SVNews r327404

NOTE: This service is experimental and subject to change! Use at your own risk!

2017-12-31 03:06:29 - r327404 by mjg (Mateusz Guzik)

Complete list of files affected by revision r327404:

(Note: At the moment, these links point to ViewVC on They are probably slow. Do not overuse.)

   Contents     MODIFY   /stable/11  
  History   Contents   Diff   MODIFY   /stable/11/sys/kern/kern_proc.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/kern/kern_sysctl.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/kern/subr_vmem.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/kern/vfs_bio.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/vm/uma_core.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/vm/vm_page.c  
  History   Contents   Diff   MODIFY   /stable/11/sys/vm/vm_pager.c  

Commit message:

MFC r323234,r323305,r323306,r324044:

  Start annotating global _padalign locks with __exclusive_cache_line

  While these locks are guarnteed to not share their respective cache lines,
  their current placement leaves unnecessary holes in lines which preceeded

  For instance the annotation of vm_page_queue_free_mtx allows 2 neighbour
  cachelines (previously separate by the lock) to be collapsed into 1.

  The annotation is only effective on architectures which have it implemented
  their linker script (currently only amd64). Thus locks are not converted to
  their not-padaligned variants as to not affect the rest.


  Annotate global process locks with __exclusive_cache_line


  Annotate Giant with __exclusive_cache_line


  Annotate sysctlmemlock with __exclusive_cache_line.


Powered by Python FreeBSD support by secnetix GmbH & Co. KG

Page generated in 38 ms, 8 files printed. Current time is 2018-04-20 13:18:18. All times are in UTC/GMT.