Version 2 (modified by 19 years ago) ( diff ) | ,
---|
Design Noteds for nodehandler
Underlying model
- Broadcast nodehandler broadcasts each command to all the nodes using a C program
System Parameters
- Underlying traffic model: Figure out
- how many packets
- of what size
- and with what interarrival
are generated by a "typical" experiment script
- For this traffic model, test the performance in terms of packet loss, and avg. latency
Building reliability into the protocol
Some thoughts on building reliability into the protocol
- Cumulative ACK by nodeagent every 5 packets
- Stagger sending of ACK's to reduce the collision domains based on
N* backoff interval, where N = row no.
- nodehandler separate thread maintains a bitmap for all packets and fills a "one" for every missing packet reported by the nodeagent
- nodehandler broadcasts these missing packets after a timeout
- This timeout is based on the time taken by all nodes to send an ACK to the nodehandler using the convention of Step 2
Fetching OML xml schema
- Replacet existing ruby webserver with proper Apache to serve xml files
- nodeagents still use wget to fetch these
Attachments (9)
- num-pkts-lost.png (4.4 KB ) - added by 19 years ago.
- num-pkts-recvd.png (4.5 KB ) - added by 19 years ago.
- num-pkts-lost.2.png (4.5 KB ) - added by 19 years ago.
- num-pkts-recvd.2.png (4.7 KB ) - added by 19 years ago.
- num-pkts-lost.3.png (4.6 KB ) - added by 19 years ago.
- num-pkts-recvd.3.png (4.7 KB ) - added by 19 years ago.
- total-time.png (5.0 KB ) - added by 19 years ago.
- total-time.2.png (4.1 KB ) - added by 19 years ago.
- total-time.3.png (4.0 KB ) - added by 19 years ago.
Download all attachments as: .zip
Note:
See TracWiki
for help on using the wiki.