On November 12, 2026, AWS started letting EBS backups held in a logically air-gapped vault move down to Amazon EBS Snapshots Archive. The cost argument sells itself: archive costs US$ 0.0125 per GB-month against US$ 0.05 for the standard EBS snapshot tier. The question I care about isn't how much this saves, it's what happens to your RTO on the day the only clean recovery point sits in archive. To answer it, I wrote the postmortem before the incident.
How to read this: This is a pre-mortem: a game day scenario built from limits AWS documents, not a customer or employer incident. The timeline timestamps are exercise assumptions. The limits (72-hour restore, 5 concurrent restores per account, 90-day archive minimum, no copy after the transition) come from the documentation cited at the end.
What happened in the scenario
The system is a settlement core in us-east-1: 12 EBS volumes, 18 TB combined, encrypted with a customer managed key. Protection had two layers. Daily layer: an AWS Backup rule to a standard vault, 35-day retention, no Vault Lock. Monthly layer: a rule copying into a logically air-gapped vault, archive enabled after 30 days in warm storage, and 7-year total retention because the regulator asks for long history.
The platform team did what the announcement suggests and turned on archive to cut cost. The copy to us-west-2, where the isolated recovery environment (the clean room) lived, wasn't in the rule: it was a quarterly job copying points from the LAG vault into a second LAG vault in the other Region. On the retention spreadsheet it looked equivalent.
The attacker got in with administrative credentials for the primary organization and stayed quiet for about four months before encrypting. When encryption started, all 35 days of daily points were already tainted, and the standard vault, with no lock, had its points deleted. The LAG vault did what it promises: compliance mode, nobody deletes, not even root. The most recent clean point was the monthly one from four months earlier. And it had been in archive since day 31.
Protection worked: the data survived. Recovery failed, because the design never asked how long it takes to bring back a point older than 30 days.
Exercise timeline
T+0h: detection: Settlement core volumes encrypted. CloudTrail shows
DeleteRecoveryPointsucceeding on the standard vault and denied on the LAG vault.T+0h45: primary organization declared compromised: The team stops trusting any identity in the primary organization and moves to the recovery account in a second organization.
T+2h: restore access vault approved: The Multi-party approval team reaches its threshold and grants the restore access backup vault in the recovery account. It worked as designed.
T+3h: clean point identified: Forensics points to the monthly backup from four months ago as the last clean point. Status: archived.
T+3h10: the copy to the clean room fails: An EBS backup that has moved to archive can't be copied to another vault or Region, including from the restore access vault. The clean room in
us-west-2is useless for that point.T+4h: archive restore started in us-east-1: Only 5 concurrent restores per account. The 12 volumes become 3 waves, and none can be cancelled once started.
T+24h: RTO breached: The agreed RTO was 24 hours. At the documented worst case, up to 72 hours per wave, the last volume comes back near T+220h, almost nine days later.
Root cause: The root cause wasn't the attack, it was a retention design that treated archive as a cost tier when it's also an RTO tier. Three decisions compounded: the cross-Region copy was planned from the LAG vault after the transition, when it's no longer possible; nobody mapped RTO to the age of the point; and the 5-concurrent-restores-per-account quota never made it into the runbook.
Why archive is an RTO decision
An archived point doesn't behave like a snapshot. The EBS documentation lists the failure modes, and each one moves recovery time.
Slow, one-way restore: bringing a snapshot from archive back to the standard tier takes up to 72 hours depending on size, and the process can't be cancelled once started. Picked the wrong point? You pay for the full restore and wait again.
No direct use: an archived snapshot can't create a volume, can't go into a block device mapping, can't be shared or copied. Fast snapshot restore is disabled on transition and has to be re-enabled by hand afterwards.
Per-account quotas: the default is 5 concurrent archive restores and 25 archived snapshots per volume. With 12 volumes, the first number turns 72 hours into up to 216. The second deserves attention in a 7-year monthly plan, which produces 84 points per volume. I couldn't find in the LAG vault documentation whether that quota applies to points held in the AWS Backup service account. Confirm with Support before assuming.
Full snapshot: the archived point is always full, not incremental. 18 TB archived means 18 TB restored, billed at US$ 0.03 per GB.
The lesson is about engineering, not price: every storage tier needs a written RTO next to it. A warm point comes back in hours. An archived point comes back in days, and only in the Region and account where it already lives.
The three numbers that change the runbook
- US$ 0,0125: per GB-month in archive. Against US$ 0.05 on the standard EBS tier: up to 75% less, for points kept 90 days or longer.
- 72 h: archive restore. Documented ceiling to return to the standard tier. Can't be cancelled.
- 5: concurrent restores per account. Default quota. 12 volumes become 3 sequential waves.
Where the copy must happen: before the transition
The diagram answers one question: at which point of the lifecycle the backup can still leave the Region. The cross-Region copy starts from the warm tier; after archive, the point is only restored where it is. Dashed arrows are asynchronous: the lifecycle transition and the slow archive restore. Simplified: it omits the daily standard vault and the KMS key.
Workload account
- Amazon EBS 12 volumes, 18 TB (storage)
- AWS Backup plan monthly rule (compute)
Logically air-gapped vaults
- LAG vault us-east-1 warm storage (security)
- EBS Snapshots Archive up to 72h restore (storage)
- LAG vault us-west-2 warm copy (security)
Recovery organization
- Multi-party approval approval team (user)
- Restore access vault recovery account (security)
Flows
- plan -> ebs: snapshots
- plan -> warm: copy action
- warm -> dr: cross-Region copy, warm only
- warm -> archive: lifecycle after 30 days
- mpa -> rav: approves access
- rav -> warm: restore in hours
- rav -> archive: restore in up to 72h
Remediation: retention in RTO bands
The fix isn't turning archive off, it's to stop treating retention as a single line.
