Title: Reliable%20and%20Efficient%20%20%20Grid%20Data%20Placement%20using%20Stork%20and%20DiskRouter
1Reliable and Efficient Grid Data Placement
using Stork and DiskRouter
Tevfik Kosar University of Wisconsin-Madison kosa
rt_at_cs.wisc.edu April 15th, 2004
2A Single Project..
- LHC (Large Hadron Collider)
- Comes online in 2006
- Will produce 1 Exabyte data by 2012
- Accessed by 2000 physicists, 150 institutions,
30 countries
3And Many Others..
- Genomic information processing applications
- Biomedical Informatics Research Network (BIRN)
applications - Cosmology applications (MADCAP)
- Methods for modeling large molecular systems
- Coupled climate modeling applications
- Real-time observatories, applications, and
data-management (ROADNet)
4The Same Big Problem..
- Need for data placement
- Locate the data
- Send data to processing sites
- Share the results with other sites
- Allocate and de-allocate storage
- Clean-up everything
- Do these reliably and efficiently
5Outline
- Introduction
- Stork
- DiskRouter
- Case Studies
- Conclusions
6Stork
- A scheduler for data placement activities in the
Grid - What Condor is for computational jobs, Stork is
for data placement - Stork comes with a new concept
- Make data placement a first class citizen in the
Grid.
7The Concept
8The Concept
9The Concept
Condor Job Queue
DaP A A.submit DaP B B.submit Job C
C.submit .. Parent A child B Parent B child
C Parent C child D, E ..
DAG specification
C
DAGMan
Stork Job Queue
C
E
10Why Stork?
- Stork understands the characteristics and
semantics of data placement jobs. - Can make smart scheduling decisions, for reliable
and efficient data placement.
11Failure Recovery and Efficient Resource
Utilization
- Fault tolerance
- Just submit a bunch of data placement jobs, and
then go away.. - Control number of concurrent transfers from/to
any storage system - Prevents overloading
- Space allocation and De-allocations
- Make sure space is available
12Support for Heterogeneity
Protocol translation using Stork memory buffer.
13Support for Heterogeneity
Protocol translation using Stork Disk Cache.
14Flexible Job Representation and Multilevel Policy
Support
-
- Type Transfer
- Src_Url srb//ghidorac.sdsc.edu/kosart.cond
or/x.dat - Dest_Url nest//turkey.cs.wisc.edu/kosart/x
.dat -
-
- Max_Retry 10
- Restart_in 2 hours
-
-
15Run-time Adaptation
- Dynamic protocol selection
-
- dap_type transfer
- src_url drouter//slic04.sdsc.edu/tmp/tes
t.dat - dest_url drouter//quest2.ncsa.uiuc.edu/tmp
/test.dat - alt_protocols nest-nest, gsiftp-gsiftp
-
-
- dap_type transfer
- src_url any//slic04.sdsc.edu/tmp/test.da
t - dest_url any//quest2.ncsa.uiuc.edu/tmp/tes
t.dat -
16Run-time Adaptation
- Run-time Protocol Auto-tuning
-
- link slic04.sdsc.edu quest2.ncsa.uiuc.edu
- protocol gsiftp
- bs 1024KB //block size
- tcp_bs 1024KB //TCP buffer size
- p 4
17Outline
- Introduction
- Stork
- DiskRouter
- Case Studies
- Conclusions
18DiskRouter
- A mechanism for high performance, large scale
data transfers - Uses hierarchical buffering to aid in large scale
data transfers - Enables application-level overlay network for
maximizing bandwidth - Supports application-level multicast
19Store and Forward
C
A
With DiskRouter
DiskRouter
B
Without DiskRouter
Improves performance when bandwidth fluctuation
between A and B is independent of the bandwidth
fluctuation between B and C
20DiskRouter Overlay Network
90 Mb/s
B
A
21DiskRouter Overlay Network
90 Mb/s
B
A
400 Mb/s
400 Mb/s
DiskRouter
C
Add a DiskRouter Node C which is not necessarily
on the path from A to B, to enforce use of an
alternative path.
22Data Mover/Distributed Cache
Source
Destination
DiskRouter Cloud
- Source writes to the closest DiskRouter and
Destination receives it up from its closest
DiskRouter
23Outline
- Introduction
- Stork
- DiskRouter
- Case Studies
- Conclusions
24Case Study I SRB-UniTree Data Pipeline
- Transfer 3 TB of DPOSS data from SRB _at_SDSC to
UniTree _at_NCSA - A data pipeline created with Stork and DiskRouter
25Failure Recovery
Diskrouter reconfigured and restarted
UniTree not responding
SDSC cache reboot UW CS Network outage
Software problem
26Case Study -II
27Dynamic Protocol Selection
28Runtime Adaptation
- Before Tuning
- parallelism 1
- block_size 1 MB
- tcp_bs 64 KB
- After Tuning
- parallelism 4
- block_size 1 MB
- tcp_bs 256 KB
29Conclusions
- Regard data placement as first class citizen.
- Introduce a specialized scheduler for data
placement. - Introduce a high performance data transfer tool.
- End-to-end automation, fault tolerance, run-time
adaptation, multilevel policy support, reliable
and efficient transfers.
30Future work
- Enhanced interaction between Stork, DiskRouter
and higher level planners - co-scheduling of CPU and I/O
- Enhanced authentication mechanisms
- More run-time adaptation
31You dont have to FedEx your data anymore.. We
deliver it for you!
- For more information
- Stork
- Tevfik Kosar
- Email kosart_at_cs.wisc.edu
- http//www.cs.wisc.edu/condor/stork
- DiskRouter
- George Kola
- Email kola_at_cs.wisc.edu
- http//www.cs.wisc.edu/condor/diskrouter