nfs: server not responding still trying task blocked for more than 120 seconds

D-State Task Hang - A process is stuck in uninterruptible sleep (D-state), waiting on hardware or network I/O. This entry explains how to confirm the cause, apply the fix, and separate it from adjacent storage failures.

The literal signature is "nfs: server not responding still trying task blocked for more than 120 seconds". It is a data pipeline failure associated with data loaders, GPU Direct Storage, and network filesystems. The line identifies the failing operation or subsystem, while the surrounding evidence decides whether it is the initiating fault or a downstream symptom.

D-State Task Hang - A process is stuck in uninterruptible sleep (D-state), waiting on hardware or network I/O. The failure becomes visible at this call site because the operation first requires the missing resource, valid state, healthy peer, or correct result. Earlier log lines and a known-good control carry more causal value than the final wrapper exception.

• The workload stops or loses forward progress after emitting "nfs: server not responding still trying task blocked for more than 120 seconds".
• A retry on the same configuration reproduces the failure because the causal state has not changed.
• The outer framework exception can hide the rank, node, allocation, or dependency that failed first.
• Increasing timeouts or reducing workload size can suppress the symptom without correcting the cause.

• data loaders, GPU Direct Storage, and network filesystems
• production-shaped multi-accelerator workloads
• containerized and bare-metal deployments of the same stack

Apply the following checklist to a small reproduction: each box below is a positive signal that you are looking at this exact failure rather than a sibling in the same taxonomy.

• ✓Find the first occurrence of "nfs: server not responding still trying task blocked for more than 120 seconds" and preserve at least 100 lines before it.
• ✓Identify which rank, node, device, or process emitted the first related warning.
• ✓Compare the failing rank, node, input, or configuration with one known-good control.
• ✓Repeat the same input after the targeted change and require the signature to disappear.
• ✓Resume from node-reboot only after the control passes.

nfs: server not responding still trying task blocked for more than 120 seconds

Timestamps and exact values vary across runs, but the pattern. An info-level start, an early WARN, an ERROR carrying the symptom. Is the actual fingerprint you should alert on. The Denpex platform flags this combination automatically.

Usually caused by a dead storage mount (NFS/GPFS) or a failing PCIe bus. The node must be rebooted, as D-state tasks cannot be killed (`kill -9` will fail). This changes the condition in the causal diagnosis instead of hiding the outer exception. The repeated control proves ownership before recovery from node-reboot.

# Preserve evidence before restarting
rg -n -i 'error|exception|timeout|failed' <log-file>
nvidia-smi
python -m torch.utils.collect_env

# Find the exact signature in the complete log
rg -n -F -- "nfs: server not responding still trying task blocked for more than 120 seconds" <log-file>

Adapt the snippet to your framework. The same pattern holds for PyTorch Lightning, Hugging Face Trainer, DeepSpeed, Megatron-LM, and vLLM training wrappers. Where the wrapper exposes a config flag (for examplelr_scheduler_type in Trainer), prefer the flag over the imperative API to keep the schedule declarative and reproducible.

Select the traceback or open the failed terminal, then run Denpex locally to see the initiating rank, collateral failures, exact fix, and verification command without uploading the log.

• D-State Task Hang - A process is stuck in uninterruptible sleep (D-state), waiting on hardware or network I/O.
• The decisive evidence is the first log line that precedes "nfs: server not responding still trying task blocked for more than 120 seconds" and differs from a healthy run.
• A nearby failure remains a competing hypothesis until a control separates configuration, capacity, transport, and hardware causes.