1 CyberBricks: The future of Database And Storage Engines Jim Gray Gray.
Jim Gray 1 EOSDIS Alternate Architecture Study Jim Gray McKay Fellow, UC Berkeley, 1 May 1995, gray...
-
Upload
ophelia-kennedy -
Category
Documents
-
view
212 -
download
0
Transcript of Jim Gray 1 EOSDIS Alternate Architecture Study Jim Gray McKay Fellow, UC Berkeley, 1 May 1995, gray...
Jim Gray
1
EOSDIS Alternate Architecture StudyJim Gray
McKay Fellow, UC Berkeley, 1 May 1995, gray @ crl.com
1. Background - problem and proposed solution
2. What California proposed
Co workers:
Mike Stonebraker: Producer / Director / Script Writer / Propeller Head
Bill Farrell: Ramrod and Computer-literate DirtBag
Jeff Dozier: Godfather
Special effects:
Earth Science: Frank Davis, C. Roberto Mechoso, Jim Frew
Computer Science: Reagan Moore, Jim Gray, Joe Pasquale
Administration: Claire Mosher
Writing: Stephanie Sides
Prototypes: many-many....people
Jim Gray
2
What’s The Problem?Antarctica is melting -- 77% of fresh water liberated
=> sea level rises 70 meters => Chico & Memphis are beach front propertyNew York, Washington, SF, LA, London, Paris
Let’s study it! Mission to Planet Earth
EOS: Earth Observing System (17B$ => 10B$) 50 instruments on 10 satellites 1997-2001
Plus Landsat (added later)
EOS DIS: Data Information System:3-5 MB/s raw, 30-50 MB/s processed.4 TB/day, 15 PB by year 2007
Issues
How to store it?
How to serve it to users?
Jim Gray
3
What Happened?1986: Mission to Planet Earth
1989: Bids from Hughes & TRW
1993: Contract Grant, Public Review:
customers do not want it (tape/mainframe centric)
1994: Alternate Architecture
Three “outside teams”Wyoming: Internet 20,000,000
Maryland: Software Engineering
California: DB centric
One “home team” CORBA & Z 39.50 & UNIX
1995: Drifting in the Sequoia direction
Jim Gray
4
The Hughes Plan8 DAACs (Data Active Archive Centers) = Bytes
(one per congressional district?)
N SCFs (Scientific Computation Facilities) = MIPS(typically instrument or science teams)
Thin wires among them
90% of DAAC processing is PULLbuilding standard data products
fixed pipeline: calibrate, grid, derive
Typical subscriber gets tapes or CDroms(standard data products)
One “chauffeur” per 10 customers (high ops costs)
Build everything (operations, HSM, DBMS,...) from scratchCORBA and Z 39.50 is the glue.
Criticism: not evolvable, not open, not online, not useful.
Jim Gray
5
What California Proposed0. Design for success: expect that millions will use the system (online)1. DBMS centric design automates discovery, access, management2. Object relational databases enable
Automate access to data so that the NASA 500, Global Change 10,000 and Internet 20,000,000 can use system.
Cache popular results, not all results (saves 3x or more) Compute on demand (saves lots of storage and cpu).
Emphasize pull processing rather than push processing.Use parallelism to get scaleup.
Do Batch as a data pump
3 Be Smart Shoppers: Use COTS hardware/software (saves 400M$)
Just-in-time acquisition (saves 400M$)Use workstation not mainframe technology (gives 10x more stuff)Depreciate over 3 years (ends in 2007 with "fresh" equipment)
4. 2 + N node architecture 2 Super DAACs for fault tolerance and for growth.
Unify the 2 "big" data storage centers with 2 big data analysis centers.Allow many “little” peer-DAACs at science/user groups
Jim Gray
6
Meta-Model for Sequoia ProposalBe technological optimists:
couldn’t build it today, count on progress.
ride technology wave (= not water cooled)
Buy or Seed, do not build.
Use COTS where possible
Fund 2 or more COTS vendors if need product
OR DBMS
HSM
Operations.
Replace people with technology (= OR DBMS):
automate data discovery, access, visualization
DBMS Centric view.
