Print

Print


Hi Andy,

as we are about all and any arguments. In case of DNS-RR host alias as 
meta manager all || any is preferred way when host+ is specified? For 
instance, assuming host+ is always there (with at least two hosts IPs 
behind):

all.manager meta all cmsxrootd.fnal.gov+ 1213
or
all.manager meta any cmsxrootd.fnal.gov+ 1213

Which one of two practically brings operational benefit or drawbacks and 
why? My guess is "all" is right way to go as the fail-over is partially 
DNS-RR itself...?

Thanks,
Marian

On 20.3.2014 17:23, Andrew Hanushevsky wrote:
>
>
> -----Original Message----- From: Matevz Tadel
> Sent: Thursday, March 20, 2014 12:36 PM
>
> We're setting up RR-DNS for US-CMS now ... and I still don't understand
> what
> any/all do when subscribing a manager to a set of meta-managers.
>
> all.manager meta all cmsxrootd.fnal.gov+ 1213
>
> I thought that namespace cache on (meta) managers is only populated with
> things
> that they actively query. Are managers actually pushing their caches
> upwards to
> meta-managers? But then neither any nor all is any good as the caches
> will still
> end up on one meta-manager only and client connections come in from a
> random one.
>
> I thought this kicks in for client requests that can not be served
> locally and
> have to be redirected upwards.
>
> Please explain! :)
> ----------------------------
> Hi Matevz,
>
> Sure. The basic problem is that you are confusing xrootd with cmsd. The
> cmsd is what is caching the information and only xrootd's connect on a
> client's behalf. So access is strictly controlled and is deterministic.
> When you specify "all" the requests are load balanced in such a way that
> the cache is not duplicated across cmsd's unless one of them dies. For
> "any" (which makes sense if there are only 2 cmsd's) always uses a
> particular cmsd unless it dies. So, again, caches are not duplicated
> across cmsd's.
>
> Andy

########################################################################
Use REPLY-ALL to reply to list

To unsubscribe from the XROOTD-DEV list, click the following link:
https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&A=1