May 15, 2014
* Created issues, will space out across sprints and add estimates
* One of them is to follow up with HTCondor team on dynamic slot ClassAds
* Adding visit id to worker job for monitoring
* Working on pre-script to write DAG dynamically
+ Will keep simple; probably not so necessary for Nightly Computing
* Will estimate story points
* Have replicator jobs talking to replicator nodes and distributor nodes
+ Just metadata for now, not data yet
+ How much data? Will be 500+MB; maybe use 50MB scaled to network
+ How to transfer data?
- Job to node: shm, socket
- Replicator to distributor: memory to memory via socket, file transfer
- Doesn't matter much; whatever is easiest
* Using regular lsst-dev HTCondor pool
* Right now, some scripts point to SRP's home directory
+ Will work on making relocatable
OCS will have DDS interface available sooner than expected, maybe June/July
* Log messages gathered to one location? Yes
+ Also critical messages can go via real-time messages
+ Also status updated directly in databases for monitoring
* Need to make sure operators have sufficient insight into system
* Is Tucson headquarters an overall control center?
+ Anticipate HQ is mostly overall management, not day-to-day
+ Four operational centers (Base, Archive, Chile DAC, US DAC)
+ Operational centers run mostly independently
+ Base runs Nightly Computing in conjunction with NCSA
+ Archive runs DRP
* DES is trying out large solid-state disk behind GPFS
+ K-T will see if there are any potential uses for LSST testing
+ Maybe DB group?