Changes between Version 4 and Version 5 of CreditNew

Timestamp:

Nov 3, 2009, 10:23:53 AM (14 years ago)

Author:

davea

Comment:

--

CreditNew

@@ -199 +199 @@
 
 Notes:
+ * This mechanism reduces the claimed credit of hosts
+   that are less efficient than average,
+   and increases the claimed credit of hosts that are more efficient
+   than average.
  * VNPFC* is averaged over jobs, not hosts.
- * Both averages are exponential recent averages,
-   so that they respond to changes in job sizes and app versions characteristics.
  * This assumes that all hosts are sent the same distribution of jobs.
    There are two situations where this is not the case:
    a) job-size matching, and b) GPUGrid.net's scheme for sending
    some (presumably larger) jobs to GPUs with more processors.
+   This can be dealt with using app units (see below).
+
+== Computing averages ==
+
+We need to compute averages carefully because
+
+ * The quantities being averaged may gradually change over time
+   (e.g. average job size may change,
+   app version efficiency may change as new versions are deployed)
+   and we need to track this.
+ * A given sample may be wildly off,
+   and we can't let this mess up the average.
+
+In addition, we may as well maintain the standard deviation
+of the quantities,
+although the current system doesn't use it.
+
+So for each quantity we maintain the following object:
+{{{
+struct STATS {
+    int nsamples;
+    double sum;
+    double exp_avg;
+
+    void update(double sample) {
+    }
+
+    double mean() {
+    }
+};
+}}}
+
+== Jobs versus app units ==
    To deal with this, we can weight jobs by workunit.rsc_flops_est.
 
-== Computing averages ==
- * Averages are computed as a moving average,
-   so that the system will respond quickly as job sizes change
-   or new app versions are deployed.
-
-== Jobs versus app units ==
+If a project changes between jobs to app units,
+it must reset
 
 == Cross-project scaling factors ==
@@ -253 +284 @@
   subsequent jobs will be replicated.
 
+== Job runtime estimates ==
+
 == Implementation ==