The presentation introduces the Web Liquid Streams (WLS) framework. WLS lets developers create distributed topologies across a pool of heterogeneous devices thanks to the abstraction offered by JavaScript, the lingua franca of the Web. Through a set of use case scenarios we show the feasibility of the approach.

1. Decentralized Stream Processing
over Web-enabled devices
Masiar Babazadeh
@masiarb
Andrea Gallidabino
@agallidabino
Cesare Pautasso
@pautasso
University of Lugano (USI)
Faculty of Informatics
Switzerland
name.surname@usi.ch
1

2. 2
Tessel Arduino
Raspberry PiSmartphones

3. 3

4. 4

5. 4

6. 5 5

7. 6

8. 7
Stream
Processing
1

9. 8
Heterogeneous
Hardware
2

10. 9
Dynamic
Environment
3

11. 10
Web Liquid 1

12. 11
Web 2

13. 12
2Web

14. 13
3Web

15. Web
14
3

16. Web
14
3

17. Web
14
3

18. 15
Consumer
checkup.js
Consumer
viz.js
Producer
temp.js
Consumer
fan.js
Filter
filter.js
Web Liquid Streams

19. 16
F
Operator Elasticity

20. 16
F
Operator Elasticity

21. 16
F
Operator Elasticity

22. 16
F
Operator Elasticity

23. 16
F
Operator Elasticity

24. 16
F
Operator Elasticity

25. 16
F
Operator Elasticity

26. 17
var k = require('wls.js');
setInterval(function(){
getTemperature(
function(temp, sensor_id){
k.send({
"temperature" : temp,
"id" : sensor_id,
"ts" : new Date().getTime(),
});
}
);
}, 1000);
Producer

27. 17
var k = require('wls.js');
setInterval(function(){
getTemperature(
function(temp, sensor_id){
k.send({
"temperature" : temp,
"id" : sensor_id,
"ts" : new Date().getTime(),
});
}
);
}, 1000);
Producer

28. 17
var k = require('wls.js');
setInterval(function(){
getTemperature(
function(temp, sensor_id){
k.send({
"temperature" : temp,
"id" : sensor_id,
"ts" : new Date().getTime(),
});
}
);
}, 1000);
Producer

29. 17
var k = require('wls.js');
setInterval(function(){
getTemperature(
function(temp, sensor_id){
k.send({
"temperature" : temp,
"id" : sensor_id,
"ts" : new Date().getTime(),
});
}
);
}, 1000);
Producer

30. var k = require(’wls.js’);
k.createOperator(function(msg) {
var setpoint = k.db_get("setpoint", temp_data.id);
var threshold = k.db_get("threshold",
temp_data.id);
//[...] compute average
if(abs(average - setpoint) > threshold){
k.send({
"start" : true,
"room_id" : temp_data.id
});
}
else //[...]
});
18 Filter

31. var k = require(’wls.js’);
k.createOperator(function(msg) {
var setpoint = k.db_get("setpoint", temp_data.id);
var threshold = k.db_get("threshold",
temp_data.id);
//[...] compute average
if(abs(average - setpoint) > threshold){
k.send({
"start" : true,
"room_id" : temp_data.id
});
}
else //[...]
});
18 Filter

32. var k = require(’wls.js’);
k.createOperator(function(msg) {
var setpoint = k.db_get("setpoint", temp_data.id);
var threshold = k.db_get("threshold",
temp_data.id);
//[...] compute average
if(abs(average - setpoint) > threshold){
k.send({
"start" : true,
"room_id" : temp_data.id
});
}
else //[...]
});
18 Filter

33. var k = require(’wls.js’);
k.createOperator(function(msg) {
var setpoint = k.db_get("setpoint", temp_data.id);
var threshold = k.db_get("threshold",
temp_data.id);
//[...] compute average
if(abs(average - setpoint) > threshold){
k.send({
"start" : true,
"room_id" : temp_data.id
});
}
else //[...]
});
18 Filter

34. var k = require(’wls.js’);
k.createOperator(function(msg) {
if(this.id == msg.id){
if(msg.start){
startFan();
}
else {
stopFan();
}
}
});
19 Consumer

35. var k = require(’wls.js’);
k.createOperator(function(msg) {
if(this.id == msg.id){
if(msg.start){
startFan();
}
else {
stopFan();
}
}
});
19 Consumer

36. 20
{
topology : {
id : “HAS_topology”,
operators : [
{
id : “producer”,
script : “temp.js”,
constraints : [“temperature”],
},
…
],
bindings : [
{
from : “producer”,
to : [“filter”, “web_consumer_1”]
},
…
]
}
}
Producer
temp.js
JSON Topology

37. 21
Web Liquid Streams Runtime

38. 22
Node.js
Operator
wls.js Peer (Server)
Receiver Sender
ZeroMQ
WebSockets
Web Server Runtime

39. 23
Web Browser
Operator
wls.js Peer (HTML)
Receiver
Sender
WebRTC
WebSockets
Dispatcher
Main Thread Web Workers
Web Browser Runtime

40. 24

41. 25
P F C
Negative Filter
Variable Workload

42. 26
Raspberry Pi
1 core 700MHz
256MB RAM
NodeJS v.0.10.15
MacBook Pro (2012)
4 cores 2.3GHz
16GB RAM
Chrome v. 37
iPhone 5S
1 core 1.3GHz
1 GB RAM
Chrome v. 40
Variable Workload

43. 27
Variable Workload

44. 28
P F C
Triple DES
Variable Workload

45. 29
MacBook Pro (2012)
4 cores 2.3GHz
16GB RAM
NodeJS v. 0.10.15
Web Server (Ubuntu)
24 cores 2GHz
128GB RAM
NodeJS v. 0.10.15
Web Server (Ubuntu)
4 cores 3GHz
8GB RAM
NodeJS v. 0.10.15
Variable Workload

46. 30
Variable Workload

47. 31
VS.
Centralised vs. P2P

48. 32
P F C
Prime Numbers
Centralised vs. P2P

49. 33
P F C
Single WLS Peer
Web Server (Ubuntu)
24 cores 2GHz
128GB RAM
NodeJS v. 0.10.15
Centralised

50. 34
MacBook Pro (2012)
4 cores 2.3GHz
16GB RAM
Chrome v. 37
P CFFFF
Centralised vs.

51. 35
Centralised vs. P2P

52. 36
End-to-endLatency(sec)
Centralised vs. P2P

53. 37
WEB LIQUID STREAMS

54. 37
WEB LIQUID STREAMS

55. 37
WEB LIQUID STREAMS

56. 37
WEB LIQUID STREAMS

57. 38
Decentralized Stream Processing
over Web-enabled devices
Masiar Babazadeh
@masiarb
Andrea Gallidabino
@agallidabino
Cesare Pautasso
@pautasso
University of Lugano
Faculty of Informatics
Switzerland
name.surname@usi.ch
38Thank you.