Jim Gray
7
DBMS Centric ViewThis is a database problem (no kidding)!
This is not
a file system problem (file wrong abstraction)
a rpc problem (CORBA wrong abstraction)
a Z 39.50 problem (Z 39.50 is a FAP).
This is a operations problem
Hierarchical storage management
Network management
Source code control
client-server tools.
You can BUY all this stuff. Fund COTS.
BUILD AS LITTLE AS POSSIBLE
Jim Gray
8
What California Proposed0. Design for success: expect that millions will use the system (online)1. DBMS centric design automates discovery, access, management2. Object relational databases enable
Automate access to data so that the NASA 500, Global Change 10,000 and Internet 20,000,000 can use system.
Cache popular results, not all results (saves 3x or more) Compute on demand (saves lots of storage and cpu).
Emphasize pull processing rather than push processing.Use parallelism to get scaleup.
Do Batch as a data pump
3 Be Smart Shoppers: Use COTS hardware/software (saves 400M$)
Just-in-time acquisition (saves 400M$)Use workstation not mainframe technology (gives 10x more stuff)Depreciate over 3 years (ends in 2007 with "fresh" equipment)
4. 2 + N node architecture 2 Super DAACs for fault tolerance and for growth.
Unify the 2 "big" data storage centers with 2 big data analysis centers.Allow many “little” peer-DAACs at science/user groups
Jim Gray
9
Design for Success: Expect Lots of UsersExpect that millions will use the system (online)
Three user categories:
NASA 500 -- funded by NASA to do science
Global Change 10 k - other dirt bags
Internet 20 m - everyone elseGrain speculatorsEnvironmental Impact ReportsNew applications
=> discovery & access must be automatic
Allow anyone to set up a peer-DAAC & SCFDesign for Ad Hoc queries, Not Standard Data Products
If push is 90%, then 10% of data is read (on average).
=> A failure: no one uses the data, in DSS, push is 1% or less.
=> computation demand is 100x Hughes estimate (pull is 10x to 100x greater than push)
Jim Gray
10
The Process FlowData arrives and is pre-processed.
instrument data is calibrated,
gridded
averaged
Geophysical data is derived
Users ask for stored data
OR to analyze and combine data.
Can make the pull-push split dynamically
Pull Processing Push ProcessingOther Data
Jim Gray
11
The Software Model: Global View
SQL* is the FAP and API.
Applications use it to access data.
It includes
stored procedures
(so RPC)
GC class libraries
Computation is data driven
Gateways for other interfaces
HTTP, Z 39.50, Corba & COM
TP or TP-lite manages workflow
COTS middleware
client program
client program
other protocol
gateway
gateway
SQL–*SQL–*
SQL–*
non-SQL–* DBMS on
peerDAAC orsuperDAAC or
non-EOSDIS system
SQL–*COTS SQL-*local DBMS
on peerDAAC orsuperDAAC other protocol
Jim Gray
12
Automate access to data Invest in:
Design global change schema.cooperate with standards groups.
OR DBMS class libraries for GC datatypes
Develop browser to do resource discovery
Community will develop access & vis tools
OR DBMS will do
PUSH processing: triggers and workflow
PULL processing: query optimization.
(some assembly required).
Jim Gray
13
How Well Did SQL Work?Bill Farrell and others did 30 user scenarios schema,
application, SQL, performance
Snow cover, CO2, GCM,...
Avg ad hoc scenario generated about 30% of
EOSDIS baseline processing
=> validated PULL over PUSH demand
SQL was indeed a power tool:
Many scenarios became a few simple SQL queries:
Need a spatial & temporal SQL.
Personal view:
It’s great!, much better than Farrell or I expected.
Jim Gray
14
Compute on demand90% of data is NEVER used (according to Hughes).
Some data is used only once.
Data is often re-calculated
repair hardware/software bugs,
new & better algorithms
Optimization: store only popular data.
Compute this based on past use(of this data and related data)
Balance two costs:1. Re_Compute_Cost / Re_Use_Interval2. Storage_Cost x Re_Use_Interval
Recompute is often cheaper (saves 3x we think).
