CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara...

23
CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011

Transcript of CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara...

Page 1: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

CS 414 - Spring 2011

CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3)

Klara Nahrstedt

Spring 2011

Page 2: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Administrative MP3 – posted today

CS 414 - Spring 2011

Page 3: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Some Interesting Facts

DBMS2.com Source (May 2009)Facebook had 400 terabytes of disks managed by

Hadoop/Hive with an approx. 6:1 compression ratioFacebook’s Hadoop/Hive system ingests 15

terabytes of new data per dayFacebook had 610 Hadoop nodes (in May 2009)

running in a single cluster and was heading for 1000 Yahoo had 2000 nodes (in May 2009) and was heading for

4000

CS 414 - Spring 2011

Page 4: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Some Interesting Facts Source: www.slideshare.net (March 2011) Current data sets:

NYSE: 8PB; Google > 12PB; Data Volumes:

NYSE: 1.5 TB daily; Facebook: 350 M users; 3.5B shared items/weekFacebook adds > 100K users, 55M ‘status’

updates, 80M photos daily

CS 414 - Spring 2011

Page 5: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Outline Disk Scheduling

SCAN-EDF Group Sweeping Mixed Scheduling

Admission Control File System Metadata/Indexing Block Size Issues

CS 414 - Spring 2011

Page 6: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Disk Scheduling Policies Goal of Scheduling in Traditional Disk

Management Reduce cost of seek time Achieve high throughput Provide fair disk access

Goal of Scheduling in Multimedia Disk Management Meet deadline of all time-critical tasks Keep necessary buffer requirements low Serve many streams concurrently Find balance between time constraints and efficiency

CS 414 - Spring 2011

Page 7: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

EDF (Earliest Deadline First) Disk Scheduling Each disk block request is tagged with

deadline Policy:

Schedule disk block request with earliest deadline

Excessive seek time – high overheadPure EDF must be adapted or combined with

file system strategies

CS 414 - Spring 2011

Page 8: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

EDF Example

CS 414 - Spring 2011

Note: Consider that block number Implicitly encapsulates the disk track number

Page 9: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

SCAN-EDF Scheduling Algorithm Combination of SCAN and EDF algorithms Each disk block request tagged with

augmented deadline Add to each deadline perturbation

Policy: SCAN-EDF chooses the earliest deadline If requests with same deadline, then choose

request according to scan direction

CS 414 - Spring 2011

Page 10: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Implementation of SCAN-EDF Notation:

Di be deadline of disk block request ‘i’

Ni be track (block) position on disk

Nmax be maximum number of disk tracks

Deadline Modification: Di + f(Ni)

f(Ni) converts track number of ‘i’ into a small perturbation of deadline

Perturbation small enough so that Di + f(Ni) ≤ Dj + f(Nj) for Di ≤ Dj

Possible f(Ni) = Ni/Nmax

CS 414 - Spring 2011

Page 11: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

SCAN EDF Example (Nmax = 100)

CS 414 - Spring 2011

Page 12: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Enhanced SCAN-EDF (1) Use more accurate perturbation of deadline Consider

Actual track position of disk head ‘N’ Nmax – max number of disk tracks

Ni – next track to be considered

CS 414 - Spring 2011

Head Moves Upwards

Page 13: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Enhanced SCAN-EDF (2) Algorithm:

If head moves upwards (towards Nmax), then

(a)

(b)

CS 414 - Spring 2011

maxmax )(,;

N

NNNfNNNN iiii

max

max)(,1;N

NNNfNNN iiii

Page 14: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Enhanced SCAN-EDF (3) If head moves downwards (towards 1), then

(a)

(b)

CS 414 - Spring 2011

maxmax )(:;

N

NNfNNNN iiii

max

)(:1;N

NNNfNNN iiii

Page 15: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Group Sweeping Algorithms

Policy: Each Request consists of (Deadline, Block Number

)Disk Block Requests served in cycles In one cycle, requests divided into groups

according to similar deadlinesWithin group use SCANAs we retrieve blocks, we may need smoothing

buffers to ensure continuity

CS 414 - Spring 2011

Page 16: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Group Sweeping Example

CS 414 - Spring 2011

Page 17: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Mixed Scheduling (uses SSTF – Shortest Seek Time First)

CS 414 - Spring 2011

Example of SSTF

Page 18: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Mixed Scheduling

CS 414 - Spring 2011

SSTF (Shortest Seek Time First) + Balanced Strategy

Page 19: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Admission Control

CS 414 - Spring 2011

Client 1 retrieves K1 blocks in oneround

Client 2 retrievesK2 blocks

Client 3 retrievesK3 blocks

Client 4 retrieves K4 blocks

Server

Page 20: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Admission Control Disk block requests are timed

Media server must determine admit a stream serve (schedule) a stream without having negative effect on

other streams already serviced.

Deterministic Guarantees Admission control considers worst case scenario when admitting

new stream Constrained Disk Placement Example: M - size of blocks, G –

size of gabs, rdt – data transfer of disk

CS 414 - Spring 2011

)/(sec

)(sec)(sec

storsr

torsGtorsMT

dtplay

Page 21: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Admission Control

CS 414 - Spring 2011

)/)((min)( ipl

iii

i

RK

α – overhead switching from one round (‘j-1’)to another round (j), and then transmitting the first block of the ‘j’ round

β – transmission time of (Ki-1) blocks in ‘j’ round, i=1,..4Ki – number of blocks retrieved by client ‘i’ ηi – Block granularity retrieved for client ‘i’ (e.g., in Bytes)Ri – playback rates of client ‘i’ (e.g., in Bytes per second)

Minimal Intra- Ki blocks delay Cost to switch and move Ki blocks

Page 22: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Admission Control

Statistical GuaranteesDeadlines are guaranteed with certain

probabilityAdmission control considers statistical

behavior of the disk system while admitting new stream (average performance)

Best effort ServiceNo guarantees

CS 414 - Spring 2011

Page 23: CS 414 - Spring 2011 CS 414 – Multimedia Systems Design Lecture 27 – Media Server (Part 3) Klara Nahrstedt Spring 2011.

Conclusion

The data placement, scheduling, are very important for any media server design and implementation.

Still need to consider multimedia file system and caching – next lecture

CS 414 - Spring 2011