Plateforme Level Extreme
Abonnement
Profil corporatif
Produits & Services
Support
Légal
English
Eye-Opener
Message
De
27/03/2015 14:22:53
 
 
À
27/03/2015 04:15:52
Thomas Ganss (En ligne)
Main Trend
Frankfurt, Allemagne
Information générale
Forum:
Technology
Catégorie:
Équipement
Titre:
Divers
Thread ID:
01617300
Message ID:
01617331
Vues:
35
>>http://www.itworld.com/article/2901453/no-its-not-always-quicker-to-do-things-in-memory.html
>
>Sorry Al, no Eye-Opener but only stupid pet trick.
>
>Esp. telling is that the authors of the origina paper do ***not*** list the results of the mutable string types in Java, while going the extra mile with listing the times of the [lucky] benchmarking of an implemetation detail between Linux and Windows for copying on top of stack.
>
>We even had a similar discussion UT about typical timing observed when creating long strings (size of multi-page reporst for instance). In languages like vfp it ***might*** be open to discussion, but for Java IMO they are just benchmarking programmer/rookie mistake, as the typical article on string vs. StringBuffer/StringBuilder will show.
>
>While the authors in the conclusion list better education for programmers, the headline is meant to evoke further mentioning in print glossing over that not-so-PC finding ;-))

You're right that the tests are somewhat artificial and they're not benchmarking best practices such as StringBuilders where such can be used. Another thing they gloss over is the results are almost certainly not "sustainable" (i.e. continuous load vs "bursts"). They get excellent results for the write-to-disk option as long as the write cache is not overwhelmed; once that happens write performance can be no higher than the disk subsystem IOPS, and is probably (much) less due to overhead/thrashing.

Nonetheless I think the article is worthwhile:

- It shows just how bad some rookie programming mistakes can be :)

- It shows how good a modern virtual memory manager coupled with a write cache can be

- There may be scenarios where you can't take full advantage of mutable types. In those cases, it's a warning not to get too carried away trying to minimize disk I/O, and to at least benchmark the direct I/O case to see if any optimization you're doing is making things better or worse ;)

Speaking of sustained operation and disk IOPS, SSDs are a game changer in that area, 2 orders of magnitude faster than mechanical drives: http://en.wikipedia.org/wiki/IOPS . All other things being equal, makes the direct write to disk option that much more attractive ;)
Regards. Al

"Violence is the last refuge of the incompetent." -- Isaac Asimov
"Never let your sense of morals prevent you from doing what is right." -- Isaac Asimov

Neither a despot, nor a doormat, be

Every app wants to be a database app when it grows up
Précédent
Suivant
Répondre
Fil
Voir

Click here to load this message in the networking platform