Copy before the transition: the copy to the us-west-2 LAG vault becomes a copy action in the monthly rule itself, with the copy lifecycle keeping the point warm. The documentation is explicit: to keep a copy in another account or Region, copy while the backup is still in warm storage. A quarterly job from the LAG vault is exactly what doesn't work.
Bands with a written RTO: the last 3 monthly points stay warm in both Regions (RTO in hours). From month 4 on they go to archive (RTO in days, only in us-east-1). That table goes into the continuity document the business signs, not into the platform team's heads.
Lifecycle constraints: the rule must run monthly or less often. Total retention must be at least 90 days longer than time in warm and fall within the vault's minimum and maximum retention. A vault created with a 35-day maximum rejects a 7-year copy and nothing on the spreadsheet warns you; check MaxRetentionDays first.
Key: a volume encrypted with the AWS managed key (aws/ebs) can't be shared across accounts, so it can't go into the LAG vault. Use a customer managed key with a key policy that allows AWS Backup.
Quota and invitation: request the concurrent restore quota increase before the incident. RAM sharing accepts individual account IDs only, and the invitation expires in 12 hours: accept it during the game day, not on attack day.
Cost: run the whole math, not just storage
Archive saves real money, but the math has four lines, not one.
Full versus incremental: on the standard tier you pay only for changed blocks; in archive you pay for the whole volume. From the price ratio (0.0125 / 0.05), an archived full breaks even with a standard incremental that's 25% of the volume size. A volume with little monthly change can cost more archived. That's why the documentation advises against archiving daily incrementals.
Referenced blocks stay: data that other snapshots in the lineage still use remains on the standard tier and is billed to the next snapshot. Archiving doesn't zero the standard tier bill.
Restore and early exit: restoring the scenario's 18 TB (18,432 GB) costs about US$ 553 each time. Deleting or permanently restoring before 90 days triggers a pro-rated charge for the remaining days. A temporary restore doesn't, but you pay for both tiers during the restore period.
LAG vault pricing: LAG vault storage is billed as AWS Backup, not EBS, and has its own rate table. The pricing page example uses US$ 0.0575 per GB-month warm in Ireland. Check your Region in the calculator before reusing EBS numbers.
To observe it, filter CUR by the usage types SnapshotArchiveStorage, SnapshotArchiveRetrieval and SnapshotArchiveEarlyDelete. The third one above zero almost always points to a misconfigured lifecycle.
Anti-patterns the scenario exposed
- Cross-Region copy after archive: planning the second Region as a later job from the LAG vault. After the transition the point can't leave the Region, not even through the restore access vault.
- One RTO for the whole retention: promising 24 hours for any point across 7 years of history. An archived point has a different RTO, and the business has to sign off on both.
- Standard vault without Vault Lock as first line: the daily layer was deleted by whoever held admin credentials. Only the compliance-mode vault survived.
- Archiving daily incrementals: every point becomes full in archive. With a low change rate, the bill goes up instead of down.
- Quota discovered during the incident: 5 concurrent restores is the default. Requesting an increase with the system down adds days to the RTO.
Pillar reading
-
security: LAG vault in compliance mode, customer managed key and Multi-party approval in a second organization. Approval teams only exist in
us-east-1: that's a Region dependency of your recovery plan and has to be written down. - reliability: Write RTO per point-age band (warm in hours, archive in days) and test both with restore testing from the restore access vault. Cross-Region copy always as a copy action in the rule, while the point is warm.
Curator's note: I'd turn on archive in the LAG vault, but only after two things: the cross-Region copy inside the monthly rule and an RTO-per-band table signed by the business owner. I've seen DR plans approved because the retention was right while nobody had measured the time to come back. That isn't a tool failure, it's a question failure. The first test I'd run is a real, timed restore of an archived point, with all 5 concurrent restores busy.
Lessons
Use archive in the logically air-gapped vault when: the point is monthly or sparser, kept well beyond 90 days, exists for retention requirements rather than as an operational recovery line, and the business has accepted in writing a days-long RTO for it. Keep warm, and copied to the second Region before the transition, every point that could be the last clean one after an attack with months of dwell time. The feature is good for long regulatory retention; as the only line of defense against ransomware, it trades cost for an RTO nobody probably approved.
Rating: Adopt with RTO bands
References
- AWS What's New: AWS Backup adds logically air-gapped vault support for Amazon EBS Snapshots Archive (12/11/2026)
- AWS Backup Developer Guide: Logically air-gapped vault
- AWS Backup Developer Guide: Multi-party approval for logically air-gapped vaults
- Amazon EBS User Guide: Archive Amazon EBS snapshots (quotas)
- Amazon EBS User Guide: Considerations and limitations for archiving snapshots
- Amazon EBS User Guide: Pricing and billing for archiving snapshots
- AWS Storage Blog: Streamline ransomware protection while reducing cost with logically air-gapped vault primary backup
- AWS Architecture Blog: Cyber resilience on AWS, a reference approach for recovery from ransomware and destructive events
Originally published at fernando.moretes.com. By Fernando F. Azevedo: Senior Solutions Architect.
Top comments (1)
The 5-concurrent-restores limit is the detail that would have caught me too — I always did the math on storage cost and never on how many restores can run at once. I run a small setup where the whole point is the backup disconnecting itself after the job, and your "last 3 monthly points stay warm in both Regions" is the same lesson in a different shape: the copy that saves you is the one that is still reachable in hours, not the one that is cheapest to keep. The pre-mortem format works — I wish more teams wrote the failure down before the incident instead of after.