Beispiel #1
0
 public List<PingData> findAllViews(Promise<JoinRsp> promise) {
   int num_expected_mbrs =
       Math.max(
           max_found_members,
           Math.max(num_initial_members, view != null ? view.size() : num_initial_members));
   max_found_members = Math.max(max_found_members, num_expected_mbrs);
   return findMembers(promise, num_expected_mbrs, false, getViewId());
 }
Beispiel #2
0
    /**
     * Merge all MergeData. All MergeData elements should be disjunct (both views and digests).
     * However, this method is prepared to resolve duplicate entries (for the same member).
     * Resolution strategy for views is to merge only 1 of the duplicate members. Resolution
     * strategy for digests is to take the higher seqnos for duplicate digests.
     *
     * <p>After merging all members into a Membership and subsequent sorting, the first member of
     * the sorted membership will be the new coordinator. This method has a lock on merge_rsps.
     *
     * @param merge_rsps A list of MergeData items. Elements with merge_rejected=true were removed
     *     before. Is guaranteed not to be null and to contain at least 1 member.
     */
    private MergeData consolidateMergeData(Vector<MergeData> merge_rsps) {
      long logical_time = 0; // for new_vid
      Membership new_mbrs = new Membership();
      Vector<View> subgroups =
          new Vector<View>(11); // contains a list of Views, each View is a subgroup

      for (MergeData tmp_data : merge_rsps) {
        View tmp_view = tmp_data.getView();
        if (tmp_view != null) {
          ViewId tmp_vid = tmp_view.getVid();
          if (tmp_vid != null) {
            // compute the new view id (max of all vids +1)
            logical_time = Math.max(logical_time, tmp_vid.getId());
          }
          // merge all membership lists into one (prevent duplicates)
          new_mbrs.add(tmp_view.getMembers());
          subgroups.addElement((View) tmp_view.clone());
        }
      }

      // the new coordinator is the first member of the consolidated & sorted membership list
      new_mbrs.sort();
      Address new_coord = new_mbrs.size() > 0 ? new_mbrs.elementAt(0) : null;
      if (new_coord == null) {
        if (log.isErrorEnabled()) log.error("new_coord == null");
        return null;
      }
      // should be the highest view ID seen up to now plus 1
      ViewId new_vid = new ViewId(new_coord, logical_time + 1);

      // determine the new view
      MergeView new_view = new MergeView(new_vid, new_mbrs.getMembers(), subgroups);

      // determine the new digest
      Digest new_digest = consolidateDigests(merge_rsps, new_mbrs.size());
      if (new_digest == null) {
        if (log.isErrorEnabled())
          log.error("Merge leader " + gms.local_addr + ": could not consolidate digest for merge");
        return null;
      }
      if (log.isDebugEnabled())
        log.debug(
            "Merge leader "
                + gms.local_addr
                + ": consolidated view="
                + new_view
                + "\nconsolidated digest="
                + new_digest);
      return new MergeData(gms.local_addr, new_view, new_digest);
    }
Beispiel #3
0
    /**
     * Merge all MergeData. All MergeData elements should be disjunct (both views and digests).
     * However, this method is prepared to resolve duplicate entries (for the same member).
     * Resolution strategy for views is to merge only 1 of the duplicate members. Resolution
     * strategy for digests is to take the higher seqnos for duplicate digests.
     *
     * <p>After merging all members into a Membership and subsequent sorting, the first member of
     * the sorted membership will be the new coordinator. This method has a lock on merge_rsps.
     *
     * @param merge_rsps A list of MergeData items. Elements with merge_rejected=true were removed
     *     before. Is guaranteed not to be null and to contain at least 1 member.
     */
    private MergeData consolidateMergeData(List<MergeData> merge_rsps) {
      long logical_time = 0; // for new_vid
      List<View> subgroups =
          new ArrayList<View>(11); // contains a list of Views, each View is a subgroup
      Collection<Collection<Address>> sub_mbrships = new ArrayList<Collection<Address>>();

      for (MergeData tmp_data : merge_rsps) {
        View tmp_view = tmp_data.getView();
        if (tmp_view != null) {
          ViewId tmp_vid = tmp_view.getVid();
          if (tmp_vid != null) {
            // compute the new view id (max of all vids +1)
            logical_time = Math.max(logical_time, tmp_vid.getId());
          }
          // merge all membership lists into one (prevent duplicates)
          sub_mbrships.add(new ArrayList<Address>(tmp_view.getMembers()));
          subgroups.add(tmp_view.copy());
        }
      }

      // determine the new digest
      Digest new_digest = consolidateDigests(merge_rsps, merge_rsps.size());
      if (new_digest == null) return null;

      // remove all members from the new member list that are not in the digest
      Collection<Address> digest_mbrs = new_digest.getMembers();
      for (Collection<Address> coll : sub_mbrships) coll.retainAll(digest_mbrs);

      List<Address> merged_mbrs = gms.computeNewMembership(sub_mbrships);

