1) The document presents FlexACMS, a framework that automatically configures monitoring slices when cloud slices are created in cloud platforms. It enhances FlexACMS with dynamic task attribution to monitoring servers and load balancing.
2) An evaluation shows the enhanced FlexACMS reduces response time by up to 60% compared to the previous version. Scalability tests show response time is mostly affected by the number of metrics and monitoring slices, not the number of existing cloud slices.
3) The automatic configuration of multiple monitoring solutions via FlexACMS is feasible and can help administrators achieve monitoring needs when solutions are not integrated with cloud platforms. Future work includes improving load balancing and supporting additional cloud models.
Efficient Configuration of Monitoring Slices for Cloud Administrators
1. 1/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Efficient Configuration of Monitoring Slices for
Cloud Platform Administrators
M´arcio Barbosa de Carvalho, Rafael Pereira Esteves, Guilherme da Cunha
Rodrigues, Clarissa Cassales Marquezan (2), Lisandro Zambenedetti Granville,
Liane Margarida Rockenbach Tarouco
Institute of Informatics – Federal University of Rio Grande do Sul – Brazil
(2) Paluno, University of Duisburg-Essen, Germany
19th IEEE Symposium on Computer and Communications
June 24th, 2014
2. 2/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Outline
1 Introduction
2 FlexACMS
New architecture
3 Evaluation
Comparative
Scalability
4 Conclusions and future work
3. 3/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Introduction
Motivation
Cloud providers grant computational resources (e.g., compute,
storage, network) to cloud users in form of cloud slices
Cloud slices must be closely monitored by the cloud provider
to avoid wasting expensive physical resources while still
satisfying the cloud users expectations
A single monitoring solution does not address all cloud
monitoring requirements, which imposes to cloud
administrators the utilization of multiple monitoring solutions
Once a cloud slice is created, a set of monitoring solutions
must be configured in order to start monitoring the computing
resources that form the new cloud slice
4. 4/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Introduction
Monitoring Slices
Monitoring Slices
Monitoring Slices reflect all the monitoring information about
a cloud slice, which is composed by the collected values of the
monitored metrics and the configuration of the monitoring solutions
that are needed to collect these metrics.
Every cloud slice is coupled with a monitoring slice, whose goal is
to detect cloud slice malfunctioning
5. 5/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Introduction
Monitoring slices
CPU
Memory
Network
CPU Utilization
Memory Utilization
Network Utilization
Monitoring SlicesCloud Slices
OpenStack
Ceilometer
6. 6/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Introduction
Problem
Problem
However, the lack of integration between some monitoring solutions
and cloud platforms imposes for cloud administrators to manually
set up monitoring solutions or develop scripts to automate the mon-
itoring slice creation
7. 7/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
Approach
In a previous work1, we propose a framework to automatically
create monitoring slices when cloud slices are created
Flexible Automated Cloud Monitoring Slices (FlexACMS):
enables self-configurable cloud monitoring strategies
independent of the monitoring solutions employed
creates monitoring slices automatically using monitoring
solutions that satisfy the cloud administrator’s needs
facilitates the reuse of scripts developed by cloud
administrators to automate the creation of monitoring slices
supports diverse cloud platforms and monitoring solutions
collects information from cloud platforms and triggers
appropriated components to build monitoring slices
1
CNSM 2013, Poster session
8. 8/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
Approach
Now, we enhanced FlexACMS:
Dynamic and automatic attribution of configuration tasks in a
Message-Queueing fashion: enables the automatic mapping
between type of metrics to be monitored in a monitoring slice
and the type of monitoring server to consume the request -
Enhancement!
Load balancing during the configuration of the monitoring
slices: enables the monitoring servers to volunteer to receive a
task (i.e., setting up the monitoring slice) when they have
capacity for doing so - Enhancement!
9. 9/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
New architecture
FlexACMS Core
Gatherers
Configurators
REST
WebService
...
Cloud Monitoring
... Monitoring
Slices
Cloud Platform
... Cloud
Slices
Requests
Queue
Request
Workers
Changes
Queue
Change
Worker
Change
Worker
Configurator
Workers
Change
Worker
Change
Worker
Change
Workers
Configurator
Queues
12
3
4
5
7
8
9
6
...
Gatherers:
responsible for collecting information from cloud platforms
(e.g., @slice.ip, @slice.identifier, @slice.owner)
handle peculiarities of APIs (e.g., Amazon EC2 API)
send collected information to FlexACMS Core through REST
Web service
10. 10/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
New architecture
FlexACMS Core
Gatherers
Configurators
REST
WebService
...
Cloud Monitoring
... Monitoring
Slices
Cloud Platform
... Cloud
Slices
Requests
Queue
Request
Workers
Changes
Queue
Change
Worker
Change
Worker
Configurator
Workers
Change
Worker
Change
Worker
Change
Workers
Configurator
Queues
12
3
4
5
7
8
9
6
...
