Transcript metadata_stonjek_short-3D - Indico

Distributed Databases
for ATLAS
Stefan Stonjek
04-Jul-2006
Stefan Stonjek: LCG 3D
1
Outline

LCG 3D Project


COOL


Distributed Deployment of Databases for LCG
Conditions Database Project
Other database applications
04-Jul-2006
Stefan Stonjek: LCG 3D
2
Client access patterns


Main applications: Reconstruction, Simulation
Access Patterns








Read from file: experiment data, physics model
Read from database: file catalogue, geometry, conditions
Write to file: reconstructed data, simulated data
Write to database: file catalogue
Some minor applications (calibration) write to conditions database
Geometry, conditions: high volume; file catalogue: low volume
No need for instantaneous replication
Model for conditions database: write only at Tier-0 and replicate to Tier-1s and from
there to Tier-2s
•
•
Geometry change less, can be deployed by files
File catalogue is a more localized issue, not covered in this talk
•
04-Jul-2006
file catalogue is local for two but distributed for two other experiments
Stefan Stonjek: LCG 3D
3
Tiers, Resources and Level of Service

Different requirements and service capabilities for different tiers

Tier1 Database Backbone





Tier2




Medium volume, often only sliced extraction of data
Asymmetric, possibly only uni-directional replication
Part time administration (shared with fabric administration)
Tier3/4 (eg Laptop extraction)



High volume, often complete replication of RDBMS data
Can expect good network connection to other T1 sites
Asynchronous, possibly multi-master replication
Large scale central database service, local dba team
Support fully disconnected operation
Low volume, sliced extraction from T1/T2
Need to deploy several replication/distribution technologies


Each addressing specific parts of the distribution problem
But all together forming a consistent distribution model
04-Jul-2006
Stefan Stonjek: LCG 3D
4
Possible Service Architecture
O
T0
M
M
- autonomous
reliable service
T1- db back bone
- all data replicated
- reliable service
O
T2 - local db cache
T3/4
-subset data
-only local service
M
O
M
Oracle Streams
Cross vendor extract
MySQL Files
Proxy Cache
04-Jul-2006
Stefan Stonjek: LCG 3D
5
Possible distribution technologies

Vendor native distribution,Oracle replication and related technologies






Table-to-Table replication via asynchronous update streams
Transportable tablespaces
Little (but non-zero) impact on application design
Potentially extensible to other back-end database through API
Evaluations done at FNAL and CERN
Combination of http based database access with web proxy caches close to
the client

Performance gains



reduced real database access for largely read-only data
reduced transfer overhead compared to low level SOAP RPC based approaches
Deployment gains



04-Jul-2006
Web caches (e.g. squid) are much simpler to deploy than databases and could remove
the need for a local database deployment on some tiers
No vendor specific database libraries on the client side
“Firewall friendly” tunneling of requests through a single port
Stefan Stonjek: LCG 3D
6
Multi Tier Computing for LHC
T2
T2
T2s and T1s are inter-connected
by the general purpose research
networks
T2
T2
T2
T2
GridKa
IN2P3
T2
T2
Any Tier-2 may
access data at
any Tier-1
Dedicated
10 Gbit links
Brookhaven
TRIUMF
ASCC
T2
Nordic
Fermilab
T2
RAL
CNAF
T2
T2
T2
04-Jul-2006
PIC
SARA
T2
T2
Stefan Stonjek: LCG 3D
7
COOL

COOL: conditions database toolkit
Allow easy handling of condition data on a relational
database
 Is not relational itself


Data devided into
Folders (read: subdetector)
 Channels
 IOVs (interval of validity)


Still some performance issues
04-Jul-2006
Stefan Stonjek: LCG 3D
8
COOL performance



COOL performance testing done in a way which is
optimal for COOL but not close to a real world
scenario
ATLAS should provide number about the planed
COOL / conditions database usage
Because of internal COOL structure


Do not use many folders
Loop over Folder, Channel, IOV

04-Jul-2006
Sounds strange
Stefan Stonjek: LCG 3D
9
ATLAS


ATLAS is using the COOL system
Sometimes ATLAS has to keep using old
version of COOL
COOL had no backward compatibility
 New versions are sometimes unstable


ATLAS has to learn how to use COOL in an
optimal way
04-Jul-2006
Stefan Stonjek: LCG 3D
10
Conclusion


3D, COOL and ATLAS are on a good way
One has to ensure that they work well together
Need COOL tests which reflect ATLAS usage
pattern
 Nee ATLAS information how ATLAS wants to use
COOL (with numbers)

04-Jul-2006
Stefan Stonjek: LCG 3D
11