      // the new coordinator is the first member of the consolidated & sorted membership list
      Address new_coord = merged_mbrs.isEmpty() ? null : merged_mbrs.get(0);
      if (new_coord == null) return null;

      // should be the highest view ID seen up to now plus 1
      ViewId new_vid = new ViewId(new_coord, logical_time + 1);

      // determine the new view
      MergeView new_view = new MergeView(new_vid, merged_mbrs, subgroups);

      if (log.isTraceEnabled())
        log.trace(
            gms.local_addr
                + ": consolidated view="
                + new_view
                + "\nconsolidated digest="
                + new_digest);
      return new MergeData(gms.local_addr, new_view, new_digest);
    }
Beispiel #4
0
  /** The coordinator itself wants to leave the group */
  public void leave(Address mbr) {
    if (mbr == null) {
      if (log.isErrorEnabled()) log.error(Util.getMessage("MemberSAddressIsNull"));
      return;
    }
    if (mbr.equals(gms.local_addr)) leaving = true;
    gms.getViewHandler().add(new Request(Request.LEAVE, mbr, false));
    gms.getViewHandler()
        .stop(true); // wait until all requests have been processed, then close the queue and leave

    // If we're the coord leaving, ignore gms.leave_timeout:
    // https://issues.jboss.org/browse/JGRP-1509
    long timeout = (long) (Math.max(gms.leave_timeout, gms.view_ack_collection_timeout) * 1.10);
    gms.getViewHandler().waitUntilCompleted(timeout);
  }
Beispiel #5
0
  /**
   * Computes the next view. Returns a copy that has <code>old_mbrs</code> and <code>suspected_mbrs
   * </code> removed and <code>new_mbrs</code> added.
   */
  public View getNextView(
      Collection<Address> new_mbrs,
      Collection<Address> old_mbrs,
      Collection<Address> suspected_mbrs) {
    synchronized (members) {
      ViewId view_id = view != null ? view.getViewId() : null;
      if (view_id == null) {
        log.error("view_id is null");
        return null; // this should *never* happen !
      }
      long vid = Math.max(view_id.getId(), ltime) + 1;
      ltime = vid;
      Membership tmp_mbrs = tmp_members.copy(); // always operate on the temporary membership
      tmp_mbrs.remove(suspected_mbrs);
      tmp_mbrs.remove(old_mbrs);
      tmp_mbrs.add(new_mbrs);
      List<Address> mbrs = tmp_mbrs.getMembers();
      Address new_coord = local_addr;
      if (!mbrs.isEmpty()) new_coord = mbrs.get(0);
      View v = new View(new_coord, vid, mbrs);

      // Update membership (see DESIGN for explanation):
      tmp_members.set(mbrs);

      // Update joining list (see DESIGN for explanation)
      if (new_mbrs != null) {
        for (Address tmp_mbr : new_mbrs) {
          if (!joining.contains(tmp_mbr)) joining.add(tmp_mbr);
        }
      }

      // Update leaving list (see DESIGN for explanations)
      if (old_mbrs != null) {
        for (Address addr : old_mbrs) {
          if (!leaving.contains(addr)) leaving.add(addr);
        }
      }
      if (suspected_mbrs != null) {
        for (Address addr : suspected_mbrs) {
          if (!leaving.contains(addr)) leaving.add(addr);
        }
      }
      return v;
    }
  }
Beispiel #6
0
  public Object down(Event evt) {
    switch (evt.getType()) {
      case Event.MSG: // Add UnicastHeader, add to AckSenderWindow and pass down
        Message msg = (Message) evt.getArg();
        Address dst = msg.getDest();

        /* only handle unicast messages */
        if (dst == null || msg.isFlagSet(Message.NO_RELIABILITY)) break;

        if (!running) {
          if (log.isTraceEnabled())
            log.trace("discarded message as start() has not yet been called, message: " + msg);
          return null;
        }

        SenderEntry entry = send_table.get(dst);
        if (entry == null) {
          entry = new SenderEntry(getNewConnectionId());
          SenderEntry existing = send_table.putIfAbsent(dst, entry);
          if (existing != null) entry = existing;
          else {
            if (log.isTraceEnabled())
              log.trace(
                  local_addr
                      + ": created connection to "
                      + dst
                      + " (conn_id="
                      + entry.send_conn_id
                      + ")");
            if (cache != null && !members.contains(dst)) cache.add(dst);
          }
        }

        short send_conn_id = entry.send_conn_id;
        long seqno = entry.sent_msgs_seqno.getAndIncrement();
        long sleep = 10;
        while (running) {
          try {
            msg.putHeader(
                this.id,
                Unicast2Header.createDataHeader(seqno, send_conn_id, seqno == DEFAULT_FIRST_SEQNO));
            entry.sent_msgs.add(seqno, msg); // add *including* UnicastHeader, adds to retransmitter
            if (conn_expiry_timeout > 0) entry.update();
            break;
          } catch (Throwable t) {
            if (!running) break;
            if (log.isWarnEnabled()) log.warn("failed sending message", t);
            Util.sleep(sleep);
            sleep = Math.min(5000, sleep * 2);
          }
        }

