MultiDrive – free backup, clone & wipe disk utility from Atola Technology

All times are UTC - 5 hours [ DST ]




Post new topic Reply to topic  [ 3 posts ] 
Author Message
 Post subject: Acceptable Response Time Spikes for New HDD?
PostPosted: September 7th, 2025, 23:03 
Offline

Joined: September 7th, 2025, 22:36
Posts: 1
Location: Germany
Hiya :)
I'm testing a new unused WD Red Pus NAS HDD drive (4Tb) and most sectors are quick but am getting a few hundred sectors ~150ms and about 20 of them at 210ms. I don't know how to interpret this and gemini (AI chat) is telling me this is a sign of physical damage (as the slow sectors are near each other) and totally unaccetable for a new drive and there should be 0 slow sectors.
The drive was not partitioned and unused while testing.

I can't find info on whats considered acceptable for number of sectors with latency spikes on new drives, if any. Would appreciate any input.

I'm doing a write/read test with HD sentinel next and will check the SMART details after. Gemini is telling me no matter what the results are, I should return the drive. Kicker - this is the second one.. I just had the exact same results and replaced the drive for another from the shop a few days later (the one I'm asking about now).


Top
 Profile  
 
 Post subject: Re: Acceptable Response Time Spikes for New HDD?
PostPosted: September 11th, 2025, 9:15 
Offline
User avatar

Joined: May 13th, 2019, 7:50
Posts: 1150
Location: Nederland
I fed Gemini your post and get this:

Quote:
Based on the user's post, the advice they received from a chatbot is not entirely accurate. While a few slow sectors on a brand new drive can be a concern, it's not always a definitive sign of physical damage or that the drive is completely unusable.

Understanding Slow Sectors
Slow sectors are areas on a hard disk drive (HDD) that take longer than usual to read or write data. When a drive encounters a slow sector, the read/write head has to retry the operation, which causes a delay. Here's a breakdown of what the user is experiencing:

Quick sectors: These are the normal, healthy sectors that respond very quickly (typically under 10 ms).

Slow sectors (~150 ms and ~210 ms): These are sectors that are taking significantly longer to access. This can be caused by a few different issues:

Physical degradation: Microscopic imperfections on the platter surface can make the head struggle to read or write data.

Magnetic instability: The magnetic charge on the platter might be weak in some spots, requiring multiple attempts to read the data correctly.

Firmware issues: The drive's internal software might be mismanaging the read/write process in specific areas.

Imperfect manufacturing: It's not uncommon for hard drives to have a small number of these sectors right out of the factory. The drive's internal firmware is designed to handle this by mapping them out as "bad" and reallocating data to spare sectors. This is a normal part of the drive's self-management process.

The fact that the slow sectors are "near each other" suggests a localized issue on the platter's surface, which is consistent with the reasons listed above.

Interpretation and What to Do
The user is getting mixed messages. Here's a clearer perspective:

Is it "unacceptable"? A few slow sectors on a new drive, while not ideal, aren't necessarily "unacceptable." A brand-new drive should indeed have very few, if any, slow sectors. However, all HDDs are built with a certain number of spare sectors to handle such imperfections. The drive's internal controller will automatically reallocate data from a slow or failing sector to one of these spares. As long as the number of reallocated sectors remains low, the drive is considered healthy and reliable.

Is it "physical damage"? It could be a minor physical imperfection, but it's not necessarily a sign of a catastrophic failure. A large cluster of unreadable sectors or a high and rapidly increasing number of slow sectors would be more indicative of a serious problem. The small number the user described (a few hundred slow, 20 very slow) is a reason for caution, not immediate alarm.

My recommendation for the user would be:

Run a full diagnostic scan: They should use the drive manufacturer's own diagnostic tool (like Western Digital's Data Lifeguard Diagnostic). This tool will perform a more thorough test and provide a definitive pass or fail status. It will also show if the number of reallocated sectors is increasing.

Monitor the S.M.A.R.T. data: The Self-Monitoring, Analysis, and Reporting Technology (S.M.A.R.T.) data is the drive's internal health report. The user should look specifically at the following attributes:

Reallocated Sector Count: This tells you how many sectors the drive has remapped from bad to good. A new drive should have a count of zero. If it's increasing, that's a bad sign.

Current Pending Sector Count: This shows how many sectors the drive has marked as potentially bad but hasn't yet reallocated. This is a common precursor to reallocated sectors.

Seek Error Rate: This can indicate issues with the read/write head.

Consider an exchange: If the manufacturer's diagnostic tool fails the drive or the S.M.A.R.T. data shows a high or increasing number of reallocated sectors, they should immediately return the drive for a replacement under warranty. It's not worth the risk of a potential failure down the line, especially for a new drive. If the tests pass and the S.M.A.R.T. data looks good, the drive is likely fine. However, since it is a brand-new drive, the user might simply opt for a replacement to be safe.

_________________
Joep - http://www.disktuna.com - video & photo repair & recovery service


Top
 Profile  
 
 Post subject: Re: Acceptable Response Time Spikes for New HDD?
PostPosted: September 12th, 2025, 7:35 
Offline
User avatar

Joined: January 28th, 2009, 10:54
Posts: 3547
Location: Greece
and I fed ChatGPT your post and got this: :)

Quote:
Hi

What you’re seeing is not necessarily “physical damage.” A few points to clarify:

Sector access times:

Normal sectors on a modern 4 TB HDD usually respond in <10–20 ms.

Occasional spikes of 100–200 ms on a handful of sectors can happen due to internal error correction (ECC retries). This does not automatically mean the drive is defective.

Clustering of slow sectors:

If they’re all bunched in the same area, it might be an early weak spot on the platter, but it could also be normal variation in manufacturing. Drives use adaptive formatting and sparing — the firmware can handle small irregularities.

SMART monitoring:

Before deciding anything, check SMART values, especially Reallocated Sector Count, Pending Sectors, and Uncorrectable Errors.

If those are all zero after a full write/read test, the drive is functioning within spec.

Testing methodology:

HD Sentinel (or any surface test) often shows latency spikes that don’t translate to real-world problems.

A proper test is a full write + full read verification cycle. If it completes without reallocated or pending sectors, the drive passed.

What’s acceptable:

Manufacturers don’t guarantee “0 slow sectors” — they only guarantee that the drive passes its own self-tests and has no uncorrectable errors.

A few hundred 150 ms hits in billions of sectors is usually not a return-worthy fault.

However, if slow sectors increase over time or pending/reallocated counts rise, that is a reason to RMA.

Why both drives look the same:

Likely not bad luck. Some WD Red Plus drives show small groups of slower sectors even when new — it’s within normal tolerance.

Gemini telling you “totally unacceptable” is an overstatement. Real drive health is judged by SMART stability and error counts, not isolated latency spikes.

Bottom line:

Run the write/read test.

Check SMART (before and after).

If SMART is clean, keep the drive — it’s normal.

If you see any pending or reallocated sectors, then return it.

_________________
http://www.northwind.gr
SandForce SSD Recovery
Ransomware Reverse Engineering - NoMoreRansom! partners


Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 3 posts ] 

All times are UTC - 5 hours [ DST ]


Who is online

Users browsing this forum: Google [Bot] and 30 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group