Question re ZFS with mixed drive speeds & types

Greg Marsh greg.marsh at gmail.com
Thu Aug 6 20:33:01 UTC 2020


Thank you all for your input and memories. I’m glad to hear I’m not hallucinating having recalled said storage sales pitches. =)

I suspect what I’ll end up doing is migrating my current array to the new system, then experiment with adding mixed drives to a second, testing array. 

When I started in IT, it was in a big VAX/Alpha OpenVMS using company. The programmers couldn’t stop talking about how lighting fast the RMS file/record storage system was. I was just an operator at the time. 
But, when I saw the circulation system (I worked at a newspaper) move from a single Alpha 233 to a dual 2 GHz Xeon running Linux and ProgressDB move waaaay slower, was I convinced there had to be better ways. 
To be fair, I generally blame the crappy off the shelf program that replaced a decades old, in house developed one.


Cheers,
Greg

Sent from my iPhone

> On Aug 6, 2020, at 15:21, Paul Pathiakis via freebsd-questions <freebsd-questions at freebsd.org> wrote:
> 
> Wow.... someone as old as me... :)
> I had no idea.  I remember a lot of those applications in an OS that were based on this theory.  I believe there were even a few that indexed tape drives with UNIX i-nodes.  Good times..... :)
> P.
> 
>    On Wednesday, August 5, 2020, 2:46:06 PM EDT, Polytropon <freebsd at edvax.de> wrote:  
> 
> On Wed, 5 Aug 2020 20:26:36 +0200, Jacques Foucry wrote:
>> Le mercredi 05 août 2020 à 01:32:02 (-0700), David Christensen à écrit:
>>> On 2020-08-04 23:55, Greg Marsh wrote:
>>>> [...]
>>>> I ask because about 10 years ago, I was involved in a project that had a HUGE storage component. Many of the vendors we brought in to pitch, including Sun, were promoting tiered storage. Sun in particular were quite proud of this tech. Their system ran ZFS and had a hybrid of ssd, sas & SATA, with the system dynamically moving data around the different speed/capacity drives, based on their activity, all transparent to the application or user. Most often used data coming from the ssd & sas drives, with less active files kept on the SATA drives.
>> 
>> 
>> I remember the same thing when Sun demostrate us ZFS (I was a Sunkskill at
>> this time). But I never tried.
> 
> Sounds a bit like HSM - hierarchical storage management,
> implemented on IBM mainframe systems (DFHSM) and on
> DEC VMS for VAX and Alpha, also has been implemented
> on AIX and other UNIX operating systems.
> 
> So decades old stuff is "new" again... ;-)
> 
> 
> 
> 
> -- 
> Polytropon
> Magdeburg, Germany
> Happy FreeBSD user since 4.0
> Andra moi ennepe, Mousa, ...
> _______________________________________________
> freebsd-questions at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-questions
> To unsubscribe, send any mail to "freebsd-questions-unsubscribe at freebsd.org"  
> _______________________________________________
> freebsd-questions at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-questions
> To unsubscribe, send any mail to "freebsd-questions-unsubscribe at freebsd.org"


More information about the freebsd-questions mailing list