        if (log.isTraceEnabled()) {
          StringBuilder sb = new StringBuilder();
          sb.append(local_addr)
              .append(" --> DATA(")
              .append(dst)
              .append(": #")
              .append(seqno)
              .append(", conn_id=")
              .append(send_conn_id);
          if (seqno == DEFAULT_FIRST_SEQNO) sb.append(", first");
          sb.append(')');
          log.trace(sb);
        }

        try {
          down_prot.down(evt);
          num_msgs_sent++;
        } catch (Throwable t) {
          log.warn("failed sending the message", t);
        }
        return null; // we already passed the msg down

      case Event.VIEW_CHANGE: // remove connections to peers that are not members anymore !
        View view = (View) evt.getArg();
        List<Address> new_members = view.getMembers();
        Set<Address> non_members = new HashSet<Address>(send_table.keySet());
        non_members.addAll(recv_table.keySet());

        members = new_members;
        non_members.removeAll(new_members);
        if (cache != null) cache.removeAll(new_members);

        if (!non_members.isEmpty()) {
          if (log.isTraceEnabled()) log.trace("removing non members " + non_members);
          for (Address non_mbr : non_members) removeConnection(non_mbr);
        }
        break;

      case Event.SET_LOCAL_ADDRESS:
        local_addr = (Address) evt.getArg();
        break;
    }

    return down_prot.down(evt); // Pass on to the layer below us
  }
Beispiel #7
0
  /**
   * Sets the new view and sends a VIEW_CHANGE event up and down the stack. If the view is a
   * MergeView (subclass of View), then digest will be non-null and has to be set before installing
   * the view.
   */
  public void installView(View new_view, Digest digest) {
    ViewId vid = new_view.getVid();
    List<Address> mbrs = new_view.getMembers();
    ltime =
        Math.max(
            vid.getId(),
            ltime); // compute the logical time, regardless of whether the view is accepted

    // Discards view with id lower than or equal to our own. Will be installed without check if it
    // is the first view
    if (view != null) {
      ViewId view_id = view.getViewId();
      int rc = vid.compareToIDs(view_id);
      if (rc <= 0) {
        if (log.isWarnEnabled()
            && rc < 0
            && log_view_warnings) { // only scream if view is smaller, silently discard same views
          log.warn(
              local_addr
                  + ": received view < current view;"
                  + " discarding it (current vid: "
                  + view_id
                  + ", new vid: "
                  + vid
                  + ')');
        }
        return;
      }
    }

    /* Check for self-inclusion: if I'm not part of the new membership, I just discard it.
    This ensures that messages sent in view V1 are only received by members of V1 */
    if (!mbrs.contains(local_addr)) {
      if (log.isWarnEnabled() && log_view_warnings)
        log.warn(local_addr + ": not member of view " + new_view.getViewId() + "; discarding it");
      return;
    }

    if (digest != null) {
      if (new_view instanceof MergeView) mergeDigest(digest);
      else setDigest(digest);
    }

    if (log.isDebugEnabled()) log.debug(local_addr + ": installing view " + new_view);

    Event view_event;
    synchronized (members) {
      view = new View(new_view.getVid(), new_view.getMembers());
      view_event = new Event(Event.VIEW_CHANGE, new_view);

      // Set the membership. Take into account joining members
      if (!mbrs.isEmpty()) {
        members.set(mbrs);
        tmp_members.set(members);
        joining.removeAll(mbrs); // remove all members in mbrs from joining
        // remove all elements from 'leaving' that are not in 'mbrs'
        leaving.retainAll(mbrs);

        tmp_members.add(joining); // add members that haven't yet shown up in the membership
        tmp_members.remove(
            leaving); // remove members that haven't yet been removed from the membership

        // add to prev_members
        for (Address addr : mbrs) {
          if (!prev_members.contains(addr)) prev_members.add(addr);
        }
      }

      Address coord = determineCoordinator();
      if (coord != null && coord.equals(local_addr) && !haveCoordinatorRole()) {
        becomeCoordinator();
      } else {
        if (haveCoordinatorRole() && !local_addr.equals(coord)) {
          becomeParticipant();
          merge_ack_collector.reset(null); // we don't need this one anymore
        }
      }
    }

    // - Changed order of passing view up and down (http://jira.jboss.com/jira/browse/JGRP-347)
    // - Changed it back (bela Sept 4 2007): http://jira.jboss.com/jira/browse/JGRP-564
    // - Moved sending up view_event out of the synchronized block (bela Nov 2011)
    down_prot.down(view_event); // needed e.g. by failure detector or UDP
    up_prot.up(view_event);

    List<Address> tmp_mbrs = new_view.getMembers();
    ack_collector.retainAll(tmp_mbrs);
    merge_ack_collector.retainAll(tmp_mbrs);

    if (new_view instanceof MergeView) merger.forceCancelMerge();

    if (stats) {
      num_views++;
      prev_views.add(new Tuple<View, Long>(new_view, System.currentTimeMillis()));
    }
  }