January 2024 - Qlustar General - Qlustar Mailing Lists

Exception trying to save updated Info field for user in LDAP (Qluman/server 13.4.7)
by Rolandas Naujikas 29 Feb '24

29 Feb '24

Exception handling request Traceback (most recent call last): File "/usr/lib/python3/dist-packages/qluman-13/server/admin.py", line 2967, in on_request yield from handler(self, channel, msg) File "/usr/lib/python3/dist-packages/qluman-13/server/admin.py", line 1759, in request_DBUpdateRequest table.update(entries) File "/usr/lib/python3/dist-packages/qluman-13/server/db/Ldap.py", line 106, in update entries = self._do_update(entries) File "/usr/lib/python3/dist-packages/qluman-13/server/db/Ldap.py", line 443, in _do_update self.manage.ol_user_modify(entry.uname, entry) File "/usr/lib/python3/dist-packages/qluman-13/components/ldap/manage.py", line 741, in ol_user_modify attr = USER_DB_TO_LDAP_FIELD_NAME[field] KeyError: 'locked'

3 4

Security/Bug fix releases 13.1.4, 12.0.3.3
by no-reply-list＠qlustar.org 30 Jan '24

30 Jan '24

The Qlustar releases 13.1.4 and 12.0.3.3 are ready including a number of security/bug fixes. Please check the following web pages for details about security fixes and special update instructions: https://qlustar.com/qsa/2024/0130241 https://qlustar.com/qsa/2024/0130242 The following non-security related updates/enhancements/bug fixes are included: For Qlustar 13: - Update to QluMan 13.5.0 - Update to Lustre 2.15.4 - Update to Nvidia graphics drivers 535.154.05 - Switch to use pam_slurm_adopt for restricting ssh access to slurm nodes

1 0

Infiniband - headnode does not have ib0 interface / ip adress on infiniband interface
by wo.nicolai＠vuykrotterdam.com 30 Jan '24

30 Jan '24

Hi all, I've started with a new cluster using Qlustar 13.1 (fresh install). Hardware setup contains (currently) 3 HP DL380 machines, all hardware boxes have an infiniband interface and are connected to the same infiniband switch. 1 headnode (with openSM during installation), FE-login as VM, 2 compute nodes. I noticed that the on the head node the infiniband interface is down. Upon investigating I discovered the following: In the qlustar management interface, the network config for the headnode shows ib0 in the commandline interface on the headnode using "ip address" I do not see any ib0 interface. I do see ibo49d1 (o not zero) "9: ibo49d1: <BROADCAST,MULTICAST> mtu 2044 qdisc fq_codel state DOWN group default qlen 256 link/infiniband 80:00:02:25:fe:80:00:00:00:00:00:00:04:09:73:ff:ff:e4:f4:22 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff altname ibp4s0d1" in /etc/network/interfaces interface ib0 is mentioned When I update the network config for the headnode in the qlustar management interface from ib0 to ibo49d1 and reboot after, the interface remains down without any ip address. I also noticed that for such a change in the qlustar management interface, I do not need to write files? in /etc/network/interface ib0 remains mentioned, while I expected that this would be updated to ibo49d1. Manually changing ib0 into ibo49d1 in /etc/network/interfaces did not work either. The infiniband port is active: ibv_devinfo -d mlx4_0 hca_id: mlx4_0 transport: InfiniBand (0) fw_ver: 2.42.5700 node_guid: 0409:73ff:ffe4:f420 sys_image_guid: 0409:73ff:ffe4:f423 vendor_id: 0x02c9 vendor_part_id: 4103 hw_ver: 0x0 board_id: HP_1380110017 phys_port_cnt: 2 port: 1 state: PORT_DOWN (1) max_mtu: 4096 (5) active_mtu: 1024 (3) sm_lid: 0 port_lid: 0 port_lmc: 0x00 link_layer: Ethernet port: 2 state: PORT_ACTIVE (4) max_mtu: 4096 (5) active_mtu: 4096 (5) sm_lid: 1 port_lid: 1 port_lmc: 0x00 link_layer: InfiniBand Using ibnetdiscover on the headnode, both compute nodes and the switch is listed. Obviously I'm missing something. How do I get IPoIB up and running on the headnode? The above is for the head node only. the compute nodes do have an interface ib0 and an ip adress for this interface.

3 3

node install II (forget the previous one)
by Christophe Guilbert 08 Jan '24

08 Jan '24

Scratch my previous email since I moved forward. Here my new problem. I managed to create beo-206 , I can see it in "Enclosure View" Than I select it in "Enclosure View" and open "Manage Hosts" -> "Hardware Wizard" -> "Selected" I have the following message: "Missing Hardware info: beo-206" I created specific "host template", "hardware property set" for that node (2 x 12 core, 2 thread per core), I tried all kind of properties combinations. no luck , the same message of missing hardware is coming back. I did took example on beosrv-c and set up the properties as following: "beo-206" -> "Select host template" -> "<None>" "beo-206" -> "Set Config" -> "Network Config" -> "Standard-Node" it does not work either. same error. On the node side , PXE is looping trying to get a DHCP address. rebooting the node did not changed the outcome. What I am missing here, how to complete the "Hardware Wizard" ? I tried all kind of properties for beo-206, which ones would you recommend me to try ? Thanks Chris

2 1

node install
by Christophe Guilbert 03 Jan '24

03 Jan '24

Hi guys and happy new year. I am trying to move forward with my first node install So far, my node was set to beo-206, I can see it in Enclosure View and host overview. I am now stuck , What next ? Was trying to play with "hardware Wizard" but beo-206 is not even listed there. Was playing with "manage sets" , create a new "Host Templates" but could not find any logical way to complete the node configuration BTW what is SM twin^2 1GB ? My node is 2 x 24 cores, how do I create a template ? how Do i automatically set up the hardware type for slurm or any template, how to create an image ? .... I would assume that my next step would be to list and register the node with the correct hardware, how to do that ? I would like to create a template for this node as I have about 20 of the same time. Need help , thanks Chris

1 0