Videos

Demonstration of ACTiManager.internal functionality running on top of an OpenStack installation on a KALEAO's KMAX platform. ACTiManager.internal is responsible for scheduling incoming VMs on the 8 cores of the platform (4 big & 4 LITTLE ARM cores). The VMs are categorized as gold (high priority) or silver (low priority) and ACTiManager.internal prioritizes VMs by scheduling the gold ones on the big cores.

Demonstration of ACTiManager.internal functionality running on top of an OpenStack installation on a KALEAO's KMAX platform. ACTiManager.internal is responsible for scheduling incoming VMs on the 8 cores of the platform (4 big & 4 LITTLE ARM cores). The VMs are categorized as gold (high priority) or silver (low priority) and ACTiManager.internal prioritizes VMs by scheduling the gold ones on the big cores. Compared to Demo 1.1, now the type (gold or silver) of the incoming VM is selected randomly.

Demonstration of ACTiManager.external functionality running on top of an OpenStack installation on a KALEAO's KMAX platform. ACTiManager.external is responsible for balancing VMs (gold/high priority & silver/low priority) between 2 8-core KMAX compute nodes.

In this video, we show how we can use the memory footprint estimation given by MALCOM to select the most suitable (in terms of execution time) virtual machine to run a given SQL query. This is an example of the potential benefits in tailored resource provisioning one can expect from a flexible cloud architecture such as the ACTiCLOUD platform.

"ACTivating resource efficiency and large databases in the CLOUD" (ACTiCLOUD) is an H2020 RIA project funded under H2020-ICT-2016-1. ACTiCLOUD proposes a novel cloud computing architecture for drastically improved management of cloud resources. By utilizing modest investments on hardware intelligence that enables true resource disaggregation between multiple servers, ACTiCLOUD will progress current state-of-the-art in hypervisors and cloud management systems promoting holistic resource management at the rack scale and across distributed cloud sites. On top of this, ACTiCLOUD will evolve the ecosystem around in-memory databases, a core component for extremely demanding and highly critical classes of applications that up to now have faced severe difficulties in matching their resource requirements with state-of-the-art cloud offerings, with a final goal to provide cost-efficient and highly performant DataBase-as-a-Service (DBaaS) cloud platforms. Website: https://acticloud.eu Twitter : https://twitter.com/acticloud ResearchGate: https://www.researchgate.net/project/ACTiCLOUD

Georgios Goumas of NTUA tells us a bit about how the ACTiCLOUD team will tackle efficient resource management in cloud computing systems www.twitter.com/acticloud