Re: Adaptive RW locks

To: NetBSD Kernel Technical Discussion List <tech-kern%netbsd.org@localhost>
Subject: Re: Adaptive RW locks
From: Andrew Doran <ad%netbsd.org@localhost>
Date: Tue, 21 Jan 2020 20:28:18 +0000

To follow up: in testing this I ended up discovering a number of tedious,
complicated deadlocks that could occur due to softints, kernel_lock and
other factors.  Trying to mitigate them killed the performance gain and it
still wasn't right.  I'm abandoning this idea because in practice it seems
too complicated.  On a more positive note there are a couple of LOCKDEBUG
improvements out of it.

Andrew

Follow-Ups:
- Re: Adaptive RW locks
  - From: Andrew Doran

References:
- Adaptive RW locks
  - From: Andrew Doran
- Re: Adaptive RW locks
  - From: Takashi YAMAMOTO
- Re: Adaptive RW locks
  - From: Andrew Doran

Prev by Date: Re: Blocking vcache_tryvget() across VOP_INACTIVE() - unneeded
Next by Date: Re: libc.so's vmobjlock / v_interlock
Previous by Thread: Re: Adaptive RW locks
Next by Thread: Re: Adaptive RW locks
Indexes:

Home | Main Index | Thread Index | Old Index