[FoRK] Multicore, async segmented sequential models

Aaron Burt aaron at bavariati.org
Thu May 9 07:42:46 PDT 2013


On Thu, May 09, 2013 at 12:11:35PM +0200, Dave Long wrote:
> Our agricultural ancestors also had these kinds of problems, and
> arrived at similar solutions.  The haystack might have been[0]
> invented by someone who had the brilliant idea of interposing a
> buffer[1] between the "gather hay" process (extensive, most easily
> done by animals with thumbs) and the "transport hay to the barn"
> process (intensive, most easily done by animals which can live on
> said hay) .

At least in turn-of-the-last-century practice, it was a way to get your hay
stabilized and safe from rain and dew, once it had been cut and dried.
So while it did function as a strategy for marshalling your hay within a
single low-latency domain before the high-latency storage operation, it was
more of a strategy for protecting hay at rest in local temp storage.

(Why yes, I did recently attend a seminar on horse-powered haying.  It was
a nice break from diagnosing our MongoDB-problem-of-the-week over an EVDO
link.  That one had to do with utterly crap locking and concurrency
behaviour and still isn't fixed yet.)

Argh rargh puns,
  Aaron


More information about the FoRK mailing list