De nombreuses commandes existent sous /usr/lpp/mmfs/bin pour analyser et modifier les paramètres liés à GPFS.
Entre autres, pour la vérification des Buffers attachés aux FS, nous avons :
# /usr/lpp/mmfs/bin/mmfsadm dump fs |head -20
[statistics never reset]
Filesystem dump: FSP 0xF1000002E2089370
UMALLOC limits:
bufferDescLimit 131072 desired 131072
fileCacheLimit 15000 desired 15000
statCacheLimit 60000 desired 60000
diskAddrBuffLimit 12000 desired 12000
buffDescMem 101376 k = 131072 * 792 bytes
fileCacheMem 2547648 k = 848111 * 3076 bytes (inode size 512 + 2564)
statCacheMem 19219 k = 60000 * 328 bytes
diskAddrBufMem 1688 k = 12000 * 144 bytes
allocSegmentMem 2813 k = 10000 * 288 bytes
otherMem 471962 k
mdTemp mem 256 k
OpenFile counts: total created 15008 (in use 15000, free 8 q 0)
cached 15000, currently open 255+27, cache limit 15000 (min 10, max 15000), eff limit 15000
OpenInstance counts: in use 256 free 9188 total 9444 using 5164K memory
NFS instance limit: 10000
Pour afficher les informations des systèmes de fichiers :
# mmlsfs all
File system attributes for /dev/fs_db2wrk:
==========================================
flag value description
------------------- ------------------------ -----------------------------------
-f 32768 Minimum fragment size in bytes
-i 512 Inode size in bytes
-I 32768 Indirect block size in bytes
-m 1 Default number of metadata replicas
-M 2 Maximum number of metadata replicas
-r 1 Default number of data replicas
-R 2 Maximum number of data replicas
-j cluster Block allocation type
-D nfs4 File locking semantics in effect
-k all ACL semantics in effect
-n 130 Estimated number of nodes that will mount file system
-B 1048576 Block size
-Q none Quotas enforced
none Default quotas enabled
--filesetdf no Fileset df enabled?
-V 13.23 (3.5.0.7) File system version
--create-time Wed Feb 4 21:22:40 2015 File system creation time
-u yes Support for large LUNs?
-z no Is DMAPI enabled?
-L 4194304 Logfile size
-E yes Exact mtime mount option
-S no Suppress atime mount option
-K whenpossible Strict replica allocation option
--fastea yes Fast external attributes enabled?
--inode-limit 514048 Maximum number of inodes
-P system Disk storage pools in file system
-d gpfs2nsd Disks in file system
--perfileset-quota no Per-fileset quota enforcement
-A yes Automatic mount option
-o none Additional mount options
-T /servdd/db2/db2wrk Default mount point
--mount-priority 0 Mount priority
Quelques commandes utiles aussi :
# mmlsmgr
file system manager node
---------------- ------------------
fs_db2diag 10.42.2.160 (serverbddm1)
fs_db2logs 10.42.2.160 (serverbddm1)
fs_db2hot3 10.42.2.161 (serverbddm2)
fs_db2tmp 10.42.2.161 (serverbddm2)
fs_db2hot2 10.42.2.162 (serverbddm3)
fs_db2wrk 10.42.2.162 (serverbddm3)
fs_db2hot4 10.42.2.163 (serverbddm4)
db2fs1 10.42.2.164 (servercafm1)
fs_db2hot1 10.42.2.165 (servercafm2)
# ./mmlsconfig
Configuration data for cluster db2cluster_20150204162130.serverbddm1:
-----------------------------------------------------------------------
myNodeConfigNumber 1
clusterName db2cluster_20150204162130.serverbddm1
clusterId 464128680123316475
autoload yes
dmapiFileHandleSize 32
minReleaseLevel 3.5.0.11
maxFilesToCache 15000
pagepool 1024M
verifyGpfsReady yes
worker1Threads 2048
sharedMemLimit 3072M
failureDetectionTime 35
leaseRecoveryWait 35
totalPingTimeout 75
tiebreakerDisks gpfs1nsd
maxStatCache 30000
nsdThreadsPerQueue 12
nsdMaxWorkerThreads 480
adminMode allToAll
File systems in cluster db2cluster_20150204162130.serverbddm1:
----------------------------------------------------------------
/dev/db2fs1
/dev/fs_db2diag
/dev/fs_db2hot1
/dev/fs_db2hot2
/dev/fs_db2hot3
/dev/fs_db2hot4
/dev/fs_db2logs
/dev/fs_db2tmp
/dev/fs_db2wrk
#./mmlscluster
GPFS cluster information
