You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: _data/tools.yml
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -15,7 +15,7 @@
15
15
16
16
- id: kubeDelphi
17
17
name: "kubeDelphi: a Modular Framework for Intelligent Workload Placement and Rescheduling in Kubernetes"
18
-
description: kubeDelphi is an evolution of Kubernetes based on an advanced workload scheduling system, which is designed to optimize workload placement and rescheduling in cloud-native environments.
18
+
description: kubeDelphi is an extension of Kubernetes based on an advanced workload scheduling system, which is designed to optimize workload placement and rescheduling in cloud-native environments.
Copy file name to clipboardExpand all lines: _tools/kubeDelphi.md
+8-9Lines changed: 8 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,19 +14,18 @@ publications:
14
14
- iris_2024_7fb906c6bb213d7d6ba9
15
15
---
16
16
17
-
Kubernetes has become the de facto standard for orchestrating cloud-native workloads across clusters of machines, both on-premises and in the cloud. As organizations scale their infrastructure and diversify their workloads (including AI/ML, IoT, security functions and latency-sensitive applications), the need for intelligent, policy-driven placement and rescheduling of pods becomes critical. Standard Kubernetes scheduling is powerful but often generic, lacking the ability to optimize for custom objectives such as cost, energy efficiency, resource utilization, or application-specific constraints. **KubeDelphi** fills this gap and drive the evolution of Kubernetes towards:
17
+
Kubernetes has become the de facto standard for orchestrating cloud-native workloads across clusters of machines, both on-premises and in the cloud. As organizations scale their infrastructure and diversify their workloads (including AI/ML, IoT, security functions and latency-sensitive applications), the need for intelligent, policy-driven placement and rescheduling of pods becomes critical. Standard Kubernetes scheduling is powerful but generic, and lacks the ability to optimise for custom objectives such as cost, energy efficiency, resource utilisation, or application-specific constraints. **kubeDelphi** fills this gap and drive the evolution of Kubernetes towards:
18
18
-**Cost optimization**, reducing cloud expenditure by placing workloads on the most cost-effective resources.
19
19
-**Resource efficiency**, maximizing the use of available CPU, memory, and specialized hardware (e.g., GPUs).
20
20
-**Performance and QoS**, ensuring latency-sensitive applications meet their SLAs.
21
-
KubeDelfi addresses these needs by providing a modular, extensible framework that adds advanced placement and rescheduling capabilities to Kubernetes.
22
-
23
-
**kubeDelphi** enables cloud operators and developers to:
24
-
- Experiment with custom placement algorithms.
25
-
- Seamlessly integrate these algorithms into the Kubernetes scheduling cycle.
26
-
- Automate the rescheduling of workloads to adapt to changing cluster conditions, workload status or business objectives.
21
+
22
+
***kubeDelphi** is an extension of Kubernetes based on an advanced workload scheduling system, which is designed to optimize workload placement and rescheduling in cloud-native environments.*
23
+
27
24
28
25
## Framework overview
29
-
KubeDelphi is composed of three main components:
26
+
27
+
**kubeDelphi** enables cloud operators and developers to (i) experiment with custom placement algorithms, (ii) seamlessly integrate them into the Kubernetes scheduling cycle, and (iii) automate workload rescheduling in response to changing cluster conditions, workload status, or business objectives. These capabilities are delivered through three main components:
28
+
30
29
### kubectl Plugin
31
30
32
31
-**Purpose**: to extend the standard kubectl CLI with new commands for advanced cluster management tasks.
@@ -40,5 +39,5 @@ KubeDelphi is composed of three main components:
40
39
41
40
### Kubernetes Scheduler Plugin
42
41
-**Purpose**: to integrate with the Kubernetes scheduler to enforce placement decisions made by the algorithms.
43
-
-**Current functionalities**: the KubeDelphi scheduling plugin reads placement scores generated by the Placement Algorithm and influences pod scheduling accordingly.
42
+
-**Current functionalities**: the **kubeDelphi** scheduling plugin reads placement scores generated by the Placement Algorithm and influences pod scheduling accordingly.
44
43
-**Role in framework**: extends the Kubernetes Scheduling Framework adding a new plugin able to take into account the placement decisions made by the placement algorithm in use.
0 commit comments