Jim Gray
15
Use parallelism to get scaleup.Many queries look at 100s or 1,000s of data tiles.
e.g. Berkeley weekly Landsat images since 1972.
= 1000 tape accesses.
= 4,000 tape minutes = 6 days.
Done 1,000 way parallel: = 4 minutes.Disk & tape demands are huge: multi-GOX
Computation demands are huge: tera-ops.
Only solution:
Use parallel execution
Use parallel data access
SQL* does this for you automatically.
Jim Gray
16
Data PumpCompute on demand small jobs
less than 1,000 tape mountsless than 100 M disk accessesless than 100 TeraOps.(less than 30 minute response time)
For BIG JOBS scan entire 15PB database once a day /week
Any BIG JOB can piggyback on this data scan.
DAAC in 2007:
15 PB of Tape Robot
1 PB of Disk
10-TB RAM 500 nodes
10,000 drives
1,000 robots
Jim Gray
17
What California Proposed0. Design for success: expect that millions will use the system (online)1. DBMS centric design automates discovery, access, management2. Object relational databases enable
Automate access to data so that the NASA 500, Global Change 10,000 and Internet 20,000,000 can use system.
Cache popular results, not all results (saves 3x or more) Compute on demand (saves lots of storage and cpu).
Emphasize pull processing rather than push processing.Use parallelism to get scaleup.
Do Batch as a data pump
3 Be Smart Shoppers: Use COTS hardware/software (saves 400M$)
Just-in-time acquisition (saves 400M$)Use workstation not mainframe technology (gives 10x more stuff)Depreciate over 3 years (ends in 2007 with "fresh" equipment)
4. 2 + N node architecture 2 Super DAACs for fault tolerance and for growth.
Unify the 2 "big" data storage centers with 2 big data analysis centers.Allow many “little” peer-DAACs at science/user groups
Jim Gray
18
Use COTS hardware/software (saves 400M$)
Defense contractors want to build (and maintain) stuff.(they do it for the money)
Fund SQL* (SQL-2007): Object-Relational (extensible)
supports Global Change data types
Automates access
Reliable storage
Tertiary storage
Parallel data search (automatic)
Workflow (job control)
Reliable
Fund Operations software companies (Tivoli...)
Jim Gray
19
Use workstation technology (NOW)Use workstation hardware technology,
not Super Computers
0.5$/MB of disk vs 30$/MB of disk
100$/MIPS vs 18,000$/MIPS
3k$/tape drive vs 50k$/tape drive
Processor, Disk, Tape ARRAYS: connected by ATM
a NOW
Gives 10x (?100x) more stuff for same dollars
Allows ad hoc query load
Allows a scaleable design
Allows same hardware: SuperDAACs = PeerDAACs
Jim Gray
20
Use workstation technology (NOW)Study used RS/6000 and DEC 7000 as workstation
(they are 100k$/slice).
Should have used Compaq.
Price for 20GFlop, 24 TB disk, 2PB tape TODAY
Compaq/DLT prices computed by Gray.10% Peer DAAC costs 3M$ today, 1% Micro DAAC (200TB) costs 300K$
Type ofplatform
Maxnumberof daysto readarchive
Numberof dataservers
Numberof
compute
servers
Numberof taperobots
Dataserver
cost($M)
Diskcachecost($M)
Archive tapecost($M)
Computeplatform
cost($M)
Totalhardware
cost ($M)
WS/NTP 27.7 18 106 8 $29.5 $31.5 $12.8 $55.7 $129.5
Vector/NTP 27.7 2 4 8 $31.0 $31.5 $12.8 $128.0 $203.3
Compaq/dlt 1 100 200 1000 $4 $12 $6 $8 $30
Jim Gray
21
Just-in-time acquisition (saves 400M$)Hardware prices decline 20%-40%/year
So buy at last moment
Buy best product that day: commodity
Depreciate over 3 years so that facility is fresh. (after 3 years, cost is 23% of original). 60% decline peaks at 10M$
1996
EOS DIS Disk Storage Size and Cost
1994 1998 2000 2002 2004 2006 2008
Storage Cost M$
Data Need TB
1
10
10
10
10
10
2
3
4
5 (assume 40% price decline/year and 10% on disk.)
