MesosCon Europe 2017
2017-10-25..2017-10-27
Prague, Czechia
who it's for
platform engineers, site reliability engineers, infrastructure engineers, platform architects, framework developers, data engineers, network and storage engineers
topics
Apache Mesos operations at scale; DC/OS packaging and SDK; CNI-based container networking; CSI container storage integration; secrets management with Vault; hierarchical fair share quotas; fault domains region and zone; Marathon performance and jobs; Spark on Mesos with Kerberos; TensorFlow on DC/OS and GPU scheduling; autoscaling Mesos clusters
| title | author | length |
|---|---|---|
| Keynote: Welcome and State of Mesos | Ben Hindman | 13m |
Since the last MesosCon Europe the project ships four minor and nine patch releases and adds 13 new committers/PMC members; community Slack activity grows… | ||
| Keynote: The Apache Way | Rich Bowen | 22m |
Mesos sits inside the Apache Software Foundation, which now hosts 315 projects and runs an incubator with 60 projects learning Apache governance; projects must… | ||
| Keynote Panel Discussion: SMACK in the Enterprise | Elizabeth K. Joseph | 19m |
Companies describe deploying SMACK = Spark Mesos Akka Cassandra Kafka on DC/OS/Mesos to ingest and analyze telemetry at scale, running real-time analytics that… | ||
| Keynote: Making and Keeping Netflix Highly Available | Katharina Probst | 19m |
Netflix runs ~380 streaming-path microservices for 100+ million customers across ~1,000 device types and uses a Mesos-based stream processor Mantis plus a… | ||
| Welcome Remarks | Jörg Schad | 02m |
A quick opening polls the room about starting earlier versus sleeping longer and records about half the audience favoring a later start, so the schedule stays… | ||
| Keynote: The Future of Apache Mesos and DC/OS | Yrieix Garnier | 22m |
Apache Mesos remains the resource manager and DC/OS packages cloud services, claiming a unified platform that runs containers and stateful data services… | ||
| Keynote: Operating 600+ Mesos Servers on 7 Datacenters @Criteo | Pierre Cheynier | 19m |
Platform runs 600+ Mesos agents across seven datacenters serving ~750 production apps at up to 200K requests/sec and 40Gbps. Automation uses Chef/Consul/Apache… | ||
| Container Networking for Micro-Services: An Apache Mesos Networking Deep Dive | Jörg Schad | 33m |
Covers how DC/OS and Mesos wire containers end to end: the CNI isolator creates network namespaces and plugins (bridge, IPAM, VLAN) attach them; overlay… | ||
| Fault Domains in Mesos | Vinod Kone | 43m |
Mesos 1.4 adds a native fault domain primitive (stored in domain_info protobuf) with a simple region/zone hierarchy and offers that include an agent’s domain… | ||
| Secrets Management in Mesos | Vinod Kone | 47m |
Mesos adds first-class secrets in Mesos 1.3 with a modular Secret Resolver interface (examples use Vault); secrets are reference-based (recommended) or… | ||
| Containerization in Mesos, Embracing the Standards | Jie Yu | 43m |
Mesos claims a pluggable container model with isolators, launchers, provisioners and is actively adopting CNI, CSI, OCI standards; Docker image provisioning is… | ||
| Spark Over a Mesos Secured Productive Environment | Jorge Lopez-Malla, Marcos Peñate | 43m |
Stratio modifies Spark on Mesos to add Kerberos authentication, dynamic delegation tokens and Vault-backed secret provisioning so no master keys hit container… | ||
| DataStax Enterprise on DC/OS - Yes, It’s Possible; Customer Case Studies | Ravi Yadav | 32m |
DataStax Enterprise runs on DC/OS with two universe tiles (DSE and Ops Center), full platform features (search, graph, analytics, security) and joint support… | ||
| 8 Tips for Marathon Performance | Tomasz Janiszewski | 30m |
Eight concrete operational changes that cut outages and CPU waste: enable Marathon metrics and raise the polling to metrics interval 55s to drop metrics CPU… | ||
| Apache Kafka + Apache Mesos = Highly Scalable Streaming Microservices | Kai Waehner | 41m |
A working demo deploys Apache Kafka on DC/OS with 3 brokers and a Kafka Streams microservice that embeds an H2O decision‑tree model to predict flight delays… | ||
| The Container Storage Initiative: What is this Project About and Where are We Going? | Steven Wong | 01h 02m |
Proposal to standardize container storage via a gRPC control plane called CSI that exposes identity, controller and node services for volume lifecycle, aiming… | ||
| Doing Real DevOps with DC/OS | Julien Stroheker | 49m |
Live demo shows a Java/Tomcat + MongoDB app split into two services, built and pushed as Docker images by a Jenkins pipeline that tags builds and calls Vamp… | ||
| Mesos Security Exposed! | Alexander Rojas, Adam Bordelon | 49m |
Adds signed JWT tokens (HMAC-SHA256) to authenticate executors (payload: frameworkID, executorID, containerID) so fake executors can no longer claim IDs… | ||
| Knee Deep in Microservices | Ádám Sándor | 37m |
Argues microservices make sense at any team size but impose real costs: test/production parity, networking, service discovery, monitoring and culture… | ||
| Robust Applications in Mesos Using External Storage | David vonThenen | 52m |
Compares direct‑attached versus external volumes on Mesos and DC/OS, shows concrete tools and outcomes: uses REX‑Ray and Mesos’ volume isolator to attach… | ||
