Changes between Version 94 and Version 95 of benchmarks

Show
Ignore:
Timestamp:
11/24/11 10:19:22 (12 years ago)
Author:
bartek
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • benchmarks

    v94 v95  
    213213 
    214214=== Test 3 - Subscribing === 
     215The aim of the third benchmark was the comparison of the times of creating subscriptions in the tested systems.  
     216In the Subscribing test, a lightweight Subscriber program created the same number of the same subscriptions in each system. Similarly to the previous tests, the time, which was measured by the Subscriber program, covered a bunch of invokes of a single Subscribe operation. 
     217 
     218==== Main facts ==== 
     219* Scenario's draft: Subscriber -> Notification Broker 
     220* Time measurement: by Subscriber 
     221* Filtering based on: topics 
     222* Subscription dialect: Simple 
     223* SubscribeRequest payload: about 300 bytes 
     224* SubscribeResponse payload: about 280 bytes 
     225* Number of Subscribe operations in one bunch: 100 
     226 
     227==== Notes ==== 
     228 
     229''Pros:'' 
     230* Possibility to compare the time of creating subscriptions in the tested systems. 
     231 
     232''Cons:'' 
     233* Only one Subscriber program. 
     234* The notification services in a default configuration; no other operations invoked while subscribing - poorly realistic scenario. 
     235 
     236==== Results ==== 
     237[[Image(test-3.png, center, width=340px)]] 
     238 
     239 
    215240 
    216241[=#n]