From: Greg Ercolano <erco@(email surpressed)>
Subject: Re: [Q+A] How do I determine what caused a render node to crash during
   Date: Thu, 06 Apr 2006 21:18:32 -0400
Msg# 1272
View Complete Thread (4 articles) | All Threads
Last Next
	One quick clarification [IN CAPS]:

    It's good you ask, because yes, putting symlinks TO A MOUNT POINT in root
    are as bad putting your mount points in the root directory.

	Symlinks in / are OK, as long as they're not pointing to NFS dirs,
	including mount points.

	Basically mount points (and any dirs below them) are potential 'traps'
	for mission critical processes, like emergency root logins.

	You need to be careful that root logins don't cross paths with NFS directories,
	so that one can do emergency administration on client machines that have hung
	NFS mounts [without hanging up].

	From a sysadmin's point of view, I've learned to think of "hard" mounted
	NFS directories as the "kiss of death" that can prevent one from even
	logging in as root. If anything in the root login's process [or shell]
	touches an NFS drive, the root login is toast when there's an NFS outage.

	To ensure root logins 'always work', you have to really be vigilant
	in preventing NFS paths from getting into root logins.

--
Greg Ercolano, erco@(email surpressed)
Rush Render Queue, http://seriss.com/rush/
Tel: (Tel# suppressed)
Cel: (Tel# suppressed)
Fax: (Tel# suppressed)

Last Next