BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Pentabarf//Schedule 0.3//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALDESC;VALUE=TEXT:HPC, Big Data and Data Science devroom X-WR-CALNAME;VALUE=TEXT:HPC, Big Data and Data Science devroom X-WR-TIMEZONE;VALUE=TEXT:Europe/Brussels BEGIN:VEVENT METHOD:PUBLISH UID:4514@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T090000 DTEND:20160131T090500 SUMMARY:Opening DESCRIPTION:
A warm welcome to the HPC, Big Data, and Data Science Devroom.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_opening/ LOCATION:AW1.126 END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4014@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T090500 DTEND:20160131T093000 SUMMARY:FlinkML: Large Scale machine learning for Apache Flink DESCRIPTION:Apache Flink is an open source platform for distributed stream and batch data processing. In this talk we will show how Flink's streaming engine and support for native iterations make it an excellent candidate for the development of large scale machine learning algorithms.
This talk will focus on FlinkML, a new effort to bring scalable machine learning tools to the Flink community. We will provide an introduction to the library, illustrate how we employ some state-of-the-art algorithms to make FlinkML truly scalable, and provide a view into the challenges and decisions one has to make when designing a robust and scalable machine learning library.
Finally, if time permits, we will demonstrate how one can perform some interactive analysis using FlinkML and the notebook environment of Apache Zeppelin.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_flinkml/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Theodore Vasiloudis":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4360@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T093000 DTEND:20160131T095500 SUMMARY:MADlib: Distributed In-Database Machine Learning for Fun and Profit DESCRIPTION:Apache MADlib (incubating) is an innovative SQL-based open source library for scalable in-database analytics. It provides parallel implementations of mathematical, statistical and machine learning methods for structured and unstructured data. MADlib also has an R interface for data scientists who prefer to work in R.
In this talk, we will describe the impetus behind creating a SQL-based scale-out machine learning project, review the architecture and implementation, and describe some of the recent functionality added by the Apache community. We will also present the R interface to MADlib, called PivotalR.
Finally, we will discuss the future direction of the project and invite big data developers and data scientists to participate in Apache MADlib, for both fun and profit.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_madlib/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Frank McQuillan":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4276@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T100000 DTEND:20160131T103000 SUMMARY:[AMENDMENT] Apache Bigtop DESCRIPTION:Bigtop is an Apache Foundation project for Infrastructure Engineers and Data Scientists looking for comprehensive packaging, testing, and configuration of the leading open source big data components.
Insights into bootstrapping and automation of the packaging process on ci.bigtop.apache.org will be given. Special focus is on the use of docker containers for isolating and scaling the build processes.
Some aspects of the challenges of porting the bigtop distribution to other platforms will be covered, too.
Another focus of the talk will be on deploying Bigtop components using the supplied puppet scripts.Included are life deployment demos into docker containers featuring different Big Data scenarios.
