[PATCH] D76240: [Sanitizers][Test] If the default linker is LLD, disable threads

[Nemanja Ivanovic via Phabricator via llvm-commits]

nemanjai added a comment.

In D76240#1925419 <https://reviews.llvm.org/D76240#1925419>, @efriedma wrote:

> "overwhelmed" by what, exactly?  I mean, I guess there's fundamentally some overhead if we end up with N^2 active threads (where N is the number of cores), but threads don't have that much memory overhead on their own; it shouldn't be high in absolute terms unless your test machine somehow has hundreds of cores.  And I'm not sure what else could cause an issue; I guess if the kernel scheduler decided to do something weird, context switches might hurt performance?
>
> Also, what OS are you using?


  $ cat /etc/lsb-release 
  DISTRIB_ID=Ubuntu
  DISTRIB_RELEASE=16.04
  DISTRIB_CODENAME=xenial
  DISTRIB_DESCRIPTION="Ubuntu 16.04.6 LTS"
  
  $ lscpu
  Architecture:          ppc64le
  Byte Order:            Little Endian
  CPU(s):                192

The errors reported by the system is that it is unable to spawn any more threads because the resource is unavailable. This hardly seems unique to my machine. I imagine most machines with hyperthreading and large core counts will be in a similar situation.

BTW. I am not even convinced that the number of threads is `n^2` in the number of CPU's. I didn't really dig into the implementation of the parallel support library, but the following comment in `include/llvm/Support/Parallel.h` certainly seems a bit concerning:

  // TaskGroup has a relatively high overhead, so we want to reduce
  // the number of spawn() calls. We'll create up to 1024 tasks here.
  // (Note that 1024 is an arbitrary number. This code probably needs
  // improving to take the number of available cores into account.)


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76240/new/

https://reviews.llvm.org/D76240