========================
GPFS cluster name: db2cluster_20150204162130.serverbddm1
GPFS cluster id: 464128680123316475
GPFS UID domain: db2cluster_20150204162130.serverbddm1
Remote shell command: /var/db2/db2ssh/db2locssh
Remote file copy command: /var/db2/db2ssh/db2scp
GPFS cluster configuration servers:
-----------------------------------
Primary server: serverbddm3
Secondary server: serverbddm2
Node Daemon node name IP address Admin node name Designation
-------------------------------------------------------------------
1 serverbddm1 10.42.2.160 serverbddm1 quorum-manager
2 serverbddm2 10.42.2.161 serverbddm2 quorum-manager
3 serverbddm3 10.42.2.162 serverbddm3 quorum-manager
4 serverbddm4 10.42.2.163 serverbddm4 quorum-manager
5 servercafm1 10.42.2.164 servercafm1 quorum-manager
6 servercafm2 10.42.2.165 servercafm2 quorum-manager
#./mmlsnsd
File system Disk name NSD servers
---------------------------------------------------------------------------
db2fs1 gpfs1nsd (directly attached)
fs_db2diag gpfs3nsd (directly attached)
fs_db2hot1 gpfs6nsd (directly attached)
fs_db2hot2 gpfs7nsd (directly attached)
fs_db2hot3 gpfs8nsd (directly attached)
fs_db2hot4 gpfs9nsd (directly attached)
fs_db2logs gpfs5nsd (directly attached)
fs_db2tmp gpfs4nsd (directly attached)
fs_db2wrk gpfs2nsd (directly attached)
# ./mmlsdisk fs_db2diag
disk driver sector failure holds holds storage
name type size group metadata data status availability pool
------------ -------- ------ ----------- -------- ----- ------------- ------------ ------------
gpfs3nsd nsd 512 -1 yes yes ready up system
#./mmlspv
hdisk3 gpfs2nsd
hdisk4 gpfs3nsd
hdisk5 gpfs1nsd
hdisk6 gpfs4nsd
hdisk7 gpfs5nsd
hdisk8 gpfs6nsd
hdisk9 gpfs7nsd
hdisk10 gpfs8nsd
hdisk11 gpfs9nsd
#./mmlsmount all
File system db2fs1 is mounted on 6 nodes.
File system fs_db2diag is mounted on 6 nodes.
File system fs_db2hot1 is mounted on 6 nodes.
File system fs_db2hot2 is mounted on 6 nodes.
File system fs_db2hot3 is mounted on 6 nodes.
File system fs_db2hot4 is mounted on 6 nodes.
File system fs_db2logs is mounted on 6 nodes.
File system fs_db2tmp is mounted on 6 nodes.
File system fs_db2wrk is mounted on 6 nodes.
#./mmlsnode
GPFS nodeset Node list
------------- -------------------------------------------------------
db2cluster_20150204162130 serverbddm1 serverbddm2 serverbddm3 serverbddm4 servercafm1 servercafm2
#./mmlsfs all
File system attributes for /dev/db2fs1:
=======================================
flag value description
------------------- ------------------------ -----------------------------------
-f 32768 Minimum fragment size in bytes
-i 512 Inode size in bytes
-I 32768 Indirect block size in bytes
-m 1 Default number of metadata replicas
-M 2 Maximum number of metadata replicas
-r 1 Default number of data replicas
-R 2 Maximum number of data replicas
-j cluster Block allocation type
-D nfs4 File locking semantics in effect
-k all ACL semantics in effect
-n 130 Estimated number of nodes that will mount file system
-B 1048576 Block size
-Q none Quotas enforced
none Default quotas enabled
--filesetdf no Fileset df enabled?
-V 13.23 (3.5.0.7) File system version
--create-time Wed Feb 4 16:23:30 2015 File system creation time
-u yes Support for large LUNs?
-z no Is DMAPI enabled?
-L 4194304 Logfile size
-E no Exact mtime mount option
-S yes Suppress atime mount option
-K whenpossible Strict replica allocation option
--fastea yes Fast external attributes enabled?
--inode-limit 135168 Maximum number of inodes
-P system Disk storage pools in file system
-d gpfs1nsd Disks in file system
--perfileset-quota no Per-fileset quota enforcement
-A yes Automatic mount option
-o none Additional mount options
-T /serverbdd/db2/dbpath Default mount point
--mount-priority 0 Mount priority