REPLACEMENT for "Building open source with open source" by Nicolas Schiper
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/bigtop/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Olaf Flebbe":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:3773@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T103000 DTEND:20160131T105500 SUMMARY:Automating Big Data Benchmarking for Different Architectures DESCRIPTION:This talks will present how to perform benchmarking of Big Data systems, from low-powered devices, HPC clusters, to cloud IaaS and PaaS. It will guide participants on how to define clusters, select benchmark suites and configuration with the ALOJA open source tools. ALOJA (http://aloja.bsc.es) is a research initiative from the Barcelona Supercomputing Center to explore new cost-effective hardware architectures for Big Data. During its first year, ALOJA's benchmarking efforts have produced the largest public repository with over 50,000 Hadoop benchmark runs. The searchable repository features different applications for Hadoop, software configurations, data sizes, and more than 100 different hardware deployment options.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_automating_big_data_benchmarking/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Nicolas Poggi":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4350@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T110000 DTEND:20160131T112500 SUMMARY:hanythingondemand: easily creating on-the-fly Hadoop clusters (and more) on HPC systems DESCRIPTION:hanythingondemand (or HOD for short) is a set of scripts to start services, for example a Hadoop cluster, from within another resource management system (e.g., Torque/PBS) on an HPC system. As such, it allows traditional users of HPC systems to experiment with Hadoop and other services, or use it as a production setup if there is no dedicated setup available. Next to Hadoop clusters, HOD can also create HBase databases, IPython notebooks, and set up a Spark environment.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_hanythingondemand/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Ewan Higgs":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4301@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T113000 DTEND:20160131T115500 SUMMARY:Timely dataflow in Rust DESCRIPTION:I'll present recent work on an implementation of "timely dataflow", a neat new data-parallel programming model, in Rust, a neat new-ish programming language from Mozilla. I'll talk through how Rust's take on ownership is a great fit for distributed big data programming, and in particular how it lets us write rich high-level dataflow programs that still have the performance characteristics we expect from hand-written code.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_dataflow/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Frank McSherry":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4286@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T120000 DTEND:20160131T120500 SUMMARY:ClusterShell DESCRIPTION:HPC administration tasks require admins to run identical commands across their clusters efficiently and frequently.Cluster tools develop again and again their own set of commands to perform similar tasks. Admins often develop their own scripts trying to implement fast execution, not always successfully.ClusterShell proposes to address these problems by offering a new set of command-line tools and a Python framework, both relying on the same optimized code and features. It took the best of famous commands, like pdsh, and improved it. The library can be used to ease admin script development and remove the burden of implementing optimized parallelism.ClusterShell supports multiple execution backends like SSH or RSH variants. Tools from other projects already rely on ClusterShell for their efficient command execution like MilkCheck or Shine. Moreover, ClusterShell offers a powerful way to manage range of nodes which could be used in any tools using its Python API.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_clustershell/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Aurélien Degrémont":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:3937@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T120500 DTEND:20160131T121000 SUMMARY:Extracting Data from your Open Source Communities DESCRIPTION:Open source communities are filled with huge amounts of data just waiting to be analyzed. Getting this data into a format that can be easily used for analysis may seem intimidating at first, but there are some very useful open source tools that make this task relatively easy. The primary tools used in this talk are the open source Metrics Grimoire tools that take data from various community sources and store it in a database where it can be easily queried and analyzed.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_os_communities/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Dawn Foster":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4057@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T121000 DTEND:20160131T121500 SUMMARY:Reproducible and User-Controlled Package Management in HPC with GNU Guix DESCRIPTION:Support teams of high-performance computing (HPC) systems often find themselves between a rock and a hard place: on one hand, they understandably administrate these large systems in a conservative way, but on the other hand, they try to satisfy their users by deploying up-to-date tool chains as well as libraries and scientific software. HPC system users often have no guarantee that they will be able to reproduce results at a later point in time, even on the same system—software may have been upgraded, removed, or recompiled under their feet, and they have little hope of being able to reproduce the same software environment elsewhere. We present GNU Guix and the functional package management paradigm and show how it can improve reproducibility and sharing among researchers with representative use cases.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_gnu_guix/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Ricardo Wurmus":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:3964@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T121500 DTEND:20160131T122000 SUMMARY:Scylla, a Cassandra-compatible NoSQL database at 2 million requests/s DESCRIPTION:Scylla is a new NoSQL database, capable of 2 million requests per second per node, while providing Apache Cassandra compatibility and scaling properties. Scylla applies systems programming techniques to a horizontally scalable NoSQL design to achieve extreme performance improvements. As CPU core counts continue to grow, along with the raw speed of networking and storage devices available on a modern system, software design approaches that were valid and safe even a few years ago are no longer sustainable.
