Changes between Version 2 and Version 3 of PortalFeatures

Timestamp:

Sep 21, 2010, 8:56:01 AM (14 years ago)

Author:

davea

Comment:

--

PortalFeatures

@@ -1 +1 @@
 = BOINC support for science portals =
 
-A '''science portal''' is a web site serving a group of scientists in a particular area.
-In addition to other features, science portals typically offer a facility
-for computing, in which scientists can submit, via a web interface,
+A '''science portal''' is a web site serving a group of scientists.
+Science portals typically offer a computing service
+in which scientists can submit, via a web interface,
 sets of jobs to be run against standard applications.
-Currently these jobs are run on clusters or Grids.
+Current science portals run these jobs on clusters or Grids.
 
-This document proposes additions to BOINC to facilitate using
-a BOINC project as a computing resource for science portals.
-There are two related parts:
+This document proposes two related additions to BOINC to facilitate using
+a BOINC project as a computing resource for science portals:
 
  * A mechanism for allocating computing resources among scientists
@@ -16 +15 @@
 == Computing share ==
 
-Demand for computing power may exceed supply,
+Demand for a portal's computing power may exceed supply,
 in which case we need a mechanism for dividing the supply among scientists.
 Assume that every job is associated with a particular BOINC user,
 representing either a scientist or some other organizational entity,
-and that each such user has a numeric '''computing share''' proportional to
+and that each such user has a numeric '''computing share''' representing
 the fraction of the computing resource they should get.
 
-The way in which computing shares are determined is outside the scope,
+The way in which computing shares are determined is outside our scope,
 but some possibilities are:
 
@@ -35 +34 @@
 
 What are the precise semantics of computing share?
-Ideally this should accommodate two classes of scientists:
+Ideally the mechanism should accommodate two classes of scientists:
 
- * '''Throughput-oriented''': those who have an infinite stream of jobs.
-   They want maximum throughput, and don't care about the turnaround times
+ * '''Throughput-oriented''': those who have an infinite stream of jobs,
+   want maximum throughput, and don't care about the turnaround times
    of individual jobs.
    
@@ -59 +58 @@
 by the job's resources running at peak speed for the job's elapsed time).
 
-In this scheme, latency-oriented user can build up a debt that allows their
+In this scheme, latency-oriented users can build up a debt that allows their
 batches (if they are sufficiently infrequent) to get the full computing resource
 and finish as fast as possible.