[Devel] Re: [PATCH 0/9] namespaces: Introduction

[Eric W. Biederman]

"Serge E. Hallyn" <serue at us.ibm.com> writes:

> This patchset introduces a per-process utsname namespace.  These can
> be used by openvz, vserver, and application migration to virtualize and
> isolate utsname info (i.e. hostname).  More resources will follow, until
> hopefully most or all vserver and openvz functionality can be implemented
> by controlling resource namespaces from userspace.
>
> Previous utsname submissions placed a pointer to the utsname namespace
> straight in the task_struct.  This patchset (and the last one) moves
> it and the filesystem namespace pointer into struct nsproxy, which is
> shared by processes sharing all namespaces.  The intent is to keep
> the taskstruct smaller as the number of namespaces grows.


Previously you mentioned:
> BTW - a first set of comparison results showed nsproxy to have better
> dbench and tbench throughput, and worse kernbench performance.  Which
> may make sense given that nsproxy results in lower memory usage but
> likely increased cache misses due to extra pointer dereference.

Is this still true?  Or did our final reference counting tweak fix
the kernbench numbers?

I just want to be certain that we don't add an optimization,
that reduces performance.

> Changes:
> 	- the reference count on fs namespace and uts namespace now
> 	  refers to the number of nsproxies pointing to it
> 	- some consolidation of namespace cloning and exit code to
> 	  clean up kernel/{fork,exit}.c
> 	- passed ltp and ltpstress on smp power, x86, and x86-64
> 	  boxes.

Nice.

Eric