Scylla enables high throughput, low latency, and rapid completion of housekeeping operations such as compaction. Scylla eliminates known performance bottlenecks of existing NoSQL servers by running multiple engines, one per core, each with its own memory, CPU and multi-queue NIC. Scylla bypasses key performance bottlenecks that can affect NoSQL server performance using per-core memory allocation to avoid locking, and asynchronous I/O for storage to bypass the system page cache. With Scylla, NoSQL projects can avoid performance uncertainties up front in order to deploy a system that performs and scales with a low risk of unpredictable performance issues later.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_scylla/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Roman Shaposhnik":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4002@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T122000 DTEND:20160131T122500 SUMMARY:Taxi trip analysis (DEBS grand-challenge) with Apache Geode (incubating) DESCRIPTION:Apache Geode (incubating) is a distributed key-value store built for scale and performance. The ACM Distributed Event-Based Systems conference always create interesting challenges for data processing and in this talk we will present a solution for analysing taxi trip information completely based on Apache Geode and some other key features that the project offers being beyond other key-value stores.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_debs/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="William Markito":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4331@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T123000 DTEND:20160131T125500 SUMMARY:OpenHPC: Community Building Blocks for HPC Systems DESCRIPTION:Today, many supercomputing sites spend considerable effort aggregating a largesuite of open-source projects on top of their chosen base Linux distribution inorder to provide a capable HPC environment for their users. They alsofrequently leverage a mix of external and in-house tools to perform softwarebuilds, provisioning, config management, software upgrades, and systemdiagnostics. Although the functionality is similar, the implementations acrosssites is often different which can lead to duplication of effort. Thispresentation will use the above challenges as motivation for introducing a new,open-source HPC community (OpenHPC) that is focused on providing HPC-centricpackage builds for a variety of common building-blocks in an effort to minimizeduplication, implement integration testing to gain validation confidence, andprovide a platform to share configuration recipes from a variety of sites.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_openhpc/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Karl W. Schulz":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4257@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T130000 DTEND:20160131T132500 SUMMARY:XALT: Tracking User Jobs and Environments on a Supercomputer DESCRIPTION:Let's talk real, no-kiddin' supercomputer analytics, aimed at movingbeyond monitoring the machine as a whole or even its individualhardware components. We're interested in drilling down to the level ofindividual tasks, users, and binaries. We’re after readyanswers to the "what, where, how, when and why" that stakeholders areclamoring for: everything from which libraries (or individualfunctions!) are in demand, to preventing the problems that get in theway of successful science. This talk will show how XALT can providethis type of job-level insight.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_xalt/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Robert McLay":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4334@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T133000 DTEND:20160131T135500 SUMMARY:Multi-host containerised HPC cluster DESCRIPTION:With Docker v1.9 a new networking system was introduced, which allows multi-host networking to work out-of-the-box in any Docker environment. This talk provides an introduction on what Docker networking provides, followed by a demo that spins up a full SLURM cluster across multiple machines.The demo is based on QNIBTerminal, a Consul backed set of Docker Images to spin up a broad set of software stacks.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_hpc_cluster/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Christian Kniep":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4313@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T140000 DTEND:20160131T142500 SUMMARY:Parallel Inception DESCRIPTION:The intersection of massively parallel processing (MPP) databases and general-purpose programming on graphics processors (GPGPU) affords incredible compute capabilities to scientists and analysts. This talk will showcase the marriage of well-established, open source MPP database infrastructure and cutting edge data-level parallelism using GPGPU. Some examples will be shown using a hosted, cluster environment to showcase the ease of implementation. Pending disclosure authorization, some real-world use cases will be discussed as well.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_mpp/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Kyle Dunn":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4146@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T143000 DTEND:20160131T145500 SUMMARY:Using Hadoop as a SQL Data Warehouse DESCRIPTION:Apache HAWQ is a Hadoop native SQL query engine that combines the key technological advantages of MPP database with the scalability and convenience of Hadoop. It provides users the tools to confidently and successfully interact with petabyte range data sets. HAWQ provides users with a complete, standards compliant SQL interface.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_hadoopsql/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Lei Chang":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4339@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T150000 DTEND:20160131T152500 SUMMARY:ORCA: Query Optimization as a Service DESCRIPTION:We all know there is more data than ever before. We do our best to optimize the computation of data, but our tools and techniques haven't kept up. The need for a new approach to query optimization has never been greater.
