Starting around 4 PM Sunday, the Phoenix scratch filesystem became non-responsive, causing issues with access to files and directories stored in ~/scratch. Functionality was restored promptly Monday morning, and at this time, all systems are performing as expected. If you were running jobs that utilized scratch storage during this outage, they may have been negatively impacted; please reach out to pace-support@oit.gatech.edu with related IDs for any such jobs.

[Update – 08/13/2021 – 10:00AM]

Dear PACE Users,

Our scheduled maintenance has completed ahead of the schedule! All Coda datacenter clusters are ready for research. As usual, we have released all users jobs that were held by the scheduler. We appreciate everyone’s patience as we worked through these maintenance activities.

Our next maintenance period is tentatively scheduled to begin at 6:00AM on Wednesday, 11/03/2021, and it is tentatively scheduled to conclude by 11:59PM on Friday, 11/05/2021.

Here is an update on the tasks performed during this maintenance period.

ITEMS REQUIRING USER ACTION:

• None.

ITEMS NOT REQUIRING USER ACTION:

• [Complete] [Datacenter] Databank will need to replace components of one of the transformers feeding the room that will require a complete power off for the research hall that includes the PACE managed clusters.
• [Complete] [Storage] Upgrade controller for the storage appliances: SFA200NV, SFA18KE
• [Complete] [Storage] Replace a miniSAS cable on Hive storage appliance: SFA14KXE
• [Complete] [Storage] Replace a failed hard drive on a pre-production OSG cluster
• [Complete] [System/Security] Operating system patch installs
• [Complete] [System/Security] Endpoint Protection Updates
• [Complete] [Benchmarks] Conduct IO500 and HPCG benchmarks for Hive and Phoenix clusters
• [Complete] [System] Update NVidia drivers and add NVidia specific libraries
• [Complete] [System] Reboot scheduler nodes

If you have any questions or concerns, please do not hesitate to contact us at pace-support@oit.gatech.edu.

Best,

The PACE Team

[Original Message – 07/13/2021 – 4:15PM that was updated on August 4, 2021 with list of tasks] 

Dear PACE Users,

This is another friendly reminder that our next Maintenance period is scheduled to begin at 6:00AM on Wednesday, 08/11/2021, which is tentatively scheduled to conclude by 11:59PM on Friday, 08/13/2021.  Please note, as usual, jobs with resource requests that would be running during the Maintenance Period will be held until after the Maintenance Period by the scheduler. During the Maintenance Period, access to all the PACE managed computational and storage resources will be unavailable.

Please see the list of activities to be completed:

ITEMS REQUIRING USER ACTION:

• Currently, none.

ITEMS NOT REQUIRING USER ACTION:

• [Datacenter] Databank will need to replace components of one of the transformers feeding the room that will require a complete power off for the research hall that includes the PACE managed clusters.
• [Storage] Upgrade controller for the storage appliances: SFA200NV, SFA18KE
• [Storage] Replace a miniSAS cable on Hive storage appliance: SFA14KXE
• [Storage] Replace a failed hard drive on a pre-production OSG cluster
• [System/Security] Operating system patch installs
• [System/Security] Endpoint Protection Updates
• [Benchmarks] Conduct IO500 and HPCG benchmarks for Hive and Phoenix clusters
• [System] Update Nvidia drivers and add Nvidia specific libraries
• [System] Reboot scheduler nodes

If you have any questions or concerns, please do not hesitate to contact us at pace-support@oit.gatech.edu.

Best,

The PACE Team

[Update – July 13, 2021] 

OIT has restored operation to Data Warehouse service on July 12, 11:22AM.  Shortly after, PACE has restored functionality to our database and our administrative services.   OIT has continued to monitor the Data Warehouse service.  At this time, all PACE user facing utilities such as pace-check-queue, pace-quota, and pace-whoami are operational.

Please accept our sincere apology for any inconvenience that this temporary limitation may have caused you.  If you have any questions or concerns, please direct them to pace-support@oit.gatech.edu

[Original Message – July 12, 2021]

Dear PACE Users,

We are reaching out to inform you that on Saturday at about 10:00am, there was an outage to OIT’s Enterprise Data Warehouse service, which PACE relies on for hosting our database instance that subsequently went down at 11:07am.  The impact to PACE from this service outage is mainly limited to administrative side, and there is some impact to user facing utilities such as pace-check-queue; however, there is no impact to users’ jobs or ability to submit jobs.

What’s happening and what we are doing:  Currently, OIT is investigating the outage impacting the Data Warehouse service that occurred on Saturday, and this outage is tracked at OIT’s status page.   PACE is monitoring this development closely.

