Print

Print


Hi Stephane,

Andy's statement described a model that is used by Babar (and may be by WT2 in the future), that is, a backend tape (or tape like) system holds all data, and disk are just frontend cache. So if a storage node with disk is down, other nodes will server the request from jobs  by fetching the data from tape backend. This may not be the case for you.

I think so far the method described in Patrick McGain's respond is probably the best option to drain a storage node.

regards,
Wei Yang  |  [log in to unmask]  |  650-926-3338(O)


On Jan 19, 2012, at 1:36 PM, Stephane Willocq wrote:

> Hi Andy,
> 
>   I was interested in your answer:
> 
> On 1/9/12 3:41 AM, Andrew Hanushevsky wrote:
>> P.S. The current model is that missing files from a faulty data server
>> would be automatically copied in on other servers when so requested.
>> That is a reasonable model is you assume that te ailure rate is
>> relatively small.
> 
> You mention an automatic copy to other servers can be requested. How do 
> we request this?
> 
> 
> Stephane.
> 
> 
>> On Sat, 7 Jan 2012, Doug Benjamin wrote:
>> 
>>> Hello,
>>> 
>>> Are there any xrootd commands to drain a faulty data server of files
>>> and distribute them across the
>>> rest of the data servers in the storage system.
>>> 
>>> Thanks,
>>> 
>>> Doug Benjamin
>>> 
>>> ########################################################################
>>> Use REPLY-ALL to reply to list
>>> 
>>> To unsubscribe from the XROOTD-L list, click the following link:
>>> https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1
>>> 
> 
> -- 
> -----------------------------------------------------------------
> Stephane Willocq                            Office (413) 545-0525
> Department of Physics                       Fax    (413) 545-0648
> University of Massachusetts
> 710 North Pleasant St                   [log in to unmask]
> Amherst, MA 01003-9337            http://people.umass.edu/willocq
> -----------------------------------------------------------------
> 
> ########################################################################
> Use REPLY-ALL to reply to list
> 
> To unsubscribe from the XROOTD-L list, click the following link:
> https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1

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

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