Dec 13, 2024

About

Traces

Tools

Links

edit SideBar

Search

FTAFormat

The trace format is organized hierarchically as follows:
Platform → Node → Component → Event Trace.


We summary the meaning of each table below. Table names are shown in bold.

  • A platform contains a set of nodes. Examples of a platform include SETI@home, desktops at Microsoft.
  • A node contains a set of components, which is a software module or hardware resource of the node. Each node can have several components (e.g. CPU speed, availability memory, client availability), each of which has a corresponding trace.
  • A component describes attributes of a software module or hardware resource of a node.
  • component_perf is the component performance, as measured through benchmarks for example.
  • A creator is the person responsible for the trace data set. This table stores details about citations and copyright.
  • An event_trace is the trace of an event, with all of corresponding timing information
  • event_state is the state corresponding to an event_trace. For example, for CPU availability, the event_state could be the idleness of the CPU. For host availability, it could be the monitoring information associated with the event.

A description of the table attributes appears below. The mysql schema is defined in fta.src.

platform
platform_idA unique number identifying this platform. It allows one to differentiate pools of nodes.
platform_namename of the platform (e.g. "Berkeley_NOW_Lab_Fall_1998")
platform_locationlocation name of the platform source (e.g. "Berkeley NOW Lab - Soda Hall 2nd Floor, USA, Planet Earth")
platform_typetype of the platform (cluster, multicluster, grid, desktop_grid, or volunteer_computing)
notesmiscellaneous notes
node
node_idunique ID for this node
platform_idid of the platform containing node
node_namename of node
node_ipIP address
node_locationlocation of the node (e.g. country, geographic coordinates)
timezonetime zone of the resource (second offset from GMT)
proc_modelprocessor name, model, version number
os_namename and version of the resource OS
cores_per_procnumber of cores per processor
num_procsnumber of processors for this node
mem_sizenumber of bytes of memory
disk_sizenumber of bytes of disk space
up_bwnumber of bytes/sec of upload speed
down_bwnumber of bytes/sec of download speed
metric_idunique ID for performance metric (e.g. benchmark)
notesother notes related to this resource
node_perf
metric_idunique ID for performance metric (benchmark)
node_idunique ID for this node
platform_idID of platform containing node
sfpop_speedsingle precision floating point speed (ops/sec)
dfpop_speeddouble precision floating point speed (ops/sec)
iop_speedinteger operation speed (ops/sec)
i_valinteger
f_valfloat
s_valstring
component
component_idunique ID for this component
node_idID of the node containing this component
platform_idID of platform containing this node
creator_idID of creator of this component trace data
node_nameName of the node
component_typetype of this component trace (for example, host, CPU, or network). see below for codes
trace_startwhen the trace event first appeared (epoch time). Can be NULL if component was always available.
trace_endwhen the trace event last appeared (epoch time). Can be NULL if component was always available.
resolutionresolution of the traces in seconds
creator
creator_idID of creator of this component trace data
component_idunique ID for this component trace data
node_idID of the node corresponding to this trace
platform_idID of platform containing node
creatorname(s) of the person(s) who recorded the event traces
citecitation (bibtex, etc) for using the data from the event traces
copyrightdetails of the copyright and rights reserved
event_trace
event_idunique ID of event state
component_idunique ID for this component trace data
node_idunique ID for this node
platform_idID of platform that is the node parent
node_namename of node
event_typetype of event. see below for event_type codes
event_start_timestart of this event (UNIX epoch time)
event_end_timeend of this event (UNIX epoch time)
event_end_reasonreason the event type or state changed at the end of this trace (for example, reason that CPU became unavailable. see below for event_end_reason codes)
event_state
event_idunique ID of event state
component_idunique ID for this component trace data
node_idunique ID for this node
platform_idID of platform that is the node parent
i_valinteger
f_valfloat (for example, 0% - 100% for CPU availability)
s_valstring

Component type codes

component.component_type code definitions
codedefinition
0host
1CPU
2IO
3network
4memory
5software

Event type codes

Below are code ranges and definitions for the fields above.

Event id's up to 10,000 are reserved; the rest can be user defined.

event_trace.event_type code definitions
codedefinition
0unavailability
1availability
2*user present
3*CPU threshold exceeded

(*) These codes are specifically for the Notre Dame trace.


