TY - JOUR
T1 - Self managed virtual machine scheduling in
Cloud systems
AU - Sotiriadis, Stelios
AU - Bessis, Nik
AU - Buyya, Rajkumar
PY - 2018/4/1
Y1 - 2018/4/1
N2 - In Cloud systems, Virtual Machines (VMs)
are scheduled to hosts according to their
instant resource usage (e.g. to hosts with
most available RAM) without considering
their overall and long-term utilization.
Also, in many cases, the scheduling and
placement processes are computational
expensive and affect performance of
deployed VMs. In this work, we present a
Cloud VM scheduling algorithm that takes
into account already running VM resource
usage over time by analyzing past VM
utilization levels in order to schedule VMs
by optimizing performance. We observe
that Cloud management processes, like
VM placement, affect already deployed
systems (for example this could involve
throughput drop in a database cluster), so
we aim to minimize such performance
degradation. Moreover, overloaded VMs
tend to steal resources (e.g. CPU) from
neighbouring VMs, so our work maximizes
VMs real CPU utilization. Based on these,
we provide an experimental analysis to
compare our solution with traditional
schedulers used in OpenStack by exploring
the behaviour of different NoSQL
(MongoDB, Apache Cassandra and
Elasticsearch). The results show that our
solution refines traditional instant-based
physical machine selection as it learns the
system behaviour as well as it adapts over
time. The analysis is prosperous as for the
selected setting we approximately
minimize performance degradation by 19%
and we maximize CPU real time by 2%
when using real world workloads.
AB - In Cloud systems, Virtual Machines (VMs)
are scheduled to hosts according to their
instant resource usage (e.g. to hosts with
most available RAM) without considering
their overall and long-term utilization.
Also, in many cases, the scheduling and
placement processes are computational
expensive and affect performance of
deployed VMs. In this work, we present a
Cloud VM scheduling algorithm that takes
into account already running VM resource
usage over time by analyzing past VM
utilization levels in order to schedule VMs
by optimizing performance. We observe
that Cloud management processes, like
VM placement, affect already deployed
systems (for example this could involve
throughput drop in a database cluster), so
we aim to minimize such performance
degradation. Moreover, overloaded VMs
tend to steal resources (e.g. CPU) from
neighbouring VMs, so our work maximizes
VMs real CPU utilization. Based on these,
we provide an experimental analysis to
compare our solution with traditional
schedulers used in OpenStack by exploring
the behaviour of different NoSQL
(MongoDB, Apache Cassandra and
Elasticsearch). The results show that our
solution refines traditional instant-based
physical machine selection as it learns the
system behaviour as well as it adapts over
time. The analysis is prosperous as for the
selected setting we approximately
minimize performance degradation by 19%
and we maximize CPU real time by 2%
when using real world workloads.
KW - Cloud computing
KW - OpenStack
KW - Virtualmachine placement
KW - Virtual machinescheduling
KW - Virtual machine scheduling
KW - Virtual machine placement
UR - http://www.scopus.com/inward/record.url?scp=85022082650&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85022082650&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/46b0e9b2-dc80-319d-ae05-669f180b0d90/
U2 - 10.1016/j.ins.2017.07.006
DO - 10.1016/j.ins.2017.07.006
M3 - Article (journal)
SN - 0020-0255
VL - 433-434
SP - 381
EP - 400
JO - Information Sciences
JF - Information Sciences
ER -