[Info-vax] Nasty HP SSD bug.

[Simon Clubley]

On 2019-11-26, Jan-Erik Söderholm <jan-erik.soderholm at telia.com> wrote:
> Hi.
>
> Not an 100% OpenVMS issue, but could affect storage used
> from an OpenVMS system
>
> https://support.hpe.com/hpsc/doc/public/display?docId=emr_na-a00092491en_us
>
>  From that page:
>
> "Issue Fixed:
>
> The issue affects SSDs with an HPE firmware version prior to HPD8 that
> results in SSD failure at 32,768 hours of operation (i.e., 3 years, 270
> days 8 hours), neither the SSD nor the data can be recovered, after the
> SSD failure occurs.
> In addition, SSDs which were put into service at the same time will likely
> fail nearly simultaneously."
>

It's a pity they didn't use unsigned variables instead of signed variables
for counting time - you would have got an extra 3+ years out of your drives
before they all failed...

Seriously however, this is a _really_ _really_ bad bug. :-( :-(

Makes you wonder why this wasn't caught when the appropriate data structures
were been designed and why someone didn't realise that (apparently) 16 bits
would not be enough.

I actually feel sorry for the people who are going to get caught by this.
It certainly reinforces the mindset that you should mix makes and ages
of disks in your data centre if you can.

Simon.

-- 
Simon Clubley, clubley at remove_me.eisner.decus.org-Earth.UFP
Walking destinations on a map are further away than they appear.