How does this impact me:  This data warehouse service outage impacts user facing utilities such as pace-check-queue, pace-quota, pace-whoami that are partially or fully nonfunctional.   In addition, until the Data Warehouse service is restored, PACE will be unable to create new user and PI account requests.  

What we will continue to do:  PACE team will continue to monitor this development, and we will report as needed.   

Please accept our sincere apology for any inconvenience that this temporary limitation may cause you.  If you have any questions or concerns, please direct them to pace-support@oit.gatech.edu

Best,

The PACE Team

Dear PACE Users,

It has come to our attention that we are not receiving support requests generated by the pace-support.sh script, which allows submission of support tickets directly from PACE clusters. Our investigation is ongoing.

At this time, please email us at pace-support@oit.gatech.edu from a non-PACE system for all support requests, to ensure that we receive your message.

From our initial investigation, it appears that this outage began at some point in May. We apologize for any lost messages since then. If you have been trying to reach us via the pace-support script, please email us instead. You should receive an automated acknowledgement email from Service Desk when your request is successfully processed.

Please contact us at pace-support@oit.gatech.edu with questions.

The PACE Team

[Update – 06/25 11:40PM]

The storage controller cable on Hive cluster was replaced this evening and brought back online.  Unfortunately, after the repairs, GPFS storage mounts became unavailable, which had interrupted users’ running jobs this evening.   We’ve paused the scheduler briefly while we restarted the GPFS services across the cluster.  The storage mounts were restored, and scheduler has been resumed.

User’s jobs that have been running/queued between about 7:00pm and 10:30pm today (6/25/2021)  may have been interrupted, and we recommend the users to check on their jobs and resubmit your jobs as needed.  Please accept our sincerest apology for this inconvenience.

We will continue to monitor the services and update as needed.  If you have any questions, please contact us at pace-support@oit.gatech.edu.

[Original Message – 06/25 5:12PM]

Dear Hive Users,

We are reaching out to inform you that one of our storage controllers for Hive cluster has a bad cable that needs to be replaced to ensure optimal performance and data integrity.   We have the cable at hand, and are in a process of replacing this cable this evening, Friday 06/25/2021.  This work will impact storage performance briefly, which users may experience as storage slowness as we are routing all our traffic to a secondary controller during this operation. 

What’s happening and what we are doing:  More specifically, PACE has assessed a high failure rate of the disks in one of the enclosures for the storage controller with a bad cable.  As a precaution, we will be shutting down the controller with the bad cable to unfail the disks and to ensure data integrity of the system.  We will work on replacing the cable this evening during which the controller will be shutdown.  During this work, all storage traffic will be routed to a secondary controller that is fully operational.   Given the anticipated load on the secondary controller, we anticipate users experiencing performance degradation.  

How does this impact me:  With only one storage control in operation, users may experience storage slowness.  In a highly unlikely event, this could cause downtime to the storage which would impact all users’ running jobs; however, we do not anticipate any storage outage during this operation.

What we will continue to do:  PACE team will work on the cable replacement and restore the storage to optimal operation, and update the community as needed. 

Please accept our sincere apology for any inconvenience that this  may cause you.  If you have any questions or concerns, please direct them to pace-support@oit.gatech.edu

Best,

The PACE Team

The Hive scheduler experienced an outage this afternoon, as the resource and workload managers were unable to communicate. Our team identified the issue as relating to a missing library file and corrected the issue, restoring functionality at approximately 5 PM today.
Jobs submitted this afternoon would not have been able to start until the repair was implemented. Already-running jobs should not have been affected.
Please contact us at pace-support@oit.gatech.edu with any questions.

[Update 6/12/21 6:30 PM]

Phoenix Lustre scratch has been restored. We paused the scheduler at 4:40 PM to prevent additional jobs from starting and resumed scheduling at 6:20 PM. As noted, please contact us with the job number for any job that began prior to 4:40 PM and was affected by the scratch outage, in order to receive a refund.

[Original post, 6/12/21 4:30 PM]

We are experiencing an outage on Phoenix’s Lustre scratch storage. Our team is currently investigating and has confirmed that this issue is related to the scratch mount and does not affect home or project storage. Users may be unable to list, read, or write files in their scratch directories.
If your running job has failed or runs without producing output as a result of this outage, please contact us at pace-support@oit.gatech.edu with the affected job number(s), and we will refund the value of the job(s) to your charge account. Please refrain from submitting additional jobs utilizing your networked Lustre scratch directory until the service is repaired, in order to avoid increasing the number of failed jobs.