Strongly agree with Patrick. SSD is still slow storage compared to RAM.
gerry
On Thu, Mar 30, 2017 at 3:11 PM, Patrick L. Francis <wxprofessor@xxxxxxxxx>
wrote:
> Has anybody tried to put a queue exceeding physical memory size on a solid
> state drive? With the 3km NAM nested our product lifespan went down to
> about 4 min. ldmadmin vetqueuesize states 40 GB is needed, I am not even
> sure that the current server supports that amount of memory.
>
>
>
> I've found that the best performance is achieved by creating a ramdisk to
> both hold the queue in physical memory, and performing calculations (gddiag
> and such). Memory is cheap enough now that a box can easily be maxed out
> with memory to provide more than enough room for supporting the queue.
> However, I can say that using a mounted SSD would improve performance
> somewhat from older drives, simply from an IO perspective. [image:
> *ALIEN*]
>
>
> best of luck [image: :-)]
>
>
> cheers,
>
>
> --patrick
>
>
> …………………………………………………………...........
>
> Patrick L. Francis
>
> Director of Research & Development
>
> Aeris Weather
>
>
>
> http://aerisweather.com/
>
> http://modelweather.com/
>
>
>
> wxprofessor@xxxxxxxxx
>
> http://facebook.com/wxprofessor/
>
>
>
> …………………………………………………………
>
>
> ..
>
>
>
>
>
>
>
> _______________________________________________
> NOTE: All exchanges posted to Unidata maintained email lists are
> recorded in the Unidata inquiry tracking system and made publicly
> available through the web. Users who post to any of the lists we
> maintain are reminded to remove any personal information that they
> do not want to be made public.
>
>
> ldm-users mailing list
> ldm-users@xxxxxxxxxxxxxxxx
> For list information or to unsubscribe, visit:
> http://www.unidata.ucar.edu/mailing_lists/
>
--
Gerry Creager
NSSL/CIMMS
405.325.6371
++++++++++++++++++++++
“Big whorls have little whorls,
That feed on their velocity;
And little whorls have lesser whorls,
And so on to viscosity.”
Lewis Fry Richardson (1881-1953)
