Tools

I Want To

Home » Historical Section » Show all

Historical Section

The Historical Section includes all traces that are older than 10 years.

The following traces are free to download under the terms of the SNIA Trace Data Files Download License. Please note that cookies must be enabled within your browser in order to download traces.
For questions about downloading using a shell script, see Using Shell Scripts, and for more information about downloading using a Windows batch script, see Using Batch Scripts.

Displaying Traces 1–10 of 24 in total

Show per page

View Additional Columns

Trace Name	Details	Related Tools	Year Recorded	Timespan	Record Count	File Size
FIU Traces	Traces collected at FIU.	These traces can be decoded using blkparse. This utility is available on all standard Linux systems.	2008-2009	3 months	475 Million	28.8 GB
Microsoft Production Server Traces	Traces of several production servers at Microsoft, as described in the IEEE International Symposium on Workload Characterization, 2008. Long Description Because of the size of the traces, the BuildServer traces have been repackaged by IOTTA into eight zip files. The first seven files are divided into one for each of the first seven timestamped hours in the original traces. The last file contains traces of the remaining 18 traced hours, in which the activity was much lighter. All eight zip files contain the same Readme.* and Disclaimer files. They are designed so that if all are unpacked in the same directory, the original trace collection will be recreated. Short Description		2007-2008	4 months	1 Billion	18.2 GB
Microsoft Enterprise Traces	Traces collected at Microsoft using the event tracing for Windows framework.		2007-2008	4 months	2.6 Billion	25.1 GB
MSR Cambridge Traces	1-week block I/O traces of enterprise servers at Microsoft Long Description 1-week block I/O traces of enterprise servers at Microsoft Research Cambridge. The citation for the MSRC traces can be found here. Short Description		2007	7 days	434 Million	4.94 GB
Second Animation Dataset	NFS traces of an animation company. Long Description Traces collected for the paper "Capture, conversion, and analysis of an intense NFS workload" by Eric Anderson, FAST 2009. Short Description	All of the traces have been stored in DataSeries (ds) format; a tool to read the traces can be found on this Github page.	2007	10 months	144 Billion	3.4 TB
TraceFS Sample Traces	Sample traces collected with the TraceFS system. Long Description Sample traces of three benchmark runs collected with the TraceFS tracing system. Additional information about TraceFS can be found at the following URL: http://www.filesystems.org/project-tracefs.html Short Description	This traces are stored in a binary format. The code for opening them can be found at http://www.filesystems.org/project-tracefs.html.	2007	13 days	1 Million	57.7 MB
Animation Dataset	NFS traces from an animation company, taken at a number of different points. Long Description Each set of data is a single contiguous trace from a single network location. Each set has been broken into downloadable ~4 GB chunks by iotta. Download the index.html file for more information. Short Description	All of the traces have been stored in DataSeries (ds) format; a tool to read the traces can be found on this Github page.	2003-2004	6 months	55 Billion	506 GB
Harvard SOS Traces	Traces from Harvard campus and departmental servers Long Description Software to process the NFSdump format is available here. Further information about the traces can be found on the project page. Short Description		2001-2003	over 1 year		158 GB
Multimedia file sizes	File-size data collected on various OSes, including measurements of multimedia files. Long Description File-size data collected for the paper "A Study of Irregularities in File-Size Distributions". Short Description	This trace has no related tools yet.	2001	21 days		17.1 MB
Microsoft Longitudinal Study	The raw data used for the FAST 2007 paper "A Five Year Study Of File System Metadata" by Nitin Agarwal, William J. Bolosky, John R. Douceur, and Jacob R. Lorch. There are five years worth of snapshot data, for years from 2000 to 2004. Long Description Because of the size of the traces, they have been repackaged by IOTTA into 22 zip files. Each zip files contains information from the original snapshot, directory, and file info files, repackaged by user. More information on how the files were repackaged can be found in the readme-iotta.txt file found in each zip file. Short Description		2000-2004	over 4 years	5 Billion	91.1 GB