WD officially spun all NAND flash operations into Sandisk.

The shakeout in HDD sales had a direct impact on us here regionally. The company that originally developed the "head" suspension mechanism was based about 50 miles from my house.


They've been hit pretty hard...

www.wqow.com

HTI announces nearly 75% of Eau Claire staff being laid off

Hutchinson Technology (HTI) in Eau Claire is laying off about 75% of their workers.
www.wqow.com www.wqow.com

I wonder if these huge capacity data center drives might inject some new life into HDD sales?
 
Metanis said:
I wonder if these huge capacity data center drives might inject some new life into HDD sales?
Click to expand...
Seems likely according to the article "Meanwhile, Western Digital is focusing on the evolving opportunities in the HDD market. "As AI accelerates and impacts industries around the world, and as companies generate and store more data, HDD exabyte shipments are expected to increase," CEO Irving Tan said. He also points out that much of the data stored by cloud service providers, such as native cloud application data, AI data lakes, media, and machine learning data, runs on HDDs."

Guess it makes sense that data centers may use a lot of hard drives vs SSDs. Read speeds probably aren't that critical in cloud services, while capacity is more important. I'd suppose data center guys want to be able to manage failures of drives, something that's more predictable with spinning drives.
 
timeshifter said:
I'd suppose data center guys want to be able to manage failures of drives, something that's more predictable with spinning drives.
Click to expand...

And where "warning signs" are almost always given well ahead of actual failure. Every SSD failure I've dealt with so far has been instantaneous and sans any warning of any kind. Like a light switch. I never had an HDD die in such a manner. There was always something that proceeded from "wee, small voice" up through "bellowing" leading up to the actual final failure.
 
@timeshifter, The read delays on platters relative to SSDs vanish entirely when you've got hundreds of disks in a huge array. The scale at which Microsoft operates with Azure is mind blowing. Amazon's AWS is no different.

We usually think of redundancy at the point of the disk, when we're smarter... we think of redundancy at the point of the server.

Amazon, Google, Microsoft? They think of redundancy at the point of the data center! Let that sink in... they swap in and out entire data centers, like we do hard drives! It's utterly boggling...
 
britechguy said:
And where "warning signs" are almost always given well ahead of actual failure. Every SSD failure I've dealt with so far has been instantaneous and sans any warning of any kind. Like a light switch. I never had an HDD die in such a manner. There was always something that proceeded from "wee, small voice" up through "bellowing" leading up to the actual final failure.
Click to expand...

Yep especially the nvme drives. They just seem like they'll quit when they want to. I set up an optiplex 3070 last week. It had an nvme from 2021 in it. Everything perfectly fine during setup. Worked fine for about 4 days and then poof dead. I'm just thankful we had an image to restore after all the setup work lol. I ended up putting in a samsung sata pro series in instead of an nvme just because I trust it way more. For what they use it for probably never will notice a difference and I told them that. Reliability much more important than speed for them.
 
You must log in or register to reply here.
Back
Top