Servers, Storage and Hardware Troubleshooting
Identifying, replacing and diagnosing server and storage hardware as a data center technician, followed through a remote hands term at Stonebridge Data's campus in Ashburn, Virginia: server parts, memory and PCIe, GPU trays for AI, power supplies and fans, drives and drive health, RAID and shared storage, BMCs with IPMI and Redfish, firmware and its security, replacement procedures and ESD, diagnosis from LEDs, logs and error codes, RMAs and spares, and a GPU node failure from alert to RMA.
DCT-310 12 lessons · 4 h 2 min ▶ Video lessons coming soon
Offered by HSM University · Data Center Operations
This is the American version of this course. See the Canadian version.
What you'll learn
- Describe the kinds of servers in a data center and work only on authorized remote hands tickets matched to the right device
- Identify the parts of a server and apply memory population rules and PCIe link checks
- Explain how GPU servers and rack-scale AI systems are built and handle GPU trays safely
- Maintain power supply redundancy and replace power supplies and fans, and relate fan speed and throttling to inlet temperature
- Distinguish HDD, SSD and NVMe drives, read drive health data and handle failed drives under chain of custody
- Explain RAID levels, degraded arrays and rebuilds, and the differences between DAS, SAN, NAS and object storage
- Use the BMC through IPMI and Redfish for status and logs, and apply defensive BMC security practices
- Explain firmware layers and baselines, support safe update waves and recognize firmware security protections
- Replace hot-, warm- and cold-swap parts under a method of procedure with correct ESD protection, seating and records
- Diagnose hardware faults from LEDs, POST codes, event logs and error codes, and rule out environment, power and cabling causes
- Manage RMAs, spare parts and data-bearing parts with complete records
- Work a GPU node failure from alert through diagnosis, replacement, RMA and incident record
Course content
12 lessons · 4 h 2 min total · final exam
- 1 Servers in the data center 21 min · quiz
- 2 Server architecture: CPUs, memory and buses 20 min · quiz
- 3 GPUs and accelerators for AI 20 min · quiz
- 4 Power supplies, fans and server cooling 20 min · quiz
- 5 Storage devices: HDD, SSD and NVMe 20 min · quiz
- 6 Storage systems: RAID, SAN, NAS and object storage 20 min · quiz
- 7 Remote management: BMC, IPMI and Redfish 21 min · quiz
- 8 Firmware, BIOS/UEFI and lifecycle updates 20 min · quiz
- 9 Hardware replacement procedures and ESD 20 min · quiz
- 10 Diagnosing hardware failures: logs, LEDs and error codes 19 min · quiz
- 11 Returns, RMA and spares management 20 min · quiz
- 12 Capstone: a GPU node failure from alert to RMA 21 min · quiz
- E Final exam 20 questions
Requirements
Recommended background. You can start any course at any time.
Description
Identifying, replacing and diagnosing server and storage hardware as a data center technician, followed through a remote hands term at Stonebridge Data's campus in Ashburn, Virginia: server parts, memory and PCIe, GPU trays for AI, power supplies and fans, drives and drive health, RAID and shared storage, BMCs with IPMI and Redfish, firmware and its security, replacement procedures and ESD, diagnosis from LEDs, logs and error codes, RMAs and spares, and a GPU node failure from alert to RMA.