We have identified an issue with the network switch and cables that connect the compute nodes of SQUID.
We are currently investigating the time of occurrence and the scope of the impact. Due to this issue, communication errors or performance degradation may occur when running jobs on SQUID.
 
We sincerely apologize for any inconvenience this may cause.
 
As part of the investigation and initial response, we are conducting the following work.
We also apologize for the delay in this notification.
Update (Dec 19, 2025): This work has been completed.
 
----
Date: Thursday, December 18, 2025, from 13:40
Details: Checking the status of network equipment and reconfirming connections
- During the maintenance period, network throughput may be temporarily reduced. As a result, jobs using multiple nodes on SQUID (e.g., MPI jobs) may take longer than usual to complete. There will be no impact on computational results.
- Other services, such as OCTOPUS, are not affected.
----
 
We apologize for the inconvenience and appreciate your patience while we work toward resolution.