RDD / Whatever it is saying now / Several drives failed at once

several at once · backplane · expander · PSU · controller · firmware clock · same batch

Several drives failed at once. Four drives do not die in one second. Something they share did.

Hard drives fail one at a time, and when four of them vanish in the same second, or eight of them in the same minute, the thing that failed is the thing they share: a backplane, an expander, a SAS cable, a power supply rail, a controller channel. The drives are usually fine, and the danger is what the controller does about it. A PERC or a MegaRAID that loses half its members marks the virtual disk failed and, when they come back, reports them as foreign; a hasty clear or a hasty import turns a five-minute cable fault into a reconstruction. The exception is solid state: SAS SSDs fitted in the same afternoon reach 32,768 or 40,000 power-on hours in the same afternoon, and those do die together, on schedule. One member imaged is £300 + VAT after the free look, fixed in writing; a set that has failed together is assessed as a set.

Free first lookOne fixed figure in writingNo data, no bill on most jobsReturn postage paid

Rather talk it through? An engineer answers the bench line
0800 6890668

Power down. Label every slot before a drive comes out. Do not rebuild while a second drive is flagged. Do not clear or import a foreign configuration. Do not initialise, reformat or PSID-revert anything. A rebuild reads every sector of every surviving member, and on a set whose drives were bought together it is where the second failure is found. Nothing on the drives gets worse while the server is off.

What fails in one second, and what fails on schedule.

A drive that fails takes minutes or months to do it: heads degrade, defect lists grow, firmware trips. Four drives that disappear in the same second did not fail; they lost something in common. In a server that is a backplane slot bank, an expander that fans one SAS port out to eight drives, the cable between the controller and the backplane, or a rail of the power supply that feeds one bank. In a shelf it is an expander module or the SAS cable to the head unit. In a controller it is one channel or one port. When the shared part is restored, the drives come back, and the question is what the controller has decided in the meantime.

The controller's decision is the risk. A PERC that lost four of six members has failed the virtual disk and, when they return, sees drives whose configuration it no longer trusts and reports them foreign. A MegaRAID marks them unconfigured bad. An mdadm array marks them non-fresh if writes continued on the survivors. In every case the right move is to stop, restore the shared part with the server off, and let the bench or a careful import bring the set back with every member present. Clearing the foreign configuration to tidy the screen is the mistake that costs the most.

Solid-state drives are the exception, and a documented one. HPE's SAS SSDs on firmware before HPD8 fail at 32,768 power-on hours and another line before HPD7 at 40,000; Dell's LT-series at 40,000 before D417; HPE's NVMe drives on one firmware line at 4,700. Drives fitted together reach the hour together, and a RAID 5 of six can lose four before lunch. Those drives did die, and the free look says honestly which of them still answer at controller level.

What it says, and what it means.

Describe yours to us →

What you see	The usual reason	Where that leaves you
Four drives vanished in one second	Backplane bank, expander, cable or PSU rail	Power down; restore the shared part; do not clear the config
Drives back, now foreign	The controller lost trust	Import only with every member present and current
Several SAS SSDs failed within minutes	The firmware clock	Stop; check the survivors' hours; assessed at controller level
Two drives a week apart, then a third	Same batch, same age	Image the weak ones; expect the rest
Whole shelf offline	Expander module or cable to the head	The drives are fine; the shelf is the fault
Drives vanish under load, return when idle	A PSU rail sagging	Replace the supply; image any drive that was dropped mid-write

From the parcel arriving to your files going back.

Work we have closed →

Logged the day it lands, and the first look costs nothing Free

A case number goes on the parcel and a number on every drive the day it is opened, matched to the slot you wrote on it. An engineer settles what has actually happened before anything spins: the interface, the sector format, the firmware, the security state, and what the controller was saying when it stopped. Back to you come two things together: a straight note of what is liftable and what is not, plus one figure, fixed and written down. Accept it, or decline and owe us nothing.

