Greetings, <br><br>I'm trying to get Lustre 1.8.1.1 working, but have been running into nothing but trouble.<br><br>Long story short, i'm trying to mount the OST on the OSS, but i keep getting this error: <br><br>[root@oss ~]# mount -t lustre /dev/lustre/OST /lustre/OSS<br>
mount.lustre: mount /dev/lustre/OST at /lustre/OSS failed: Input/output error<br>
Is the MGS running?<br><br>What i don't understand is, the MGS is running as far as i know. I followed this guide <a href="http://manual.lustre.org/manual/LustreManual16_HTML/ConfiguringLustreExamples.html" target="_blank">http://manual.lustre.org/manual/LustreManual16_HTML/ConfiguringLustreExamples.html</a>. After that didn't work, i tried this guide <a href="http://unixfoo.blogspot.com/2009/11/lustre-cluster-filesystem-quick-setup.html">http://unixfoo.blogspot.com/2009/11/lustre-cluster-filesystem-quick-setup.html</a>, and that didn't work either. I have the MDS and MGS on the same system.<br>
<br>In the below walk-through of what i've done from start to finish, it is clear that i mounted the MGS partition, which, if i understand lustre correctly, should start the MGS service, yet the OSS complains with an I/O error.<br>
<br>I've been struggling with this for some time, and am near giving up. Any help will be greatly appreciated.<br><br><br>Thanks,<br>Dusty<br><br>------------ here is what i typed in on the mds server (and its output). -------------<br>
[root@mds ~]# nano /etc/modprobe.conf<br>[root@mds ~]# pvcreate /dev/hdb1<br> Physical volume "/dev/hdb1" successfully created<br>[root@mds ~]# vgcreate lustre /dev/hdb1<br> Volume group "lustre" successfully created<br>
[root@mds ~]# lvcreate -L 19G -n MGS lustre<br> Logical volume "MGS" created<br>[root@mds ~]# mkfs.lustre --mgs /dev/lustre/MGS <br><br> Permanent disk data:<br>Target: MGS<br>Index: unassigned<br>Lustre FS: lustre<br>
Mount type: ldiskfs<br>Flags: 0x74<br> (MGS needs_index first_time update )<br>Persistent mount opts: errors=remount-ro,iopen_nopriv,user_xattr<br>Parameters:<br><br>checking for existing Lustre data: not found<br>
device size = 19456MB<br>2 6 18<br>formatting backing filesystem ldiskfs on /dev/lustre/MGS<br> target name MGS<br> 4k blocks 0<br> options -J size=400 -q -O dir_index,extents,uninit_groups -F<br>mkfs_cmd = mke2fs -j -b 4096 -L MGS -J size=400 -q -O dir_index,extents,uninit_groups -F /dev/lustre/MGS<br>
Writing CONFIGS/mountdata<br>[root@mds ~]# mount -t lustre /dev/lustre/MGS /lustre/MGS/<br><br>[root@mds ~]# lvcreate -L 18G -n MDT lustre<br> Logical volume "MDT" created<br>[root@mds ~]# mkfs.lustre --fsname=datafs --mdt --reformat --mgsnode=192.168.0.2@tcp0 /dev/lustre/MDT <br>
<br> Permanent disk data:<br>Target: datafs-MDTffff<br>Index: unassigned<br>Lustre FS: datafs<br>Mount type: ldiskfs<br>Flags: 0x71<br> (MDT needs_index first_time update )<br>Persistent mount opts: errors=remount-ro,iopen_nopriv,user_xattr<br>
Parameters: mgsnode=192.168.0.2@tcp mdt.group_upcall=/usr/sbin/l_getgroups<br><br>device size = 18432MB<br>2 6 18<br>formatting backing filesystem ldiskfs on /dev/lustre/MDT<br> target name datafs-MDTffff<br> 4k blocks 0<br>
options -J size=400 -i 4096 -I 512 -q -O dir_index,extents,uninit_groups -F<br>mkfs_cmd = mke2fs -j -b 4096 -L datafs-MDTffff -J size=400 -i 4096 -I 512 -q -O dir_index,extents,uninit_groups -F /dev/lustre/MDT<br>
Writing CONFIGS/mountdata<br>[root@mds ~]# mkdir /lustre/MDT<br>[root@mds ~]# mount -t lustre /dev/lustre/MDT /lustre/MDT<br><br>
<br>------------ Here is exactly what i typed in on the OSS server, as well as what was output. -------------------<br>[root@oss ~]# pvcreate /dev/hdc1<br> Physical volume "/dev/hdc1" successfully created<br>[root@oss ~]# vgcreate lustre /dev/hdc1<br>
/dev/hdb: open failed: No medium found<br> Volume group "lustre" successfully created<br>[root@oss ~]# vgs<br> VG #PV #LV #SN Attr VSize VFree <br> VolGroup00 1 2 0 wz--n- 74.41G 0 <br>
lustre 1 0 0 wz--n- 37.27G 37.27G<br>[root@oss ~]# lvcreate -n OST -L 37GB lustre<br> Logical volume "OST" created<br>[root@oss ~]# mkfs.lustre --fsname=datafs --ost --mgsnode=192.168.0.2@tcp0 /dev/lustre/OST <br>
<br> Permanent disk data:<br>Target: datafs-OSTffff<br>Index: unassigned<br>Lustre FS: datafs<br>Mount type: ldiskfs<br>Flags: 0x72<br> (OST needs_index first_time update )<br>Persistent mount opts: errors=remount-ro,extents,mballoc<br>
Parameters: mgsnode=192.168.0.2@tcp<br><br>checking for existing Lustre data: not found<br>device size = 37888MB<br>2 6 18<br>formatting backing filesystem ldiskfs on /dev/lustre/OST<br> target name datafs-OSTffff<br>
4k blocks 0<br> options -J size=400 -i 16384 -I 256 -q -O dir_index,extents,uninit_groups -F<br>mkfs_cmd = mke2fs -j -b 4096 -L datafs-OSTffff -J size=400 -i 16384 -I 256 -q -O dir_index,extents,uninit_groups -F /dev/lustre/OST<br>
Writing CONFIGS/mountdata<br>[root@oss ~]# mkdir -p /lustre/OSS<br>[root@oss ~]# mount -t lustre /dev/lustre/OST /lustre/OSS<br>mount.lustre: mount /dev/lustre/OST at /lustre/OSS failed: Input/output error<br>Is the MGS running?<br>
<br clear="all">
<br>-- <br>The graduate with a Science degree asks, "Why does it work?" The graduate with an Engineering degree asks, "How does it work?" The graduate with an Accounting degree asks, "How much will it cost?" The graduate with an Arts degree asks, "Do you want fries with that?"<br>