Date: Sat, 16 Nov 2002 21:54:37 -0800 (PST) From: Matthew Dillon <dillon@apollo.backplane.com> To: "M. Warner Losh" <imp@bsdimp.com> Cc: hackers@FreeBSD.ORG Subject: Re: cvs commit: src/bin/sleep sleep.c Message-ID: <200211170554.gAH5sbGc036574@apollo.backplane.com> References: <200211152017.gAFKHbFS044142@apollo.backplane.com> <20021116.174331.28768088.imp@bsdimp.com> <200211170158.gAH1wJhc035731@apollo.backplane.com> <20021116.200126.81091323.imp@bsdimp.com>
next in thread | previous in thread | raw e-mail | index | archive | help
:I just ran a quick test on my systems here. It looks like two
:identical systems give results that are approximately:
:
: VSZ RSS
:dynamic:
:root 79054 1.3 2.5 1952 1524 pa S 2:56AM 0:00.13 tcsh
:static:
:root 38788 0.0 0.1 1324 908 pi S 7:53PM 0:00.03 tcsh
:
:which actually is a little more than the numbers that you quoted above
:(this is 4.5-release + a couple of tweaks). These were run 3 minutes
:apart on machines in different timezone and were for just the login
:case. So it does look like there's more of a penalty for this than I
:would have otherwise expected. I don't know how much of the VSZ is
:shared with other processes in the dynamic case.
:
:When I run tcsh, I see a reduction by 592k of memory fre that vmstat
:reports in the dynamic case and a 532k reduction in that same
:parameter in the static case, so maybe someting is exagerating the
:difference between the two in the ps stats. Or maybe something else
:ran on the static system (since it is used for other things)...
:
:Warner
We could figure it out by looking at the /proc/N/map for the process
I suppose. The number I got seemed a little high, even for something
as big as csh. 50K sounds closer to what I would expect it to be.
The VSZ and RSS are irrelevant in regards to shareability, but RSZ
does give us a hint in regards to the run-time impact the program is
having on the VM system. The page-table overhead shouldn't be
discounted either.
-Matt
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200211170554.gAH5sbGc036574>