When viewing the Technical Program schedule, on the far righthand side
is a column labeled "PLANNER." Use this planner to build your own
schedule. Once you select an event and want to add it to your personal
schedule, just click on the calendar icon of your choice (outlook
calendar, ical calendar or google calendar) and that event will be
stored there. As you select events in this manner, you will have your
own schedule to guide you through the week.
You can also create your personal schedule on the SC11 app (Boopsie) on your smartphone. Simply select a session you want to attend and "add" it to your plan. Continue in this manner until you have created your own personal schedule. All your events will appear under "My Event Planner" on your smartphone.
I/O Workload Analysis with Server-side Data Collection
SESSION: Research Poster Reception
EVENT TYPE: ACM Student Research Competition Poster, Poster, Electronic Poster
TIME: 5:15PM - 7:00PM
SESSION CHAIR: Bernd Mohr
AUTHOR(S):Andrew C. Uselton, Daniela Ushizima
ROOM:WSCC North Galleria 2nd/3rd Floors
ABSTRACT: The statistical properties of data movement to and from mass storage (I/O) on a high-performance computer (HPC) system re- veal the system-wide coordination of transactions from the com- pute nodes to the I/O nodes. This research exploits server-side observations to isolate much of the I/O traffic into events that are closely related to, though not identical with, those trans- actions. The statistics of those events demonstrate a pervasive under-performance of a large fraction of the system workload. This analysis documents both the breadth and the severity of the problem on one HPC system.
In addition, we present a new visualization scheme for the time series of I/O observations. This scheme organizes and displays intricate numerical content in a meaningful and easy to under- stand graphical representation.
Chair/Author Details:
Bernd Mohr (Chair) - Juelich Supercomputing Centre
Andrew C. Uselton - Lawrence Berkeley National Laboratory
Daniela Ushizima - Lawrence Berkeley National Laboratory