Open Bug 697075 Opened 14 years ago Updated 3 years ago

Telemetry: Determine typical bandwidth/RTT available to necko

Categories

(Core :: Networking: Cache, defect, P5)

Product:
Core
Component:
Networking: Cache
Type:
defect

Tracking

()

People

(Reporter: bjarne, Unassigned)

Details

(Whiteboard: [necko-would-take])

A natural extension to the cache microbenchmark is to load resources from a throttled server to simulate slow networks and study cache-behaviour under such conditions. In order to do this we need an idea of the network-performance seen by users. I briefly talked to Patrick and he thinks we don't measure this, moreover he suggests to also measure RTT while we're at it. Of-course, this also leaves us with two related values to report but I'm not sure how to deal with it in this case. We might be able to model network performance as a simple ax+b (or maybe we need more details - Patrick..?), define a discrete set of expected a's and b's and build a histogram for this set.
Whiteboard: [necko-would-take]
Bulk change to priority: https://bugzilla.mozilla.org/show_bug.cgi?id=1399258
Priority: -- → P5
Severity: normal → S3
You need to log in before you can comment on or make changes to this bug.