Date: Wed, 30 Apr 2003 17:20:45 -0700 From: Terry Lambert <tlambert2@mindspring.com> To: Benjamin Krueger <benjamin@seattlefenix.net> Cc: Michael Nottebrock <michaelnottebrock@gmx.net> Subject: Re: SWAP size Message-ID: <3EB0685D.B88C7D3C@mindspring.com> References: <200304281054.48976.ryba@kompakt.pl> <3EB05582.297F50AE@lbl.gov> <20030430231522.GO11702@surreal.seattlefenix.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Benjamin Krueger wrote: > * Jin Guojun [DSD] (j_guojun@lbl.gov) [030430 15:54]: > > For server, 2x may be required, and typically 2.5x is needed. > > In what instance can you expect to have server processes that are ok to > page to disk? Maybe I'm wrong, but I've always considered a server that > is paging my important processes to disk a broken server in need of ram. When your boss won't buy you more hardware, and expects you to do your job anyway, and your job involves deploying services on the available machinery. As long as the processing load, when swap is included, doesn't impact user-visible performance, it probably doesn't matter if you are swapping or not. So I'm going to say there's a fair bit of distance between "user experience broken", "organization broken", and "server broken", with "server broken" being last in line... 8-). -- Terry
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3EB0685D.B88C7D3C>