| mesos2iam: IAM Credentials for Containers Running Inside a Mesos Cluster | Zain Malik | 28m |
mesos2iam runs on Mesos agents and returns per-task temporary AWS credentials so containers never store keys; it uses the AWS instance metadata/STs flow, a… | ||
| Running Distributed TensorFlow on DC/OS | Kevin Klues | 36m |
DC/OS adds a beta tensorflow package that automates distributed TensorFlow deployment: it generates the cluster spec, schedules GPU-aware tasks, restarts… | ||
| Apache Flink Meets Apache Mesos and DC/OS | Jörg Schad | 43m |
Explains a concrete Mesos/DC/OS integration: Flink becomes a Mesos framework using Fenzo offer matching and a new FLIP-6 architecture that adds a long‑running… | ||
| DIY Mesos Executor | Tomasz Janiszewski | 29m |
Custom Mesos executors replace the default to do three concrete things: injects TLS certs and encrypted config into task env (a CA signs agent certs, executor… | ||
| How We Built a Highly Scalable Machine Learning Platform Using Apache Mesos | Daniel Sârbe | 53m |
Built a containerized Machine Translation platform on Apache Mesos using Marathon/Kronos, Docker and Marathon for orchestration, Kafka for messaging, HBase on… | ||
| Building FAST Data Solutions with DC/OS on Azure | Rob Bagby | 43m |
Demo shows a sensor-producer writing to a Kafka topic with partitions, consumers read partition batches and write offsets into Cassandra, and a lag-reader… | ||
| More Bang for Your Buck: How Yelp Autoscales Mesos + Marathon on AWS Spot Fleet | Rob Johnson | 41m |
Yelp runs autoscaling PaaSTA with Mesos + Marathon, operating ~900 Marathon apps, ~5.5k tasks and ~600 agents across data centers and AWS. A service autoscaler… | ||
| Accelerating Spark Workloads in a Mesos Environment with Alluxio | Gene Pang | 35m |
Alluxio deployed on Mesos (via DC/OS) sits between Spark and backing stores (S3, HDFS), providing a memory-speed virtual distributed storage cache and a… | ||
| Using External Persistent Volumes to Reduce Recovery Times and Achieve High Availability on DC/OS | Dinesh Israni | 41m |
Claim: using Portworx external persistent volumes with DC/OS and dcos-commons cuts recovery to the time a scheduler reschedules tasks instead of hours or days… | ||
| What Building Multiple Scalable DC/OS Deployments Taught Me About Running Stateful Services on DC/OS | Nathan Shimek | |
Multiple scalable DC/OS deployments expose concrete limits and fixes: local volumes being pinned to hosts and “one task per volume” force either Portworx-style… | ||
| How Houghton Mifflin Harcourt Went from Months to Minutes for Infrastructure Delivery | Robert Allen | 42m |
Company moves from months or years to minutes for provisioning by building a shared platform called Bedrock that runs Apache Mesos and Apache Aurora, backed by… | ||
| Marathon and Jobs - Today and Tomorrow | Johannes Unterstein | 55m |
Marathon evolution focuses on concrete features and tradeoffs: added local persistent volumes and external storage via RexRay; introduced the Universal… | ||
| Optimising Mesos Utilization at Opentable | Jay Chin | 33m |
OpenTable runs Mesos with Singularity and builds a metrics pipeline where Mesostats pulls Mesos/Singularity metrics into Kafka then into Graphite and Grafana… | ||
| Seagull: A Distributed, Fault Tolerant, Concurrent Task Runner | Sagar Patwardhan | 34m |
Seagull splits a 100,000-test monolith into timed bundles and finishes a full test suite in under ten minutes by running thousands of parallel executors on… | ||
| Advanced Deployment Strategies and Workflows for Containerized Apps on DC/OS | Tim Nolet | 50m |
DC/OS/Kubernetes orchestration gets automated with vamp running as a container, using breeds and blueprints to represent app versions, a gateway that streams… | ||
| Time Traveling in the Universe of Microservices and Orchestration | Ilya Dmitrichenko | 45m |
Live demo shows a product that records container topology, metadata and Prometheus metrics so you can rewind a cluster and correlate a Git commit or automated… | ||
| WTF, My Container Just Spawned a Shell | Jorge Salamero Sanz | 43m |
Sysdig Falco is an open source runtime monitor that hooks kernel tracepoints to capture system calls plus container metadata and match them against user rules… | ||
| A Year with Apache Aurora | Rick Mangi | 42m |
Migrates the bulk of infrastructure from Puppet-managed EC2 to Apache Aurora on Mesos, running a cluster of about 1,350 cores with over 104 worker jobs and a… | ||
| Disaster Recovery with a Distributed Database | Max Neunhöffer, Jörg Schad | 38m |
ArangoDB implements asynchronous DC-to-DC replication by dumping change events into Kafka on each side and replaying them with ArangoSync so a primary cluster… | ||
| Autoscaling Mesos Cluster | Julien Stroheker | 36m |
A small Python autoscaler is built that polls Mesos leader / slaves endpoint every configurable interval, computes cluster CPU usage and calls a provider class… | ||
| There and Back Again: How Tunstall Healthcare Built an IoT Platform for Health Monitoring | Fredrik Lindner | 42m |
Builds an IoT platform using Mesos/DCOS on Azure with Marathon as the orchestrator and custom ARM/ACS templates instead of defaults to control VNETs, managed… | ||
| nothing matches | ||