/**
* Sends the new view and digest to all subgroup coordinors in coords. Each coord will in turn
*
* <ol>
* <li>broadcast the new view and digest to all the members of its subgroup (MergeView)
* <li>on reception of the view, if it is a MergeView, each member will set the digest and
* install the new view
* </ol>
*/
private void sendMergeView(
Collection<Address> coords, MergeData combined_merge_data, MergeId merge_id) {
if (coords == null || combined_merge_data == null) return;
View view = combined_merge_data.view;
Digest digest = combined_merge_data.digest;
if (view == null || digest == null) {
if (log.isErrorEnabled())
log.error("view or digest is null, cannot send consolidated merge view/digest");
return;
}
if (log.isDebugEnabled())
log.debug(
gms.local_addr + ": sending merge view " + view.getVid() + " to coordinators " + coords);
gms.merge_ack_collector.reset(coords);
int size = gms.merge_ack_collector.size();
long timeout = gms.view_ack_collection_timeout;
long start = System.currentTimeMillis();
for (Address coord : coords) {
Message msg = new Message(coord, null, null);
GMS.GmsHeader hdr = new GMS.GmsHeader(GMS.GmsHeader.INSTALL_MERGE_VIEW);
hdr.view = view;
hdr.my_digest = digest;
hdr.merge_id = merge_id;
msg.putHeader(gms.getId(), hdr);
gms.getDownProtocol().down(new Event(Event.MSG, msg));
}
// [JGRP-700] - FLUSH: flushing should span merge
// if flush is in stack wait for acks from separated island coordinators
if (gms.flushProtocolInStack) {
try {
gms.merge_ack_collector.waitForAllAcks(timeout);
long stop = System.currentTimeMillis();
if (log.isTraceEnabled())
log.trace(
"received all ACKs ("
+ size
+ ") for merge view "
+ view
+ " in "
+ (stop - start)
+ "ms");
} catch (TimeoutException e) {
log.warn(
gms.local_addr
+ ": failed to collect all ACKs for merge ("
+ size
+ ") for view "
+ view
+ " after "
+ timeout
+ "ms, missing ACKs from "
+ gms.merge_ack_collector.printMissing());
}
}
}
/**
* 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);
}
/**
* 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);
}
/**
* Removes all members from a given view which don't have us in their view
* (https://jira.jboss.org/browse/JGRP-1061). Example:
*
* <pre>
* A: AB
* B: AB
* C: ABC
* </pre>
*
* becomes
*
* <pre>
* A: AB
* B: AB
* C: C // A and B don't have C in their views
* </pre>
*
* @param map A map of members and their associated views
*/
public static void sanitizeViews(Map<Address, View> map) {
if (map == null) return;
for (Map.Entry<Address, View> entry : map.entrySet()) {
Address key = entry.getKey();
Collection<Address> members = new ArrayList<Address>(entry.getValue().getMembers());
boolean modified = false;
for (Iterator<Address> it = members.iterator(); it.hasNext(); ) {
Address val = it.next();
if (val.equals(key)) // we can always talk to ourself !
continue;
View view = map.get(val);
final Collection<Address> tmp_mbrs = view != null ? view.getMembers() : null;
if (tmp_mbrs != null && !tmp_mbrs.contains(key)) {
it.remove();
modified = true;
}
}
if (modified) {
View old_view = entry.getValue();
entry.setValue(new View(old_view.getVid(), members));
}
}
}
/**
* 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()));
}
}
/**
* Broadcasts the new view and digest, and waits for acks from all members in the list given as
* argument. If the list is null, we take the members who are part of new_view
*/
public void castViewChange(
View new_view, Digest digest, JoinRsp jr, Collection<Address> newMembers) {
if (log.isTraceEnabled())
log.trace(local_addr + ": mcasting view " + new_view + " (" + new_view.size() + " mbrs)\n");
// Send down a local TMP_VIEW event. This is needed by certain layers (e.g. NAKACK) to compute
// correct digest
// in case client's next request (e.g. getState()) reaches us *before* our own view change
// multicast.
// Check NAKACK's TMP_VIEW handling for details
down_prot.up(new Event(Event.TMP_VIEW, new_view));
down_prot.down(new Event(Event.TMP_VIEW, new_view));
List<Address> ackMembers = new ArrayList<Address>(new_view.getMembers());
if (newMembers != null && !newMembers.isEmpty()) ackMembers.removeAll(newMembers);
Message view_change_msg = new Message(); // bcast to all members
GmsHeader hdr = new GmsHeader(GmsHeader.VIEW, new_view);
hdr.my_digest = digest;
view_change_msg.putHeader(this.id, hdr);
// If we're the only member the VIEW is broadcast to, let's simply install the view directly,
// without
// sending the VIEW multicast ! Or else N-1 members drop the multicast anyway...
if (local_addr != null && ackMembers.size() == 1 && ackMembers.get(0).equals(local_addr)) {
// we need to add the message to the retransmit window (e.g. in NAKACK), so (1) it can be
// retransmitted and
// (2) we increment the seqno (otherwise, we'd return an incorrect digest)
down_prot.down(new Event(Event.ADD_TO_XMIT_TABLE, view_change_msg));
impl.handleViewChange(new_view, digest);
} else {
if (!ackMembers.isEmpty()) ack_collector.reset(ackMembers);
down_prot.down(new Event(Event.MSG, view_change_msg));
try {
if (!ackMembers.isEmpty()) {
ack_collector.waitForAllAcks(view_ack_collection_timeout);
if (log.isTraceEnabled())
log.trace(
local_addr
+ ": received all "
+ ack_collector.expectedAcks()
+ " ACKs from members for view "
+ new_view.getVid());
}
} catch (TimeoutException e) {
if (log_collect_msgs && log.isWarnEnabled()) {
log.warn(
local_addr
+ ": failed to collect all ACKs (expected="
+ ack_collector.expectedAcks()
+ ") for view "
+ new_view.getViewId()
+ " after "
+ view_ack_collection_timeout
+ "ms, missing ACKs from "
+ ack_collector.printMissing());
}
}
}
if (jr != null && (newMembers != null && !newMembers.isEmpty())) {
ack_collector.reset(new ArrayList<Address>(newMembers));
for (Address joiner : newMembers) {
sendJoinResponse(jr, joiner);
}
try {
ack_collector.waitForAllAcks(view_ack_collection_timeout);
if (log.isTraceEnabled())
log.trace(
local_addr
+ ": received all ACKs ("
+ ack_collector.expectedAcks()
+ ") from joiners for view "
+ new_view.getVid());
} catch (TimeoutException e) {
if (log_collect_msgs && log.isWarnEnabled()) {
log.warn(
local_addr
+ ": failed to collect all ACKs (expected="
+ ack_collector.expectedAcks()
+ ") for unicast view "
+ new_view
+ " after "
+ view_ack_collection_timeout
+ "ms, missing ACKs from "
+ ack_collector.printMissing());
}
}
}
}
