DISABLED:DISABLED:HEALTHY:DISABLED:HEALTHY:HEALTHY:
Check particular event
[root@prscale-a-02 ~]# mmhealth cluster show Component Total Failed Degraded Healthy Other ------------------------------------------------------------------------------------- NODE 3 0 0 0 3 GPFS 3 0 0 0 3 NETWORK 3 0 0 3 0 FILESYSTEM 3 0 0 3 0 DISK 31 0 0 31 0 CES 2 0 0 2 0 CESIP 1 0 0 1 0 FILESYSMGR 1 0 0 1 0 GUI 3 0 1 2 0 PERFMON 3 0 0 3 0 THRESHOLD 3 0 0 3 0
mmhealth cluster show [ NODE | GPFS | NETWORK [ UserDefinedSubComponent ]
| FILESYSTEM [UserDefinedSubComponent ]| DISK [UserDefinedSubComponent ]
| CES |AUTH | AUTH_OBJ | BLOCK | CESNETWORK | NFS | OBJECT | SMB
| HADOOP |CLOUDGATEWAY | GUI | PERFMON | THRESHOLD
| AFM [UserDefinedSubComponent] ]
[-Y] [--verbose]
[root@prscale-a-02 ~]# mmhealth cluster show GUI Component Node Status Reasons ------------------------------------------------------------------------------------------ GUI prscale-q-b-01 HEALTHY - GUI prscale-a-02 HEALTHY - GUI prscale-a-01 DEGRADED gui_refresh_task_failed
[root@prscale-a-01 ~]# /usr/lpp/mmfs/gui/cli/runtask help --debug [AFM_FILESET_STATE, AFM_NODE_MAPPING, ALTER_HOST_NAME, CALLBACK, CALLHOME, CALLHOME_STATUS, CAPACITY_LICENSE, CES_ADDRESS, CES_STATE, CES_SERVICE_STATE, CES_USER_AUTH_SERVICE, CLUSTER_CONFIG, CONNECTION_STATUS, DAEMON_CONFIGURATION, DF, DISK_USAGE, DISKS, FILESETS, FILESYSTEM_MOUNT, FILESYSTEMS, FILE_AUDIT_LOG_CONFIG, GUI_CONFIG_CHECK, GPFS_JOBS, DIGEST_NOTIFICATION_TASK, HEALTH_STATES, HEALTH_TRIGGERED, HOST_STATES, HOST_STATES_CLIENTS, INODES, KEYSTORE, LOG_REMOVER, MASTER_GUI_ELECTION, MOUNT_CONFIG, NFS_EXPORTS, NFS_EXPORTS_DEFAULTS, NFS_SERVICE, NODE_LICENSE, NODECLASS, OBJECT_STORAGE_POLICY, OS_DETECT, PM_MONITOR, PM_SENSORS, PM_TOPOLOGY, POLICIES, QUOTA, QUOTA_DEFAULTS, QUOTA_ID_RESOLVE, QUOTA_MAIL, RDMA_INTERFACES, REMOTE_CONFIG, REMOTE_CLUSTER, REMOTE_FILESETS, REMOTE_GPFS_CONFIG, REMOTE_HEALTH_STATES, SMB_GLOBALS, SMB_SHARES, SNAPSHOTS, SNAPSHOTS_FS_USAGE, SNAPSHOT_MANAGER, SQL_STATISTICS, STATE_MAIL, STORAGE_POOL, SYSTEMUTIL_DF, TCT_ACCOUNT, TCT_CLOUD_SERVICE, TCT_NODECLASS, THRESHOLDS, WATCHFOLDER, WATCHFOLDER_STATUS, TASK_CHAIN]
[root@prscale-a-01 ~]# /usr/lpp/mmfs/gui/cli/runtask CLUSTER_CONFIG --debug debug: locale=en_US debug: Running 'mmsdrquery 'sdrq_cluster_info' all ' on node localhost debug: Running 'mmsdrquery 'sdrq_nsd_info' all ' on node localhost debug: Running 'mmlscluster -Y ' on node localhost debug: Running 'mmsdrquery 'sdrq_node_info' all ' on node localhost debug: Running 'mmlsnodeclass 'GUI_MGMT_SERVERS' -Y ' on node localhost debug: Running 'mmlsnodeclass 'GUI_SERVERS' -Y ' on node localhost EFSSG1000I The command completed successfully.