This motivates the development of ORCA, now a fully open-source query optimizer that is designed to work with any database.
ORCA has achieved a 1000x performance improvement across TPC-DS queries by focusing on three distinct areas: Dynamic Partition Elimination, SubQuery Unnesting, and Common Table Expression.
ORCA is the default query optimizer in the open-source databases, Greenplum Database -- RDBMS data warehouse solution, and Apache HAWQ -- a SQL on Hadoop solution.
Addison will give an overview of ORCA’s architecture, where the project is headed, and how to get involved.The need to rethink query optimization led to the development of ORCA, now a fully open-source query optimizer that is designed to work with any database.
ORCA has achieved a 1000x performance improvement across TPC-DS queries by focusing on three distinct areas: Dynamic Partition Elimination, SubQuery Unnesting, and Common Table Expression. ORCA is the default query optimizer in the open-source databases, Greenplum Database -- RDBMS data warehouse solution, and Apache HAWQ -- a SQL on Hadoop solution.
Addison will give an overview of ORCA’s architecture, where the project is headed, and how to get involved.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_orca/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Addison Huddy":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4006@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T153000 DTEND:20160131T155500 SUMMARY:Big Data meets Fast Data: an scalable hybrid real-time transactional and analytics solution DESCRIPTION:Data transactions (OLTP) and analytics (OLAP) have long been treated as very different concerns. Analyzing high volume transactional data traditionally required complex and hard to maintain ELT / ETL integration batches that ran overnight, causing any insights to be based on data that is already outdated.
What if we could transact data very fast, on an open-source horizontally high scalable NoSQL system, and that data be automatically and constantly written to a massive parallel analytical database - allowing near real-time transactions and analytics?
What if we could cache back on the transactional system any analytical data insights or machine learning algorithm results, pushing those analytical findings back to the applications, allowing real closed-loop analytics?
Data streaming is gaining popularity, as it offers decreased latency, a radically simplified data infrastructure architecture, and the ability to cope with new data that is generated continuously. Apache Flink is a full-featured stream processing framework with:
Flink is used in several companies, including at ResearchGate, Bouygues Telecom, the Otto Group, and Capital One, and has a large and active developer community of well over 140 contributors. In this talk, we provide an overview of the system and its streaming-first philosophy, as well as the project roadmap and vision: fully unifying the, now separate, worlds of “batch” and “streaming” analytics.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_flink_streaming/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Till Rohrmann":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4335@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T163000 DTEND:20160131T165500 SUMMARY:Streaming Architecture: Why Flow Instead of State? DESCRIPTION:Batch processing has been, until recently, the standard model for big data. Largely, this is due to the very large influence of the original processing MapReduce implementation in Hadoop and the difficulty in replacing MapReduce in the original Hadoop framework.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdatawhy_flow_instead_of_state/ LOCATION:AW1.126 ATTENDEE;ROLE=REQ-PARTICIPANT;CUTYPE=INDIVIDUAL;CN="Tugdual Grall":invalid:nomail END:VEVENT BEGIN:VEVENT METHOD:PUBLISH UID:4515@FOSDEM16@fosdem.org TZID:Europe-Brussels DTSTART:20160131T165500 DTEND:20160131T170000 SUMMARY:Closing DESCRIPTION:Closing note of the day.
CLASS:PUBLIC STATUS:CONFIRMED CATEGORIES:HPC, Big Data and Data Science URL:https:/fosdem.org/2016/schedule/2016/schedule/event/hpc_bigdata_closing/ LOCATION:AW1.126 END:VEVENT END:VCALENDAR