PerformanceRobust Parallel IO - PowerPoint PPT Presentation
1 / 16
Title:
PerformanceRobust Parallel IO
Description:
Graduated Declustering (GD): a Virtual Streams ... Evaluation of original GD implementation: progress-based ... Proposed solution: response-rate-based GD ... – PowerPoint PPT presentation
Number of Views:46
Avg rating:3.0/5.0
Title: PerformanceRobust Parallel IO
1
Performance-Robust Parallel I/O
Virtual Streams
- Z. Morley Mao, Noah Treuhaft
- CS258
- 5/17/99
- Professor Culler
2
Introduction
- Clusters exhibit performance heterogeneity
- static dynamic, due to both hardware and
software - Consistent peak performance demands adaptive
software - building performance-robust parallel software
means keeping heterogeneity in mind - This work explores
- adaptivity appropriate for I/O-bound parallel
programs - how to provide that adaptivity
3
Heterogeneity demands adaptivity
Cluster Node
...
- Physical I/O streams are simple to build and use
- But their performance is highly variable
- different drive models, bad blocks, multizone
behavior, file layout, competing programs, host
bottlenecks - I/O-bound parallel programs run at rate of
slowest disk
4
Virtual Streams
- Performance-robust programs want virtual streams
that... - eliminate dependence on individual disk behavior
- continually equalize throughput delivered to
processes
Virtual Streams Layer
Disk
5
Graduated Declustering (GD) a Virtual Streams
implementation
- data replicated (mirrored) for availability
- use replicas to provide performance availability,
too - fast network makes remote disk access comparable
to local - distributed algorithm for adaptivity
- client provides information about its progress
- server reacts by scheduling requests to even out
progress
client A
client B
Process
GD server
GD client library
server
server
B
A
6
GD in action
- Local decisions yield global behavior
7
Evaluation of original GD implementation
progress-based
- Seek overhead due to reading from all replicas
8
Deficiency of original GD implementation seek
overhead
- Under the assumption of sequential data access
- Seek occurs even when there is no perturbation
- seeks are becoming more significant as disk
transfer rate increases - Need a new algorithm, that ...
- reads mostly from a single disk under no
perturbation - dynamically adjusts to perturbation when
necessary - achieves both performance adaptivity and minimal
overhead
9
Proposed solution response-rate-based GD
- Number of requests clients send to server based
on server response rate - servers use request queue lengths to make
scheduling decisions - uses implicit information, historyless
- no bandwidth information transmitted between
server and client - advantage each client has a primary server
10
Evaluation of response-rate-based GD
- Graph of bandwidth vs. disk nodes perturbed
11
Historyless vs. History-based adaptiveness
- History-based (progress based)
- Adjustment to perturbation occurs gradually over
time - Close to perfect knowledge, if the information
not outdated - extra overhead in sending control information
- Historyless (response-rate based)
- primary server designation possible
- to increase sensitivity to real perturbation by
creating artificial perturbation - considers varying performance of data consumers
- takes longer to converge
12
Stability and Convergence
- How long does it take for the system to converge?
- Linear with the number of nodes
- Depends on the last occurrence of perturbation
- Influenced by the style of communication
(implicit vs. explicit)
13
Server request handoff
- If a server finishes all its requests, it will
contact other servers with the same replicas to
help serve their clients (workstealing) - server request handoff keeps all disks busy when
possible - design decisions?
- How many requests to handoff? Depending on the BW
history of both servers, depending on the size of
request queue. - Benefit vs. Cost tradeoff
14
Writes
- Identical to reads except...
- Create incomplete replicas with holes
- track holes in metadata
- afterward, do hole-filling both for
availability and for performance robustness
15
Conclusions
- What did we achieve?
- New load balancing algorithm--response-rate based
- Deliver equal BW to parallel-program processes in
face of performance heterogeneity - demonstrate the stability of the system
- reduce seek overhead
- server request handoff
- writes
- creates a useful abstraction for steaming I/O in
clusters
16
Future Work
- Future work
- hot file replication
- get peak BW after perturbation ceases
- achieve orderly replies
- multiple disks abstraction
Recommended
CrystalGraphics Presentations
