Hola Guys! We're currently gathering some numbers regarding the performance of akubra-hdfs compared to the default akubra-fs implementation. All the numbers we gathered show an expected rise in e.g. ingest times when using akubra-hdfs. But when measuring the retrieve times with a sample set of small files (0.15MB - 2.1 MB) of 18000 files the results show a unintuitivly better result for akubra-hdfs compared to the default akubra implementation. Do you guys have an explanation for this behaviour? The only thing we could think of was that the HDFS Cluster does some caching and has better network latency than the local Harddisks.
I'll try to attach the images although i dont know if the list policy allows it ;) Thanks! Frank -- Frank Asseg e-Science IT, Development & Applied Research Phone +49 7247-235- Fax +49 7247 808-133 frank.as...@fiz-karlsruhe.de FIZ Karlsruhe – Leibniz Institute for Information Infrastructure Hermann-von-Helmholtz-Platz 1 76344 Eggenstein-Leopoldshafen, Germany www.fiz-karlsruhe.de ------------------------------------------------------- Fachinformationszentrum Karlsruhe, Gesellschaft für wissenschaftlich-technische Information mbH. Sitz der Gesellschaft: Eggenstein-Leopoldshafen, Amtsgericht Mannheim HRB 101892. Geschäftsführerin: Sabine Brünger-Weilandt. Vorsitzender des Aufsichtsrats: MinDirig Dr. Thomas Greiner.
<<attachment: sample1_filesize.png>>
<<attachment: get_quartil_samples.png>>
------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________ Fedora-commons-developers mailing list Fedora-commons-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/fedora-commons-developers
