Sam Saffron

  • Email:
  • Registered on: 07/22/2012
  • Last connection: 03/21/2014

Activity

Reported issues: 15

02/22/2014

09:07 PM ruby-trunk Feature #9113: Ship Ruby for Linux with jemalloc out-of-the-box
@nobusan I think that would be a reasonable approach
@eric / @ko1 / everyone
here are the results of runnin...

02/19/2014

12:05 AM ruby-trunk Feature #9113: Ship Ruby for Linux with jemalloc out-of-the-box
@Eric
sure bench needs a bit more love to be totally representative of a rails request. Also this test will do ko...

02/18/2014

11:53 PM ruby-trunk Feature #9113: Ship Ruby for Linux with jemalloc out-of-the-box
Note, this pattern of
1. Retaining large number of objects
2. Allocating a big chunk of objects (and releasing) ...
11:39 PM ruby-trunk Feature #9113: Ship Ruby for Linux with jemalloc out-of-the-box
I can confirm 2 findings.
When heaps are small you barely notice a different.
When heaps grow and general memory...

01/03/2014

08:12 PM ruby-trunk Bug #9262: global_method_cache should be configurable or grow automatically
FYI it seems perf of method lookups has regressed in 2.1:
https://gist.github.com/SamSaffron/8232978
This makes...

12/23/2013

04:56 PM ruby-trunk Bug #9262: global_method_cache should be configurable or grow automatically
Note: for comparison see the results on an unpatched 2.0.0 p353
---
home_page:
50: 35
75: 40
90: 107
...
04:35 PM ruby-trunk Bug #9262: global_method_cache should be configurable or grow automatically
Discourse Bench,
Disabled Method Cache vs Current cache vs 16x larger method cache vs Funny Falcon
Disabled...
04:11 PM ruby-trunk Bug #9262: global_method_cache should be configurable or grow automatically
There was a concern that gettimeofday is expensive and adds too much time to my results
I measured:
static VAL...
10:27 AM ruby-trunk Bug #9262: global_method_cache should be configurable or grow automatically
Before I measure the changes proposed by funny falcon I wanted to present the sad state of affairs.
I applied this...

11/27/2013

08:26 AM ruby-trunk Bug #9159: [patch] use rb_fstring for internal strings
Seeing similar results for Discourse:
https://gist.github.com/SamSaffron/7668043

Also available in: Atom