Nothing to pay for lookingA single figure, put in writingNo rebuilds, no imports, no resets

The drive on its own bench

A set that failed together arrives as its members, and each is read on its own: a set that lost a backplane is a set of healthy drives with a controller that no longer trusts them, and the bench reads the configuration from the drives and reassembles it in software. A set of SSDs that reached their hour is assessed drive by drive at controller level.

Read at its native interfaceFailing heads to the clean bench

Imaged once, at its native sector size

Every drive is imaged sector by sector, head by head where it needs it, with the bad areas last. Drives with 520- or 528-byte sectors are imaged as they are and the extra bytes stripped from the image, never the drive. Self-encrypting drives are unlocked on the imager with the key you supply. From then on the originals are not touched again.

Head by head, weak areas lastNative sector size preserved

The image, and the set

Where the set is healthy and one member was the job, the image goes back to you on a fresh drive, sector-identical, ready to rebuild from. Where the set is the job, every member is imaged and the array reassembled in software from the images: order, chunk size, parity rotation and the reshape point read from the drives' own metadata, the file system repaired on the virtual volume, never on the originals. The array work is covered in full on our RAID array site, and it happens on the same bench.

One member: a sector-identical image on fresh mediaA set: reassembled in software from the images

You see the file list before you pay

What was recovered is listed for you first, and only then does a bill exist. Approve the list and it is invoiced; turn it down and it is not — and where nothing has come back, most jobs carry no charge at all. Recovered data travels home on fresh media bought in for your job, with the postage at our end. Your case is not closed until you have opened the files on a machine of your own.

No charge until you accept the figureFresh media, supplied with the job3–4 days at the bench

From the bench

Check the shared parts first, with the server off: the cable, the expander, the supply. Four healthy drives and a cable is the commonest version of this page.
Do not clear the foreign configuration to make the warning go away. It deletes the set's description from drives that were fine.
Same batch means same age. Two failures a week apart is a set whose survivors should be imaged before the third.
Check the power-on hours on every SSD the moment one fails. The clocks are exact.

One job, followed all the way through.

UK · RDD-2026-0567JOB LOGGED ✓

Eight NL-SAS drives in an MD1200 that vanished together when an expander module failed, then came back foreign to a PERC H810 that an engineer offered to clear

The owner declined and sent the shelf's drives here. Every drive was healthy; the configuration on them was intact and consistent, and the RAID 6 was reassembled in software from the images and the volume copied out. The shelf went back into service with a new expander module and the same drives, and the copy on fresh media was kept.

100% of the volume recovered7 days here, and back by post

Illustrative example — replace with a genuine case

What helps, and what harms.

Do this much first

Power down and check the cable, the expander and the supply
Photograph the controller's screen before touching it
Label the slots and send every member if the set has failed
Check the hours on every surviving SSD

What sets us back

Clearing the foreign configuration
Importing it with a member missing
Rebuilding onto SSDs on the same clock
Assuming four dead drives

Questions answered before you commit.

Four drives failed at once. Are they all dead?

Almost certainly not. Something they share failed: a backplane, an expander, a cable, a supply rail. Restore it with the server off and do not clear the configuration.

They came back as foreign. Should I import?

Only if every member is present and the configuration is current on all of them. If in doubt, send the set; the bench reads the configuration from the drives.

Several SSDs failed within minutes. Is that the same thing?

No. That is the firmware clock, and those drives did fail. Check the survivors' hours now and send the failed ones for an honest assessment.

What does it cost?

£300 + VAT for one drive after the free look; a set of two to four from £500 + VAT; larger sets and shelves from £1,250 + VAT.

How long does it take?

5–10 days at the bench for a set.

Where this usually leads.

Foreign configuration found →SSDs failed at 32,768 or 40,000 hours →SAS drive not detected →Storage shelves →

Nothing gets worse while it is powered down.

Looking at it is free. Back comes a list of what opened and what did not, together with a single price to finish, set down in writing while you are still free to say no. Until that list reaches you, leave the server off and the drives in their slots.

0800 6890668

Price my job Packing and posting

Every kind of member drive

Manufacturers

Whatever it is saying now

What it costs, and what follows