[prev in list] [next in list] [prev in thread] [next in thread]
List: lustre-discuss
Subject: [Lustre-discuss] lctl ping fails to/from the client
From: atchley () myri ! com (Scott Atchley)
Date: 2007-04-14 7:39:21
Message-ID: 6B937FDD-730B-4BD0-8A83-5A3814175658 () myri ! com
[Download RAW message or body]
Hi all,
Problem solved. Some nodes had iptables blocking port 988 and some
didn't. :-)
Scott
On Apr 13, 2007, at 10:49 PM, Scott Atchley wrote:
> Hi all,
>
> I am trying to set up Lustre using TCP. I have the following in /
> etc/modprobe.conf:
>
> options lnet networks="tcp0(eth2)"
>
> to specify the third NIC only. I have two OSSs and one MDS. They
> startup and see each fine. My XML is pasted below.
>
> When I try to have a client start with:
>
> # lconf --node client lustre-fs.xml
>
> it hangs at:
>
> + mount -t lustre_lite -o
> osc=lov1,mdc=MDC_compute-0-1.local_mds1_MNT_client lustre-fs /mnt/
> lustre
>
> If I check its NIDs, I see:
>
> # cat /proc/sys/lnet/nis
> nid refs peer max tx min
> 0@lo 2 0 0 0 0
> 192.168.1.254@tcp 2 8 256 256 255
>
> which is the correct address for this client. If instead of using
> lconf, I simply modprobe lnet and run lctl, then I try to ping the
> MDS. It fails:
>
> # lctl
> lctl > network up
> LNET configured
> lctl > network tcp
> lctl > ping 192.168.1.250
> failed to ping 192.168.1.250@tcp: Input/output error
>
> Yet, I can ping the node on the command line:
>
> # ping -s 9000 192.168.1.250
> PING 192.168.1.250 (192.168.1.250) 9000(9028) bytes of data.
> 9008 bytes from 192.168.1.250: icmp_seq=0 ttl=64 time=0.142 ms
>
> # ping -s 9000 nas-0-0-m
> PING nas-0-0-m.local (192.168.1.250) 9000(9028) bytes of data.
> 9008 bytes from nas-0-0-m.local (192.168.1.250): icmp_seq=0 ttl=64
> time=0.111 ms
>
> If I try using lctl on the MDS to ping the client, it fails as well
> but I can ping the two OSSs.
>
> Any suggestions?
>
> Thanks,
>
> Scott
>
>
> <?xml version='1.0' encoding='UTF-8'?>
> <lustre version='2003070801' mtime='1176488849'>
> <ldlm name='ldlm' uuid='ldlm_UUID'/>
> <node uuid='client_UUID' name='client'>
> <profile_ref uuidref='PROFILE_client_UUID'/>
> <network uuid='NET_client_lnet_UUID' nettype='lnet'
> name='NET_client_lnet'>
> <nid>*</nid>
> <clusterid>0</clusterid>
> <port>988</port>
> </network>
> </node>
> <profile uuid='PROFILE_client_UUID' name='PROFILE_client'>
> <ldlm_ref uuidref='ldlm_UUID'/>
> <network_ref uuidref='NET_client_lnet_UUID'/>
> <mountpoint_ref uuidref='MNT_client_UUID'/>
> </profile>
> <node uuid='storenode1-m_UUID' name='storenode1-m'>
> <profile_ref uuidref='PROFILE_storenode1-m_UUID'/>
> <network uuid='NET_storenode1-m_lnet_UUID' nettype='lnet'
> name='NET_storenode1-m_lnet'>
> <nid>192.168.1.2</nid>
> <clusterid>0</clusterid>
> <port>988</port>
> </network>
> </node>
> <profile uuid='PROFILE_storenode1-m_UUID'
> name='PROFILE_storenode1-m'>
> <ldlm_ref uuidref='ldlm_UUID'/>
> <network_ref uuidref='NET_storenode1-m_lnet_UUID'/>
> <osd_ref uuidref='OSD_ost1_storenode1-m_UUID'/>
> </profile>
> <node uuid='storenode2-m_UUID' name='storenode2-m'>
> <profile_ref uuidref='PROFILE_storenode2-m_UUID'/>
