Mesh Testing: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
(Minor tweaks.) |
||
Line 3: | Line 3: | ||
Setup: |
Setup: |
||
* Start with ten machines, keep adding ten |
* Start with ten machines, keep adding ten at a time while it is useful to do so. |
||
Measurements to make during each test: |
Measurements to make during each test (in addition to workload-specific measurements): |
||
* Spectrum utilization -- |
* Spectrum utilization -- as measured w/ spectrum analyzer and/or from wireshark |
||
** Wireshark may be able to break down bandwidth by packet type |
|||
* Remaining bandwidth -- attempt to download a large file on one machine during test, record time taken. |
* Remaining bandwidth -- attempt to download a large file on one machine during test, record time taken or bandwidth achieved. |
||
* Total # of laptops seen on mesh view on all numbers (should be n^2). |
* Total # of laptops seen on mesh view on all numbers (should be n^2). |
||
Line 14: | Line 15: | ||
# Idle load. |
# Idle load. |
||
# Every machine coming out of suspend. |
# Every machine coming out of suspend (or booting). |
||
# Every machine trying to register with school server -- Number of machines that failed the first attempt, failed second attempt, etc. |
# Every machine trying to register with school server -- Number of machines that failed the first attempt, failed second attempt, etc. |
||
# Ricardo's web spider |
# Ricardo's web spider at various rates of download (download 1k page/second, etc) |
||
# Read -- if one laptop shares a PDF, how many laptops fail to retrieve it? |
# Read -- if one laptop shares a PDF, how many laptops fail to retrieve it? |
||
# Distance -- binary success/fail. Are there other metrics? |
|||
# Distance |
|||
# Write -- automate pressing |
# Write -- automate pressing N characters a second for small values of N, look at received rate/update time, increase number of participants per document. |
||
# olpc-update -- number of machines upgraded in 1 hour |
# olpc-update -- number of machines upgraded in 1 hour |
||
Line 26: | Line 27: | ||
* Set mesh ttl to 1 for every packet |
* Set mesh ttl to 1 for every packet |
||
* Change bcast/mcast rate on every node |
* Change bcast/mcast rate on every node |
||
* Jim's Avahi config 30% |
* Jim's Avahi config 30% fixes? |
||
* Presence: Benchmark bandwidth use of Avahi vs. Cerebro vs. no presence? |
* Presence: Benchmark bandwidth use of Avahi vs. Cerebro vs. no presence? |
||
* Collaboration: Benchmark switching from multicast to unicast? |
* Collaboration: Benchmark switching from multicast to unicast? |
||
* Suspend/resume: Off vs. on, wake-on-unicast vs. wake-on-multicast |
* Suspend/resume: Off vs. on, wake-on-unicast vs. wake-on-multicast |
||
* Block multicast in route table (are there other sources of multicast packets other than the above) |
|||
* Are there other mesh parameters to tweak? Path request timeout, for example. |
Revision as of 21:37, 21 February 2008
This page describes the network testing that will be performed on Monday Feb 25th at 1cc.
Setup:
- Start with ten machines, keep adding ten at a time while it is useful to do so.
Measurements to make during each test (in addition to workload-specific measurements):
- Spectrum utilization -- as measured w/ spectrum analyzer and/or from wireshark
- Wireshark may be able to break down bandwidth by packet type
- Remaining bandwidth -- attempt to download a large file on one machine during test, record time taken or bandwidth achieved.
- Total # of laptops seen on mesh view on all numbers (should be n^2).
Workloads -- tests to perform, along with their quantitative metrics:
- Idle load.
- Every machine coming out of suspend (or booting).
- Every machine trying to register with school server -- Number of machines that failed the first attempt, failed second attempt, etc.
- Ricardo's web spider at various rates of download (download 1k page/second, etc)
- Read -- if one laptop shares a PDF, how many laptops fail to retrieve it?
- Distance -- binary success/fail. Are there other metrics?
- Write -- automate pressing N characters a second for small values of N, look at received rate/update time, increase number of participants per document.
- olpc-update -- number of machines upgraded in 1 hour
Variables to investigate:
- Set mesh ttl to 1 for every packet
- Change bcast/mcast rate on every node
- Jim's Avahi config 30% fixes?
- Presence: Benchmark bandwidth use of Avahi vs. Cerebro vs. no presence?
- Collaboration: Benchmark switching from multicast to unicast?
- Suspend/resume: Off vs. on, wake-on-unicast vs. wake-on-multicast
- Block multicast in route table (are there other sources of multicast packets other than the above)
- Are there other mesh parameters to tweak? Path request timeout, for example.