nobu / ruby-lang.org wrote:
> "linux-gnu" in "target_os" is substituted by "linux", so your AS_CASE never match.
> You should check for libjemalloc availability instead, I think.

I used $target, not $target_os.  An early version of my patch used
$target_os, but I noticed it was a noop so I changed it to use $target.

I've tested this with bare "./configure" and also --without-jemalloc.
Both work as expected on my GNU/Linux systems.

I worry this leads to platform-specific problems on non-GNU/Linux
systems.  It seems varnish/redis only tries jemalloc on Linux, too.

Also, I get one failure on both 32-bit and 64-bit:

[1/1] Test_StringModifyExpand#test_modify_expand_memory_leak = 0.02 s
  1) Failure:
  Test_StringModifyExpand#test_modify_expand_memory_leak
  [/home/ew/ruby/test/-ext-/string/test_modify_expand.rb:7]:
  rb_str_modify_expand().
  size: 14307328 => 31084544..
  Expected 2.1726309762381906 to be < 1.5.

It looks like certain allocation patterns are worse with jemalloc, but
I think real-world apps use less memory.