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 34 in total
Show
per page
| Trace Name | Details | Related Tools | Year Recorded | Timespan | Record Count | File Size | Actions |
|---|---|---|---|---|---|---|---|
| UBC-Dedup |
Traces collected for the paper "A Study of Practical Deduplication" by Dutch T. Meyer and William J. Bolosky of The University of British Columbia and Microsoft Research
|
2009 | 4 months | 3.4 TB |
|
||
| Yahoo Cluster Files Traces |
This dataset contains total number of files, total file size, number of file accesses, number of days between the first access and the most recent access, file distribution, deletion rate of files and directories, creation rate of files and directories in a dilithium-gold cluster. The size of this dataset is 2.3K. Due to access restrictions, these traces are hosted externally
|
2009-2010 | about 1 year | 0 Bytes |
|
||
| FIU Traces | 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 |
|
|
| Los Alamos Workstation File System Statistics |
Collections of data are related to storage. File system statistics gathered from backup information for 3000 plus LANL workstations. File system statistics gathered from backup information for 3000 plus LANL workstations.The data is contained in a tar file containing three CSV files that represent the three primary types of workstations used at LANL (MAC, UNIX, Windows).
|
2008-2009 | 11 months | 0 Bytes |
|
||
| Microsoft Production Server Traces |
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.
|
2007-2008 | 4 months | 1 Billion | 18.2 GB |
|
|
| Microsoft Enterprise Traces | 2007-2008 | 4 months | 2.6 Billion | 25.1 GB |
|
||
| MSR Cambridge Traces |
1-week block I/O traces of enterprise servers at Microsoft Research Cambridge. The citation for the MSRC traces can be found here.
|
2007 | 8 days | 434 Million | 4.94 GB |
|
|
| Second Animation Dataset |
Traces collected for the paper "Capture, conversion, and analysis of an intense NFS workload" by Eric Anderson, FAST 2009.
|
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 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 |
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 |
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.
|
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 |
|