/** * Pushes a host back onto the queue of available hosts and attempts to launch a waiting * experiment (if any). * * @param hostNum the index of the host to push back onto the queue of available hosts */ protected synchronized void availableHost(int hostNum) { if (hostNum >= 0) { if (m_remoteHostFailureCounts[hostNum] < MAX_FAILURES) { m_remoteHostsQueue.push(new Integer(hostNum)); } else { notifyListeners( false, true, false, "Max failures exceeded for host " + ((String) m_remoteHosts.elementAt(hostNum)) + ". Removed from host list."); m_removedHosts++; } } // check for all sub exp complete or all hosts failed or failed count // exceeded if (m_failedCount == (MAX_FAILURES * m_remoteHosts.size())) { abortExperiment(); notifyListeners( false, true, true, "Experiment aborted! Max failures " + "exceeded on all remote hosts."); return; } if ((getSplitByDataSet() && (m_baseExperiment.getDatasets().size() == m_finishedCount)) || (getSplitByProperty() && (m_baseExperiment.getPropertyArrayLength() == m_finishedCount)) || (!getSplitByDataSet() && !getSplitByProperty() && (getRunUpper() - getRunLower() + 1) == m_finishedCount)) { notifyListeners(false, true, false, "Experiment completed successfully."); notifyListeners(false, true, true, postExperimentInfo()); return; } if (checkForAllFailedHosts()) { return; } if (m_experimentAborted && (m_remoteHostsQueue.size() + m_removedHosts) == m_remoteHosts.size()) { notifyListeners(false, true, true, "Experiment aborted. All remote tasks " + "finished."); } if (!m_subExpQueue.empty() && !m_experimentAborted) { if (!m_remoteHostsQueue.empty()) { int availHost, waitingExp; try { availHost = ((Integer) m_remoteHostsQueue.pop()).intValue(); waitingExp = ((Integer) m_subExpQueue.pop()).intValue(); launchNext(waitingExp, availHost); } catch (Exception ex) { ex.printStackTrace(); } } } }
/** * Prepares a remote experiment for running, creates sub experiments * * @throws Exception if an error occurs */ @Override public void initialize() throws Exception { if (m_baseExperiment == null) { throw new Exception("No base experiment specified!"); } m_experimentAborted = false; m_finishedCount = 0; m_failedCount = 0; m_RunNumber = getRunLower(); m_DatasetNumber = 0; m_PropertyNumber = 0; m_CurrentProperty = -1; m_CurrentInstances = null; m_Finished = false; if (m_remoteHosts.size() == 0) { throw new Exception("No hosts specified!"); } // initialize all remote hosts to available m_remoteHostsStatus = new int[m_remoteHosts.size()]; m_remoteHostFailureCounts = new int[m_remoteHosts.size()]; m_remoteHostsQueue = new Queue(); // prime the hosts queue for (int i = 0; i < m_remoteHosts.size(); i++) { m_remoteHostsQueue.push(new Integer(i)); } // set up sub experiments m_subExpQueue = new Queue(); int numExps; if (getSplitByDataSet()) { numExps = m_baseExperiment.getDatasets().size(); } else if (getSplitByProperty()) { numExps = m_baseExperiment.getPropertyArrayLength(); } else { numExps = getRunUpper() - getRunLower() + 1; } m_subExperiments = new Experiment[numExps]; m_subExpComplete = new int[numExps]; // create copy of base experiment SerializedObject so = new SerializedObject(m_baseExperiment); if (getSplitByDataSet()) { for (int i = 0; i < m_baseExperiment.getDatasets().size(); i++) { m_subExperiments[i] = (Experiment) so.getObject(); // one for each data set DefaultListModel temp = new DefaultListModel(); temp.addElement(m_baseExperiment.getDatasets().get(i)); m_subExperiments[i].setDatasets(temp); m_subExpQueue.push(new Integer(i)); } } else if (getSplitByProperty()) { for (int i = 0; i < m_baseExperiment.getPropertyArrayLength(); i++) { m_subExperiments[i] = (Experiment) so.getObject(); Object[] a = new Object[1]; a[0] = m_baseExperiment.getPropertyArrayValue(i); m_subExperiments[i].setPropertyArray(a); m_subExpQueue.push(new Integer(i)); } } else { for (int i = getRunLower(); i <= getRunUpper(); i++) { m_subExperiments[i - getRunLower()] = (Experiment) so.getObject(); // one run for each sub experiment m_subExperiments[i - getRunLower()].setRunLower(i); m_subExperiments[i - getRunLower()].setRunUpper(i); m_subExpQueue.push(new Integer(i - getRunLower())); } } }