Skip to main content
zenodoopen

ENTICE download speed measurements

<p>A sample of a measurements dataset. Monitoring of a general purpose Cloud storages (e.g. such as AWS S3) is a part of ENTICE Pareto-SLA component. This dataset has been obtained by performing downloads of objects with random data of various sizes, ranging from 1 kB to 1 GB. Each file object has been generated by dd tool: dd if=/dev/urandom of=rand-1M.bin bs=1M count=1. On the server side a Minio S3 server has been setup with a Nginx gateway. The client who performed downloads was residing in the same local 1 Gbps ethernet network as the server. On the server side, network QoS has been controlled through a Linux tc netem tool, emulating various QoS conditions for the packet delay, jitter and packet loss.</p> <p>The dataset contains the following headers:</p> <p>Timestamp - the timestamp of a measurement performed.</p> <p>Client IP - the IP address of a client - anonymised.</p> <p>Server IP - the IP address of a server - anonymised.</p> <p>QoS - min|avg|max|stdev|ploss denoting minimum, average and maximum packet round-trip-time (RTT) between the server and the client, respectively, followed by the standard deviation of the RTT and emulated packet loss with the tc tool, expressed as a percentage.</p> <p>Object size [B] - the size of the file object in bytes.</p> <p>Download time [s] - the download time of the file object from the client perspective.</p> <p>Download speed [B/s]&nbsp; - the ratio (Object size[B]) / (Download time[s]).</p>

ShareScore

44/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
4
Access
16
Reuse readiness
8
Engagement
8

Topics