Simon 'corecode' Schubert corecode at
Thu Dec 14 03:19:07 PST 2006

Vlad Galu wrote:
  It looks like the extra spage usage was fixed by Jason Evans around
March. The Google link provided by Freddie Cash pretty much covers
every info you needed. I can perform further benchmarks if needed. But
I think I'll not do it, given the reluctance on the list. I'm
certainly not the best judge for this level of technical detail.
I can't spot a definite reluctance.  Some people are conservative, some people say "why not, if it is good".  I think it shows promising numbers, but we will probably not experience the reduced contention because our userland threading is still 1:N.

In any case, we slowly need a formalized benchmark suite to spot regressions and prove that new code does what it advertises.  An allocator benchmark is needed for sure as well.

I think that jemalloc will perform better than phkmalloc in almost all cases.  However I get the feeling that it is a little bit complicated, but maybe I just don't have the right knowledge about allocators.  If nothing breaks I'm for including jemalloc, maybe not as default (I wouldn't see why not), but as runtime switchable allocator (/etc/malloc.type -> jemalloc)

Serve - BSD     +++  RENT this banner advert  +++    ASCII Ribbon   /"\
Work - Mac      +++  space for low €€€ NOW!1  +++      Campaign     \ /
Party Enjoy Relax   |      Against  HTML   \
Dude 2c 2 the max   !       Mail + News   / \
-------------- next part --------------
A non-text attachment was scrubbed...
Name: pgp00025.pgp
Type: application/octet-stream
Size: 252 bytes
Desc: "Description: OpenPGP digital signature"
URL: <>

More information about the Kernel mailing list