Ilya Baldin

2

 14 GPO-funded racks built by IBM ◦ Partnership between RENCI, Duke and IBM ◦ IBM x3650 M4 servers (X-series 2U)  1x146GB 10K SAS hard drive +1x500GB secondary drive  48G RAM 1333Mhz  Dual-socket 8-core CPU  Dual 1Gbps adapter (management network)  10G dual-port Chelseo adapter (dataplane) ◦ BNT G/40G OpenFlow switch ◦ DS3512 6TB sliverable storage  iSCSI interface for head node image storage as well as experimenter slivering ◦ Cisco(UCS-B) and Dell configuration also exist  Each rack is a small networked cloud ◦ OpenStack-based with NEuca extensions ◦ xCAT for baremetal node provisioning  3

 ExoGENI is a collection of off-the shelf institutional clouds ◦ With a GENI federation on top ◦ xCAT – IBM product ◦ OpenStack- RedHat product  Operators decide how much capacity to delegate to GENI and how much to retain for yourself  Familiar industry-standard interfaces (EC2)  GENI Interface ◦ Mostly does what GENI experimenters expect 4

6

 CentOS 6.X base install  Resource Provisioning ◦ xCAT for bare metal provisioning ◦ OpenStack + Neuca Quantum for VMs ◦ FlowVisor  Floodlight used internally by ORCA  GENI Software ◦ ORCA for VM, baremetal and OpenFlow ◦ FOAM for OpenFlow experiments  Worker and head nodes can be reinstalled remotely via IPMI + KickStart  Monitoring via Nagios (Check_MK) ◦ ExoGENI ops staff can monitor all racks ◦ Site owners can monitor their own rack  Syslogs collected centrally 7

 IBM ◦ All GPO-funded racks, NICTA  Cisco ◦ NCSU, WVnet  Dell ◦ University of Amsterdam, several others in planning 8

 ExoGENI racks are separate aggregates but also act as a single aggregate ◦ Transparent stitching of resources from multiple racks  ExoGENI is designed to bridge distributed experimentation, computational sciences and Big Data ◦ Already running HPC workflows linked to OSG and national supercomputers ◦ Newly introduced support for storage slivering ◦ Strong performance isolation is one of key goals 11

 GENI tools: Flack, GENI Portal, omni ◦ Give access to common GENI capabilities ◦ Also mostly compatible with  ExoGENI native stitching  ExoGENI automated resource binding  ExoGENI-specific tools: Flukes ◦ Accepts GENI credentials ◦ Access to ExoGENI-specific features  Elastic Cluster slices  Storage provisioning  Stitching to campus infrastructure 12

Presentation title goes here13

 Compute nodes ◦ Up to 100 VMs in each full rack ◦ A few (2) bare-metal nodes ◦ BYOI (Bring Your Own Image)  True Layer 2 slice topologies can be created ◦ Within individual racks ◦ Between racks ◦ With automatic and user-specified resource binding and slice topology embedding ◦ Stitching across I2, ESnet, NLR, regional providers. Dynamic wherever possible  OpenFlow experimentation ◦ Within racks ◦ Between racks ◦ Include OpenFlow overlays in NLR (and I2) ◦ On-ramp to campus OpenFlow network (if available)  Experimenters are allowed and encouraged to use their own virtual appliance images  Since Dec 2012 ◦ slices 14

Virtual network exchange Virtual colo campus net to circuit fabric Multi-homed cloud hosts with network control Computed embedding Workflows, services, etc.

 ExoGENI rack in Sydney, Australia  Multiple VLAN tags on a pinned path from Sydney to LA  Internet2/OSCARS ORCA-provisioned dynamic circuit ◦ LA, Chicago  NSI statically pinned segment with multiple VLAN tags ◦ Chicago, NY, Amsterdam ◦ Planning to add dynamic NSI interface  ExoGENI rack in Amsterdam ◦ ~14000 miles ◦ 120ms delay

 Strong isolation is the goal  Compute instances are KVM based and get a dedicated number of cores  VLANs are the basis of connectivity ◦ VLANs can be best effort or bandwidth-provisioned (within and between racks) 17

 Workflow Management Systems ◦ Pegasus, Custom scripts, etc.  Lack of tools to integrate with dynamic infrastructures ◦ Orchestrate the infrastructure in response to application ◦ Integrate data movement with workflows for optimized performance ◦ Manage application in response to infrastructure  Scenarios ◦ Computational with varying demands ◦ Data-driven with large static data-set(s) ◦ Data-driven with large amount of input/output data

21 462,969 condor jobs since using the on-ramp to engage-submit3 (OSG)

Hardware-in-the loop slices Hardware-in-the-Loop Facility Using RTDS & PMUs (FREEDM Center, NCSU)

New GENI-WAMS Testbed Latency & Processing Delays Packet Loss Network Jitters Cyber-security Man-in-middle attacks Aranya Chakrabortty, Aaron Hurz (NCSU) Yufeng Xin (RENCI/UNC)

 ◦ ExoBlog  28