Event end reason codes

The failure classification below is based on the traces from LANL.

event_trace.event_end_reason code ranges
code rangecategory
NULLnot reported
0reported as undetermined
1-999infrastructure
1000-1999hardware
2000-2999IO
3000-3999network
4000-4999software
5000-5999human error
6000-6999user
7000end of measurement
event_trace.event_end_reason code definitions
codedefinition
NULLnot reported
0reported as undetermined
1Infrastructure: Infrastructure
2Infrastructure: Power Outage
3Infrastructure: Power Spike
4Infrastructure: Chillers
5Infrastructure: Environment
6Infrastructure: UPS
1000Hardware: Hardware
1001Hardware: 40MM Cooling Fan
1002Hardware: Bach Plane Assembly
1003Hardware: CD ROM
1004Hardware: Console Interface Module
1005Hardware: CPU
1006Hardware: DG Board
1007Hardware: Fan
1008Hardware: Fan Assembly
1009Hardware: GFX Power Supply
1010Hardware: Graphics Accel Hdwr
1011Hardware: Graphics Video Card
1012Hardware: Heatsink bracket
1013Hardware: IO6
1014Hardware: IOS Buffer Memory
1015Hardware: IOS CPU
1016Hardware: KGPSA
1017Hardware: Ktown Board
1018Hardware: Maintenance
1019Hardware: Memory Dimm
1020Hardware: Memory Dimm/CPU
1021Hardware: Memory Module
1022Hardware: MIA
1023Hardware: Mid-plane
1024Hardware: MMB
1025Hardware: Module Assembly
1026Hardware: MSC Board
1027Hardware: OCP
1028Hardware: PCI Back Plane
1029Hardware: Power cord
1030Hardware: Power Supply
1031Hardware: Rack Power Distribution Unit
1032Hardware: Riser Card
1033Hardware: RM Board
1034Hardware: SSD Logic
1035Hardware: SSD Memory Module
1036Hardware: System Board
1037Hardware: System Controller
1038Hardware: Temp Probe
1039Hardware: Term Server
1040Hardware: Vhisp
1041Hardware: WACS Logic
1042Hardware: Wire Harness
1043Hardware: Xtown Board
1044Hardware: Node Board
2000IO: IO
2001IO: Disk Cabinet
2002IO: Disk Drive
2003IO: Drive Cage
2004IO: Fddi
2005IO: Fibre Cable
2006IO: Fibre Channel Port Adapter
2007IO: Fibre Drive
2008IO: Fibre HBA
2009IO: Fibre Raid Controller
2010IO: Fibre Raid LCC card
2011IO: Fibre Raid Midplane
2012IO: Fibre Raid Power Supply
2013IO: IDE Cable
2014IO: IOS Disk Logic
2015IO: PCI Fibre Channel Adapter
2016IO: PCI IO Module
2017IO: PCI SCSI Controller
2018IO: PCI Shoebox
2019IO: SAN Appliance
2020IO: SAN Controller
2021IO: SAN Disk Drive
2022IO: SAN Fiber Cable
2023IO: SAN GBIC
2024IO: SAN Shelf
2025IO: SAN Switch
2026IO: SCSI Adapter Card
2027IO: SCSI Controller
2028IO: SCSI Drive
2029IO: SCSI Back Plane
2030IO: HSV
2031IO: IO Controller
3000Network: Network
3001Network: 1 GBit Ethernet Card
3002Network: 100 MBit Ethernet Card
3003Network: Ethernet Cable
3004Network: Ethernet Copper Cable
3005Network: Ethernet Fiber Cable
3006Network: Ethernet Switch
3007Network: GE Board
3008Network: Gig E Connection
3009Network: Gig E Switch
3010Network: Interconnect
3011Network: Interconnect Cable
3012Network: Interconnect Interface
3013Network: Interconnect Misc
3014Network: Interconnect Soft Error
3015Network: Interconnect Switch
3016Network: PCI Ethernet Board
3017Network: PCI GBIT Ethernet Board
3018Network: Router Board
3019Network: Site Ethernet Switch
3020Network: Site Network Interface
3021Network: Console Network Device
3022Network: ELAN
4000Software: Software
4001Software: Disk IO, firmware and storage
4002Software: MPI, PVM, Array services
4003Software: Cluster File System
4004Software: Cluster Software
4005Software: Compilers and libraries
4006Software: DST
4007Software: DST-Scan for errors /scratch
4008Software: DST-Upgrd/Install OS sftw
4009Software: DST-Upgrd/Instl 3rdParty Sftw
4010Software: DST-Upgrd/Instl OS Sftw
4011Software: Interconnect
4012Software: IOS Software
4013Software: Kernel software
4014Software: Modify kernel parameters
4015Software: Modify system config files
4016Software: Network
4017Software: NFS
4018Software: OS
4019Software: Parallel File System
4020Software: Patch Install
4021Software: Resource Mgmt System
4022Software: Scheduler Software
4023Software: Scratch Drive
4024Software: Scratch FS
4025Software: Security Software
4026Software: Upgrade/Install 3rd Party Sftw
4027Software: Upgrade/Install OS sftw
4028Software: User code
4029Software: Vizscratch FS
4030Software: Applications
5000Human Error: Human Error
6000User: User
6001User: Mouse Activity
6002User: Keyboard Activity
6003User: Shutdown

Page Actions

Recent Changes

Group & Page

Back Links