Jim Gray
22
What California Proposed0. Design for success: expect that millions will use the system (online)1. DBMS centric design automates discovery, access, management2. Object relational databases enable
Automate access to data so that the NASA 500, Global Change 10,000 and Internet 20,000,000 can use system.
Cache popular results, not all results (saves 3x or more) Compute on demand (saves lots of storage and cpu).
Emphasize pull processing rather than push processing.Use parallelism to get scaleup.
Do Batch as a data pump
3 Be Smart Shoppers: Use COTS hardware/software (saves 400M$)
Just-in-time acquisition (saves 400M$)Use workstation not mainframe technology (gives 10x more stuff)Depreciate over 3 years (ends in 2007 with "fresh" equipment)
4. 2 + N node architecture 2 Super DAACs for fault tolerance and for growth.
Unify the 2 "big" data storage centers with 2 big data analysis centers.Allow many “little” peer-DAACs at science/user groups
Jim Gray
23
2+N DAAC architecture2 Super-DAACs Have 2 BIG sites which
Each store ALL the data (back each other up)
no other way to archive these 15 PB databases
Each service 1/2 the queries and run a data pump
Each produces 1/2 the standard data products
Each has a BIG MIP farm next to the Byte farm (a SCF science computation facility).
N Peer-DAACs
Each stores part of the data (got from a super DAAC)
Can be NASA sponsored or private.
Same software and hardware as Super-DAACs
Super-DAACs are “banks”, Peer-DAACs are “pubs” careful anything
goes
Jim Gray
24
Minimize Operations Costs
Reduced sites (DAACs) have reduced costs
Use Mosaic, Email, Telephone user support model
Count on vendors to provide:
Network management (NetView & SMTP)
Data replication
Application software version control
Workflow control
Help desk software
More reliable hardware/software
Jim Gray
25
Unify data storage centers with data analysisData analysis (Science Computation Facilities)
need quick & high bandwidth access to DB.
WAN technology is good but not that good.
WAN technology is not free.
=> Co-Locate DAACs and SCFs.
=> two super SCFs, many peer SCFs.
Instrument teams often find a bug or new algorithm
=> reprocess all the base data to make new data set.
=> ripple effect to data consumers
=> must track data lineage.
Jim Gray
26
BudgetWe had a VERY difficult time discovering a budget.
So we did our own.
It was less.
Big savings in operations and development
Hardware savings could give bigger DAACsHughes Sequoia
COTS 108 52Development 207 50Operations 260 120Other 193 100total 766SCFs 312 DAACs 158 SuperTotal 1236
0
100
200
300
400
500
600
700
800
Hughes Sequoia
COTS
Operations
Development
Other
10-year costs
Jim Gray
27
What California Proposed0. Design for success: expect that millions will use the system (online)1. DBMS centric design automates discovery, access, management2. Object relational databases enable
Automate access to data so that the NASA 500, Global Change 10,000 and Internet 20,000,000 can use system.
Cache popular results, not all results (saves 3x or more) Compute on demand (saves lots of storage and cpu).
Emphasize pull processing rather than push processing.Use parallelism to get scaleup.
Do Batch as a data pump
3 Be Smart Shoppers: Use COTS hardware/software (saves 400M$)
Just-in-time acquisition (saves 400M$)Use workstation not mainframe technology (gives 10x more stuff)Depreciate over 3 years (ends in 2007 with "fresh" equipment)
4. 2 + N node architecture 2 Super DAACs for fault tolerance and for growth.
Unify the 2 "big" data storage centers with 2 big data analysis centers.Allow many “little” peer-DAACs at science/user groups
Jim Gray
28
Challenging Problems
Design the Global Change Schema
Understand data lineage
Build discovery, analysis, visualization tools
Build an OR DBMS Including distributed,
parallel, workflowlazy-eager evaluationtertiary storage, SQLworkflow
Build a decent & reliable HSM
Build a way to operate a 1,000 node NOW.