> <network uuid='NET_storenode2-m_lnet_UUID' nettype='lnet'
> name='NET_storenode2-m_lnet'>
> <nid>192.168.1.4</nid>
> <clusterid>0</clusterid>
> <port>988</port>
> </network>
> </node>
> <profile uuid='PROFILE_storenode2-m_UUID'
> name='PROFILE_storenode2-m'>
> <ldlm_ref uuidref='ldlm_UUID'/>
> <network_ref uuidref='NET_storenode2-m_lnet_UUID'/>
> <osd_ref uuidref='OSD_ost2_storenode2-m_UUID'/>
> </profile>
> <node uuid='nas-0-0-m_UUID' name='nas-0-0-m'>
> <profile_ref uuidref='PROFILE_nas-0-0-m_UUID'/>
> <network uuid='NET_nas-0-0-m_lnet_UUID' nettype='lnet'
> name='NET_nas-0-0-m_lnet'>
> <nid>192.168.1.250</nid>
> <clusterid>0</clusterid>
> <port>988</port>
> </network>
> </node>
> <profile uuid='PROFILE_nas-0-0-m_UUID' name='PROFILE_nas-0-0-m'>
> <ldlm_ref uuidref='ldlm_UUID'/>
> <network_ref uuidref='NET_nas-0-0-m_lnet_UUID'/>
> <mdsdev_ref uuidref='MDD_mds1_nas-0-0-m_UUID'/>
> </profile>
> <mds uuid='mds1_UUID' name='mds1'>
> <active_ref uuidref='MDD_mds1_nas-0-0-m_UUID'/>
> <lovconfig_ref uuidref='LVCFG_lov1_UUID'/>
> <filesystem_ref uuidref='FS_fsname_UUID'/>
> </mds>
> <mdsdev uuid='MDD_mds1_nas-0-0-m_UUID' name='MDD_mds1_nas-0-0-m'>
> <fstype>ldiskfs</fstype>
> <devpath>/var/run/lustre/mds</devpath>
> <autoformat>yes</autoformat>
> <devsize>5000000</devsize>
> <journalsize>0</journalsize>
> <inodesize>0</inodesize>
> <node_ref uuidref='nas-0-0-m_UUID'/>
> <target_ref uuidref='mds1_UUID'/>
> </mdsdev>
> <lov stripesize='4194304' stripecount='-1' stripepattern='0'
> uuid='lov1_UUID' name='lov1'>
> <mds_ref uuidref='mds1_UUID'/>
> <obd_ref uuidref='ost1_UUID'/>
> <obd_ref uuidref='ost2_UUID'/>
> </lov>
> <lovconfig uuid='LVCFG_lov1_UUID' name='LVCFG_lov1'>
> <lov_ref uuidref='lov1_UUID'/>
> </lovconfig>
> <ost uuid='ost1_UUID' name='ost1'>
> <active_ref uuidref='OSD_ost1_storenode1-m_UUID'/>
> </ost>
> <osd osdtype='obdfilter' uuid='OSD_ost1_storenode1-m_UUID'
> name='OSD_ost1_storenode1-m'>
> <target_ref uuidref='ost1_UUID'/>
> <node_ref uuidref='storenode1-m_UUID'/>
> <fstype>ldiskfs</fstype>
> <devpath>/dev/sda1</devpath>
> <autoformat>no</autoformat>
> <devsize>0</devsize>
> <journalsize>0</journalsize>
> <inodesize>0</inodesize>
> </osd>
> <ost uuid='ost2_UUID' name='ost2'>
> <active_ref uuidref='OSD_ost2_storenode2-m_UUID'/>
> </ost>
> <osd osdtype='obdfilter' uuid='OSD_ost2_storenode2-m_UUID'
> name='OSD_ost2_storenode2-m'>
> <target_ref uuidref='ost2_UUID'/>
> <node_ref uuidref='storenode2-m_UUID'/>
> <fstype>ldiskfs</fstype>
> <devpath>/dev/sda1</devpath>
> <autoformat>no</autoformat>
> <devsize>0</devsize>
> <journalsize>0</journalsize>
> <inodesize>0</inodesize>
> </osd>
> <filesystem uuid='FS_fsname_UUID' name='FS_fsname'>
> <mds_ref uuidref='mds1_UUID'/>
> <obd_ref uuidref='lov1_UUID'/>
> </filesystem>
> <mountpoint uuid='MNT_client_UUID' name='MNT_client'>
> <filesystem_ref uuidref='FS_fsname_UUID'/>
> <path>/mnt/lustre</path>
> </mountpoint>
> </lustre>
>
>
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss@clusterfs.com
> https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
>
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic