Replica Optimisation Within The EU DataGrid

1
Replica Optimisation Within The EU DataGrid

• David Cameron
• e-Science Summer School
• 16 21 September 2002

2
Summary

• The need for Grid.
• Grid architecture.
• Replica management and optimisation through
  economic models.
• Grid simulation OptorSim.
• Some results.
• Simulation demo.

3
The Large Hadron Collider
4
Complexity CPU Requirements

• Complex events
• Large number of signals
• good signals are covered with background
• Many events
• 109 events/experiment/year
• 1- 25 MB/event raw data
• several PB per year
• Need world-wide

7106 SPECint95 (3108 MIPS) Several PB of
storage space
GRID
computing
5
A Physics Event

• Gated electronics response from a proton-proton
  collision
• Raw data hit addresses, digitally
• converted charges and times
• Marked by a unique code
• Proton bunch crossing number, RF bucket
• Event number
• Collected, Processed, Analyzed, Archived.
• Variety of data objects become associated
• Event migrates through analysis chain
• may be reprocessed
• selected for various analyses
• replicated to various locations.

6
Data Structure
Trigger System
Data Acquisition
Run Conditions
Level 3 trigger
Calibration Data
Raw Data
Trigger Tags
Reconstruction
Event Summary Data ESD
Event Tags
REAL and SIMULATED data required
7
Data Hierarchy
RAW
Recorded by DAQ Triggered events
2 MB/event
Detector digitisation
ESD
Pseudo-physical information Clusters, track
candidates (electrons, muons), etc.
Reconstructed information
100 kB/event
Physical information Transverse momentum,
Association of particles, jets, (best) id of
particles, Physical info for relevant objects
AOD
Selected information
10 kB/event
Analysis information
TAG
Relevant information for fast event selection
1 kB/event
8
Physics Analysis
ESD Data or Monte Carlo
Tier 0,1 Collaboration wide
Event Tags
Event Selection
Calibration Data
Analysis, Skims
INCREASING DATA FLOW
Raw Data
Tier 2 Analysis Groups
Physics Objects
Physics Objects
Physics Objects
Tier 3, 4 Physicists
Physics Analysis
9
Tier-0 - CERN
Commodity Processors IBM (mirrored) EIDE Disks..

Storage Systems.
2004 Scale 1,000 CPUs 1 PBytes
10
UK Tier-1 RAL
New Computing Farm 4 racks holding 156 dual
1.4GHz Pentium III cpus. Each box has 1GB of
memory, a 40GB internal disk and 100Mb ethernet.
Tape Robot upgraded last year uses 60GB STK 9940
tapes 45TB currrent capacity could hold 330TB.
50TByte disk-based Mass Storage Unit after RAID 5
overhead. PCs are clustered on network switches
with up to 8x1000Mb ethernet out of each rack.
2004 Scale 1000 CPUs 0.5 PBytes
11
UK Tier-2 ScotGRID

• 59 IBM X Series 330 dual 1 GHz Pentium III with
  2GB memory

• IBM X Series 370 PIII Xeon with 512 MB memory 32
  x 512 MB RAM
• 70 x 73.4 GB IBM FC Hot-Swap HDD

2004 Scale 300 CPUs 0.1 PBytes
12
Grid architecture
13
Replica management

• Replica Manager
• copyFile()
• copyAndRegisterFile()
• listReplicas()
• deleteFile()
• Replica Catalogue (LFN PFNs )
• registerEntry()
• unregisterEntry()

14
Submitting a Job
The Grid
Site 1
User
Scheduler
Site 2
Site 3
15
Replica Optimisation

• Optimise use of computing, storage and network
  resources.
• Short term optimisation
• Minimise running time of current job.
• Get me the files for my job as quickly as
  possible
• Long term optimisation
• Minimise running time of all jobs.
• Make sure files are in the best
• places for all my future jobs.

16
Optimisation Through Economic Models

• Files represent goods.
• Bought by Computing Elements for jobs.
• Bought and sold by Storage Elements to make
  profit.
• Investment decision based on projected future
  value based on previous file access patterns.
• Storage Elements can buy popular files
• independently of running jobs.

17
Replica optimiser architecture

• Access Mediator (AM) - contacts replica
  optimisers to locate the cheapest copies of files
  and makes them locally available
• Storage Broker (SB) - manages files stored in
  storage element, trying to maximise profit for
  the finite amount of storage space available
• P2P Mediator (P2PM) - establishes and maintains
  P2P communication between grid sites

18
Auction Mechanism

• Use Vickrey auction
• Every seller makes a bid lower than the asking
  price.
• File is sold to lowest bidder at second lowest
  price.
• Ensures
• Low price for purchaser.
• Trading fairness.
• Minimal messaging

19
OptorSim a replica optimiser simulation

• Need to tune optimisation algorithms.
• Develop Grid simulation in JAVA.
• Input network configuration and files and jobs.
• Job transfer the files defined in job
  description to CE running job.

20
OptorSim a replica optimiser simulation

• Schedule to CE using
• CEcost queueSize
• accessCost
• Files requested according to access pattern.
• Sequential
• Random
• Unitary random walk
• Gaussian random walk
• Zipf distribution (not yet implemented).
• No processing involved, only file transfer.

21
OptorSim a replica optimiser simulation
Data Sample Number of Files Total Size (GB)
Central J/y 120 1200
High pt electrons 20 200
Inclusive electrons 500 5000
Inclusive muons 140 1400
High Et photons 580 5800
Z0 -gt b bbar 60 600

• Input site policies and experiment data files
  (simplified CDF jobs).

• Tested replication strategies
• No replication
• Always Replicate, Delete Oldest File
• Always Replicate, Delete Least Accessed File
• Economic Model

22
Results

• Eco model 40 better for sequential but no better
  for others expected since eco model is tuned
  for sequential access.

23
Future Work

• 3rd party replication
• SAM access patterns
• Integration Optor Reptor Testbed

24
Conclusions

• Simulation shows Eco Model successful.
• Further simulation will help tune algorithms.
• Integration into testbed code soon.