9/14 7:00 p.m. add
 

We have just completed the recovery operations for the recurring issue, and the delay has now been resolved.We sincerely apologize for the inconvenience caused.
We will notify you separately regarding your affected jobs.
 
----
 
Since around 3:00 a.m. on September 13, there is a failure in SQUID file system(Lustre), causing I/O delays.
 

Specifically, the following phenomena are occurring:
 

- Jobs running on the compute nodes are delayed
- Command operations on the frontend server are delayed
 

Currently, we are conducting an investigation into the cause of the failure and working on restoration.
We apologize for the inconvenience.