Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:High-Throughput and Predictable VM Scheduling for High-Density Workloads
Speaker:Manohar Vanga
coming from:Max Planck Institute for Software Systems
Speakers Bio:
Event Type:SWS Student Defense Talks - Thesis Proposal
Visibility:SWS
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Monday, 26 March 2018
Time:15:00
Duration:-- Not specified --
Location:Kaiserslautern
Building:G26
Room:111
Abstract
In the increasingly competitive public-cloud marketplace, improving the efficiency of data centers is a major concern. One way to improve efficiency is to consolidate as many virtual machines (VMs) onto as few physical cores as possible, provided that customers' performance expectations are not violated. However, as a prerequisite for supporting increased VM densities, the hypervisor’s VM scheduler must allocate processor time efficiently and in a timely fashion. Unfortunately, we show that contemporary VM schedulers leave substantial room for improvements in both regards when facing challenging high-VM-density workloads that frequently trigger the VM scheduler.

We identify the root causes of this inability to support high-density VM scenarios to be (i) high runtime overheads and (ii) unpredictable scheduling heuristics. To better support high VM densities, we propose Tableau, a VM scheduler that guarantees a minimum processor share and a maximum bound on scheduling delay for every VM in the system. Tableau achieves this by combining a low-overhead, core-local, table-driven dispatcher within the hypervisor with a fast on-demand table-generation procedure (triggered asynchronously upon VM creation and teardown) that employs scheduling techniques typically used in hard real-time systems.

In an evaluation comparing Tableau against three current Xen schedulers on a 16-core Intel Xeon machine, Tableau is shown to improve both tail latency (e.g., a 17x reduction in maximum ping latency compared to Credit, Xen's default scheduler) and throughput (e.g., 1.6x peak web server throughput compared to Xen's real-time RTDS scheduler when serving 1 KiB files with a 100 ms SLA).
While Tableau solves one piece of the unpredictability puzzle, namely the VM scheduler, there are other sources of unpredictability that arise in a shared, high-density setting. We therefore propose extensions of Tableau to deal with two other major sources of unpredictability: LLC interference caused by other VMs co-located on the same CPU socket, and delays that arise due to I/O scheduling.

Contact
Name(s):
Video Broadcast
Video Broadcast:YesTo Location:Saarbrücken
To Building:E1 5To Room:029
Meeting ID:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created:
Maria-Louise Albrecht/MPI-KLSB, 03/23/2018 03:15 PM
Last modified:
Maria-Louise Albrecht/MPI-KLSB, 04/05/2018 02:11 PM
  • Maria-Louise Albrecht, 04/05/2018 02:11 PM
  • Maria-Louise Albrecht, 03/23/2018 03:18 PM -- Created document.