FlexACMS Core:
responsible for processing information collected by gatherers
breaks the request into small tasks to be processed in a parallel
manner - Enhancement!
detects operations performed in the platform (e.g., cloud slice
creation) (Request Workers)
11. 11/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
New architecture
FlexACMS Core
Gatherers
Configurators
REST
WebService
...
Cloud Monitoring
... Monitoring
Slices
Cloud Platform
... Cloud
Slices
Requests
Queue
Request
Workers
Changes
Queue
Change
Worker
Change
Worker
Configurator
Workers
Change
Worker
Change
Worker
Change
Workers
Configurator
Queues
12
3
4
5
7
8
9
6
...
FlexACMS Core (Change Workers):
evaluates the rules predefined by cloud administrators to
trigger configuration tasks
each Configurator has an interest and a set of conditions
puts the configuration task in the Configurator Queue
predefined by the cloud administrator - Enhancement!
12. 12/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
New architecture
Examples of Configurator rules
Configurator Attribute Value
Name: nagios host basic Interest New Slice
Queue: nagios basic Condition @slice.MaaS =˜ /basic/
Name: nagios cpu basic Interest New Resource
Queue: nagios basic Condition @resource.identifier =˜ /CPU/
Condition @slice.MaaS =˜ /basic/
Name: nagios host plat Interest New Slice
Queue: nagios platinum Condition @slice.MaaS =˜ /platinum/
Name: nagios cpu plat Interest New Resource
Queue: nagios platinum Condition @resource.identifier =˜ /CPU/
Condition @slice.MaaS =˜ /platinum/
14. 14/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
FlexACMS
New architecture
FlexACMS Core
Gatherers
Configurators
REST
WebService
...
Cloud Monitoring
... Monitoring
Slices
Cloud Platform
... Cloud
Slices
Requests
Queue
Request
Workers
Changes
Queue
Change
Worker
Change
Worker
Configurator
Workers
Change
Worker
Change
Worker
Change
Workers
Configurator
Queues
12
3
4
5
7
8
9
6
...
Configurator Workers:
consume configuration tasks from the Configurator Queue if
the monitoring server has capacity to perform the task (e.g.,
appropriated server load) - Enhancement!
execute the Configurator and send its status and output to
REST Web service for past analysis and debug
15. 15/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Evaluation
Comparative
Comparative
Goal: evaluate what is the impact of the enhancements in the
FlexACMS performance
Cloud platform: OpenStack
Monitoring solutions: Nagios and MRTG
Created cloud slices: from 1 to 10 cloud slices
Monitoring slices: from 1 to 10 monitoring slices, with 2 and
52 metrics
Workers: 10 configurator workers
17. 17/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Evaluation
Scalability
Scalability
Goal: evaluate the scalability in regards to response time
varying:
number of cloud slices already in place (101
,102
,103
,104
)
number of new monitoring slices in a burst (10,40,70,100)
number of metrics per monitoring slice (5,25,50)
Cloud platform: a gatherer generates requests similar to an
actual OpenStack gatherer
Monitoring solutions: Nagios
Workers: 10 configurator workers
18. 18/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Evaluation
Scalability
Scalability
050150250350
log(cloud slices already in place)
Responsetime(s)
New monitoring slices
10 40 70 100
1 2 3 4
(a) 5 metrics per
monitoring slice
050150250350
log(cloud slices already in place)
Responsetime(s)
New monitoring slices
10 40 70 100
1 2 3 4
(b) 25 metrics per
monitoring slice
050150250350
log(cloud slices already in place)
Responsetime(s)
New monitoring slices
10 40 70 100
1 2 3 4
(c) 50 metrics per
monitoring slice
Figure: Scalability
19. 19/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Conclusions and future work
Conclusions
New FlexACMS features:
Dynamic and automatic attribution of monitoring tasks to
pools of monitoring servers
Load balancing when attributing monitoring tasks
Performance enhancements:
reduces circa of 10% its influence in the evaluation time
(Comparative)
FlexACMS time reduced up to 60% (Comparative - 10 new
monitoring slices)
20. 20/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Conclusions and future work
Conclusions
Scalability evaluation:
The number of cloud slices already in place does not affect the
response time
The number of metrics per monitoring slice and the number of
monitoring slices that must be built affect the response time,
but they do not affect the response time at same rate of
scenario growth
The automatic configuration of multiple monitoring solutions
for cloud computing is feasible
FlexACMS can be used to help cloud administrators to
achieve their monitoring needs using monitoring solutions that
are not integrated to cloud platforms
21. 21/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Conclusions and future work
Future work
Future work:
Complete the cloud slice life-cycle automation (reconfiguration
and destruction of monitoring slices)
Improve load balancing strategies
Investigate FlexACMS feasibility for PaaS and SaaS cloud
models
22. 22/22
Efficient Configuration of Monitoring Slices for Cloud Platform Administrators
Conclusions and future work
Acknowledgments
Thank you for your attention!
Questions?
mbcarvalho@inf.ufrgs.br