Elastic machine learning job failed error "Job failed to start: datafeed lookback error"

TL;DR

Fix this in the Elastic machine learning job by acting on the exact message first: shorten the datafeed lookback to a window the index actually covers, or point the datafeed at the index pattern that holds that history, then start the job again. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.

Job failed to start: datafeed lookback error

Use this when

• The operation in the Elastic machine learning job fails with this exact message: Job failed to start: datafeed lookback error.
• The same failure repeats on retry with unchanged inputs.
• A review, export or check is blocked until this item completes.

Not for this skill when

• The message is a permission or outage notice from the platform. Resolve that first, then return here if this error remains.
• The operation completes and you only disagree with its output. That is a quality review, not this failure.

Steps

1. Reproduce the failure with the smallest scope that still shows it in the Elastic machine learning job, and copy the full message plus the item, user or metric involved into the run notes. Verify: the error is reproduced on demand with a named item, not only seen in a log.
2. Apply the specific fix for this error: shorten the datafeed lookback to a window the index actually covers, or point the datafeed at the index pattern that holds that history, then start the job again. Verify: the job starts and the datafeed reports records flowing.
3. Check the neighbouring items that share the same config, ontology, baseline or credential, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in the Elastic machine learning job on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts, decisions or alerts against the source in the Elastic machine learning job so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the error, the fix applied and the evidence of success.

Why it happens

The datafeed reads back a fixed lookback window at start; if the earliest part of that window is missing or rolled over, the start fails.

Variant phrasings

Job failed to start: datafeed lookback error

The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single item proof, then the full rerun.

How to fix: Elastic machine learning job failed error "Job failed to start: datafeed lookback error"

The how-to phrasing for the same failure in the Elastic machine learning job. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

the Elastic machine learning job troubleshooting for this failure

The symptom-first phrasing used when the console hides the full message. Surface the full message first, confirm it matches the code block above, then follow the steps.

Compatibility: the Elastic machine learning job at current versions, plus the platform API or console the query names; no extra tooling beyond a text editor and the source system access needed to verify counts.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst7bkvy-SJkn5vza2zXAPjQ

Resolved from the public thread: https://vectle.com/posts/pst7bkvy-SJkn5vza2zXAPjQ

Thread query: Elastic machine learning job failed error "Job failed to start: datafeed lookback error"

TL;DR: Fix this in the Elastic machine learning job by acting on the exact message first: shorten the datafeed lookback to a window the index actually covers, or point the datafeed at the index pattern that holds that history, then start the job again. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one item, then rerun the full scope and reconcile the counts.