Recent failures

Status of reduction of computation nodes as of 12:00 on May 25

  • mjobs.q is at 80% of its normal usage
  • ljobs.q is at 50% of its normal usage
  • Some exclusive queues are unavailable

Other queues are normal.

May 19, 2022

A failure has occurred in the cooling system of SHIROKANE and the number of compute nodes was reduced at the following time.

  • mjobs.q is at 80% of its normal usage
  • ljobs.q is at 50% of its normal usage
  • Some exclusive queues are unavailable
  • Many GPU-equipped nodes are unavailable

Other queues are normal.

From around 21:30 am, May 19, 2022 -

May 12, 2022

A failure has occurred in the cooling system of SHIROKANE and the number of compute nodes was reduced at the following time, but it has been restored now.

From around 6:00 am, May 08, 2022 - 18:00, May 12, 2022

Status of reduction of computation nodes as of 20:00 on May 11

  • mjobs.q is at 80% of its normal usage
  • ljobs.q is at 30% of its normal usage
  • arm.q is unavailable

Other queues are normal.

Status of reduction of computation nodes as of 20:00 on May 10

  • mjobs.q is at 45% of its normal usage
  • ljobs.q is at 30% of its normal usage
  • Some exclusive queues are unavailable
  • GPU-equipped nodes are at 10% of its normal usage
  • arm.q is unavailable

Other queues are normal.

May 9, 2022

A failure occurred in rshare1 at the following time, but it has been restored now.

From 18:18, May 09, 2022 - 20:26, May 09, 2022

Status of reduction of computation nodes as of 23:00 on May 9

  • mjobs.q is at 40% of its normal usage
  • ljobs.q is at 30% of its normal usage
  • Some exclusive queues are unavailable
  • Many GPU-equipped nodes are unavailable

Other queues are normal.

May 8, 2022

A failure has occurred in the cooling system of SHIROKANE and the computation node of Shirokane5 has been stopped.

From around 6:00 am, May 08, 2022 -

Apr 4, 2022

A failure occurred in network at the following time, but it has been restored now.

14:30, Apr 1, 2022 - 12:00, Apr 4, 2022.

Sep 29, 2021

The failure to access Archive Disk from the compute nodes has been restored. Please do not access Archive Disk from compute nodes, instead use intr.q, cp.q and login nodes.

From 03:40, September 29, 2021 - 09:00, September 29, 2021

Aug 31, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 14:32, August 31, 2021 - 14:36, August 31, 2021

Aug 25, 2021

Maintenance of yshare3 was performed in the following time zone.

From 10:00, August 25, 2021 - 10:15, August 20, 2021

Aug 20, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 18:16, August 20, 2021 - 18:26, August 20, 2021

A failure occurred in yshare3 at the following time, but it has been restored now.

From 15:12, August 20, 2021 - 15:24, August 20, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 14:08, August 20, 2021 - 14:42, August 20, 2021

Aug 19, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 04:22, August 19, 2021 - 10:08, August 19, 2021

Aug 17, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 19:22, August 17, 2021 - 19:42, August 17, 2021

A failure occurred in yshare2 at the following time, but it has been restored now.

From 14:30, August 17, 2021 - 17:25, August 17, 2021

Jul 13, 2021

The failure to access Archive Disk from the compute nodes has been restored. Please do not access Archive Disk from compute nodes, instead use intr.q, cp.q and login nodes.

From 12:30, July 13, 2021 - 14:00, July 13, 2021

May 11, 2021

Archive Disk has been restored from the failure.

From 01:46, May 11, 2021 - 10:34, May 11, 2021

May 1, 2021

The failure to access Archive Disk from the compute nodes has been restored. Please do not access Archive Disk from compute nodes, instead use intr.q, cp.q and login nodes.

From 17:16, May 01, 2021 - 10:04, May 06, 2021

Mar 16, 2021

The failure to access Archive Disk from the compute nodes has been restored. Please do not access Archive Disk from compute nodes, instead use intr.q, cp.q and login nodes.

From 08:46, March 16, 2021 - 09:52, March 16, 2021

Feb 28, 2021

The failure to access Archive Disk from the compute nodes has been restored. Please do not access Archive Disk from compute nodes, instead use intr.q, cp.q and login nodes.

From 19:36, February 28, 2021 - 09:58, March 01, 2021

Feb 3, 2021

Maintenance of yshare2 was performed in the following time zone.

13:00, February 3, 2021 - 17:50, February 3, 2021.

Past failures