Print

Print


Hi Pete

yes, the head is much better than the previous version. I must admit I 
did not check it on many platforms though: just solaris and linux

Jacek



Peter Elmer wrote:
>   Hi guys,
> 
>   Ok, let's figure this one out and make sure the fix is included in the
> new production version in the next days. (Plus there are small smattering of 
> fixes plus the new security updates sitting at the CVS HEAD.)
> 
>   Gerri, I see you've been doing checks on the other platforms supported by
> ROOT. Is there anything else you still need to check for the new production 
> version? (I checked gcc 3.4.3 and icc 8.0 the other day, too. I still have to 
> do icc 8.1, though.)
> 
>   Jacek, do you have any last minute fixes which have to be included
> for the monitoring?
> 
>                                    Pete
> 
> 
> On Sat, Mar 05, 2005 at 04:02:25PM -0800, Andrew Hanushevsky wrote:
> 
>>On Sat, 5 Mar 2005, Fons Rademakers wrote:
>>
>>
>>>   the old rootd never allowed two or more clients to open the same file
>>>for writing. We have the following rules:
>>>
>>>A file can only be opened for writing if the file is not already open for
>>>reading or writing by any other process.
>>>A file can only be opened for reading if the file is not already open for
>>>writing (where writing of course includes "update" mode in ROOT parlance).
>>
>>That's exactly the semantic that is in xrootd.
>>
>>
>>>To be a full drop in replacement xrootd must be able to support the file
>>>update mode. I think this could be easily achieved if we allow r/w pools
>>>where the olbd never will trigger a replication. In such a pool the olbd
>>>can be used to keep track of the status of a file, if it is open for
>>>reading, in which case it cannot be opened by another process for writing
>>>or if a file is open for writing in which case it cannot be opened by
>>>anybody else.
>>
>>That's also the semantic in xrootd. When a file is open for reading, any
>>available node can host the file. If the file is open for writing, only
>>one r/w node is allowed to host the file. I will tighten these rules to
>>make sure that a file will not be replicated if it is being hosted by
>>a r/w node.
>>
>>I think the problem in xrdcp stemmed from a misunderstanding of what the
>>"force" option really does. That option exists in both rootd and xrootd
>>and both have exactly the same semantics (I tried very hard to
>>duplicate the semantics of rootd in this area).
>>
>>Andy
> 
> 
> 
> 
> -------------------------------------------------------------------------
> Peter Elmer     E-mail: [log in to unmask]      Phone: +41 (22) 767-4644
> Address: CERN Division PPE, Bat. 32 2C-14, CH-1211 Geneva 23, Switzerland
> -------------------------------------------------------------------------