[root@prscale-a-01 ~]# mmhealth event show gui_refresh_task_failed Event Name: gui_refresh_task_failed Event ID: 998254 Description: One or more GUI refresh tasks failed. This could mean that data in the GUI is outdated. Cause: There can be several reasons. User Action: 1.) Check if there is additional information available by executing '/usr/lpp/mmfs/gui/cli/lstasklog [taskname]'. 2.) Run the specified task manually on the CLI by executing '/usr/lpp/mmfs/gui/cli/runtask [taskname] --debug'. 3.) Check the GUI logs under /var/log/cnlog/mgtsrv. 4.) Contact IBM Support if this error persists or occurs more often. Severity: WARNING State: DEGRADED [root@prscale-a-01 ~]# mmhealth event resolve 998254 The specified event gui_refresh_task_failed is not manually resolvable.
A. Objectif
Contrôler l’état d’un filesystem GPFS et rectifier les anomalies
B. Principales entités concernées
Système
C. Description générale et flux des données
D. Définition des termes
Node names
Correspondance GPFS-AIX
GPFS AIX
p5-gpfs-h oragpfh
p5-gpfs-r oragpfr
p5-gpfs-k oragpfk
E. Instructions spécifiques
1) Affichez les informations
mmlsnsd affiche les filesystemes GPFS connues sur la machine. (peut s’exécuter sur les 3 machines)
root@oragpfh:/home/root>mmlsnsd
File system Disk name Primary node Backup node
---------------------------------------------------------------------------
orafs DiskR p5-gpfs-r p5-gpfs-h
orafs DiskH p5-gpfs-r p5-gpfs-h
orafs DiskK gpfs-k
orafs2 DiskR2 p5-gpfs-r p5-gpfs-h
orafs2 DiskH2 p5-gpfs-r p5-gpfs-h
orafs2 DiskK2 gpfs-k
root@oragpfh:/home/root>mmlsnsd -L
L’option –L affiche les NSD volume ID
File system Disk name NSD volume ID Primary node Backup node
--------------------------------------------------------------------------------------------
orafs DiskR 0A040120452A20B4 p5-gpfs-r p5-gpfs-h
orafs DiskH 0A040120452A20B6 p5-gpfs-r p5-gpfs-h
orafs DiskK AC13131D48008499 gpfs-k
orafs2 DiskR2 0A04012046827A9E p5-gpfs-r p5-gpfs-h
orafs2 DiskH2 0A04012046827AA0 p5-gpfs-r p5-gpfs-h
orafs2 DiskK2 AC13131D480084BD gpfs-k
root@oragpfh:/home/root>mmlsnsd -M
L’option –L affiche la correspondance disque GPFS – disque OS/machine
ex : DiskR = hdisk0 sur p5-gpfs-r (primary node)= hdisk3 sur p5-gpfs-h (backup node)
Disk name NSD volume ID Device Node name Remarks
---------------------------------------------------------------------------------------
DiskR 0A040120452A20B4 /dev/hdisk0 p5-gpfs-r primary node
DiskR 0A040120452A20B4 /dev/hdisk3 p5-gpfs-h backup node
DiskH 0A040120452A20B6 /dev/hdisk3 p5-gpfs-r primary node
DiskH 0A040120452A20B6 /dev/hdisk0 p5-gpfs-h backup node
DiskK AC13131D48008499 /dev/descgpfslv gpfs-k primary node
DiskR2 0A04012046827A9E /dev/hdisk4 p5-gpfs-r primary node
DiskR2 0A04012046827A9E /dev/hdisk5 p5-gpfs-h backup node
DiskH2 0A04012046827AA0 /dev/hdisk5 p5-gpfs-r primary node
DiskH2 0A04012046827AA0 /dev/hdisk4 p5-gpfs-h backup node
DiskK2 AC13131D480084BD /dev/descgpfslv2 gpfs-k primary node
mmlsdisk permet d’afficher les disques d’un filesysteme GPFS. (peut s’exécuter sur les 3 machines)
root@oragpfh:/home/root>mmlsdisk orafs
disk driver sector failure holds holds
name type size group metadata data status availability
------------ -------- ------ ------- -------- ----- ------------- ------------
DiskR nsd 512 1 yes yes ready up
DiskH nsd 512 2 yes yes ready up
DiskK nsd 512 3 no no ready up
Le statu normal des disques est ready, la disponibilité est up
En cas d’incohérences, un message d’alerte est affiché après les informations disques !
