Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 31 Jan 2002 10:51:49 -0800 (PST)
From:      Matt Dillon <dillon@FreeBSD.org>
To:        cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org
Subject:   cvs commit: src/sys/kern vfs_subr.c
Message-ID:  <200201311851.g0VIpne43133@freefall.freebsd.org>

next in thread | raw e-mail | index | archive | help
dillon      2002/01/31 10:51:48 PST

  Modified files:        (Branch: RELENG_4)
    sys/kern             vfs_subr.c 
  Log:
  MFC new vlrureclaim trigger-point code.  vlrureclaim()'s purpose in life is
  to maintain kern.maxvnodes, not to try to free memory.  In fact, the reclaim
  code is generally called when there is lots of memory available but the
  system has too many vnodes.  So we can safely skip vnodes which still have
  a large number of resident pages present and thereby avoid unnecessary
  flushes (e.g. for Yahoo, potentially nasty flushes of MAP_NOSYNC pages).
  We calculate a resident count that guarentees we will still be able to
  locate enough vnodes to reclaim to satisfy kern.maxvnodes.
  
  MFC new vlruvp() procedure, which is currently a NOP.  We will be able to
  utilize this procedure after we've cleaned up the filesystem SYNCing code.
  Right now SYNC becomes wildly inefficient if the vlruvp() code is enabled.
  
  Revision    Changes    Path
  1.249.2.24  +44 -0     src/sys/kern/vfs_subr.c

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200201311851.g0VIpne43133>