ex : Attention : Due to an earlier configuration change, the file system
may contain data that is at risk of being lost
Autes commandes :
mmlscluster
root@oragpfh:/home/root>mmlscluster
GPFS cluster information
========================
GPFS cluster name: p5-gpfs-r
GPFS cluster id: 12399281700916488274
GPFS UID domain: p5-gpfs-r
Remote shell command: /usr/bin/ssh
Remote file copy command: /usr/bin/scp
GPFS cluster configuration servers:
-----------------------------------
Primary server: p5-gpfs-r
Secondary server: p5-gpfs-h
Node number Node name IP address Full node name Remarks
-----------------------------------------------------------------------------------
1 p5-gpfs-h 10.11.10.2 p5-gpfs-h quorum node
2 p5-gpfs-r 10.11.10.3 p5-gpfs-r quorum node
3 gpfs-k 10.11.10.4 gpfs-k quorum node
mmlsfs « Fs-name » (Fs-name ={orafs|orafs2}
root@oragpfh:/home/root>mmlsfs orafs
flag value description
---- -------------- -----------------------------------------------------
-s roundRobin Stripe method
-f 8192 Minimum fragment size in bytes
-i 512 Inode size in bytes
-I 16384 Indirect block size in bytes
-m 2 Default number of metadata replicas
-M 2 Maximum number of metadata replicas
-r 2 Default number of data replicas
-R 2 Maximum number of data replicas
-j cluster Block allocation type
-D posix File locking semantics in effect
-k posix ACL semantics in effect
-a 1048576 Estimated average file size
-n 32 Estimated number of nodes that will mount file system
-B 262144 Block size
-Q user;group Quotas enforced
none Default quotas enabled
-F 185344 Maximum number of inodes
-V 8.01 File system version. Highest supported version: 8.02
-u yes Support for large LUNs?
-z no Is DMAPI enabled?
-E yes Exact mtime mount option
-S no Suppress atime mount option
-d DiskR;DiskH;DiskK Disks in file system
-A yes Automatic mount option
-o none Additional mount options
-T /kora Default mount point
2) Réactiver / resynchroniser un disque
Si l’état d’un disque est différent de ready et up, il faut utiliser la commande mmchdisk pour activer le disque et mmrestripefs pour resynchroniser le disque.
Ces commandes mettent un certain temps (jusqu’à 30 minutes). Il est fortement conseiller d’attendre la fin d’une commande avant de lancer la suivante.
Si le disque DiskH est down mmchdisk orafs start -d DiskH
Si le disque DiskH est suspended mmchdisk orafs resume –d DiskH
Si la commande mmlsdisk renseigne des alertes :
Attention : Due to an earlier configuration change, the file system
may contain data that is at risk of being lost
==> mmrestripefs “Fs-name” –r –N mount (Fs-name ={orafs|orafs2})
relancer la commande mmlsdisk “Fs-name” pour conrôler le résultat
Attention : Due to an earlier configuration change, the file system
is no longer properly balanced.
==> mmrestripefs “Fs-name” -b -N mount (Fs-name ={orafs|orafs2})
relancer la commande mmlsdisk “Fs-name” pour conrôler le résultat
gpfs/gpfs_healthcheck.txt · Last modified: 2022/08/29 23:05 by manu
Except where otherwise noted, content on this wiki is licensed under the following license: GNU Free Documentation License 1.3
