wbtiger
/
foundationdb
mirror of https://github.com/apple/foundationdb.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #7385 from sfc-gh-etschannen/fix-multiple-shared-tlogs 

Avoid recruiting multiple shared tlogs
This commit is contained in:
Markus Pilman 2022-07-11 17:28:35 -06:00 committed by GitHub
parent 4ece33a0a8 4e19126f1c
commit 4f4095b6ae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 27 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
fdbserver/worker.actor.cpp
View File

@ -1589,7 +1589,7 @@ ACTOR Future<Void> workerServer(Reference<IClusterConnectionRecord> connRecord,
// As (store type, spill type) can map to the same TLogFn across multiple TLogVersions, we need to
// decide if we should collapse them into the same SharedTLog instance as well. The answer
// here is no, so that when running with log_version==3, all files should say V=3.
state std::map<SharedLogsKey, SharedLogsValue> sharedLogs;
state std::map<SharedLogsKey, std::vector<SharedLogsValue>> sharedLogs;
state Reference<AsyncVar<UID>> activeSharedTLog(new AsyncVar<UID>());
state WorkerCache<InitializeBackupReply> backupWorkerCache;
state WorkerCache<InitializeBlobWorkerReply> blobWorkerCache;
@ -1787,32 +1787,29 @@ ACTOR Future<Void> workerServer(Reference<IClusterConnectionRecord> connRecord,
Promise<Void> recovery;
TLogFn tLogFn = tLogFnForOptions(s.tLogOptions);
auto& logData = sharedLogs[SharedLogsKey(s.tLogOptions, s.storeType)];
logData.push_back(SharedLogsValue());
// FIXME: Shouldn't if logData.first isValid && !isReady, shouldn't we
// be sending a fake InitializeTLogRequest rather than calling tLog() ?
Future<Void> tl =
tLogFn(kv,
queue,
dbInfo,
locality,
!logData.actor.isValid() || logData.actor.isReady() ? logData.requests
: PromiseStream<InitializeTLogRequest>(),
s.storeID,
interf.id(),
true,
oldLog,
recovery,
folder,
degraded,
activeSharedTLog);
Future<Void> tl = tLogFn(kv,
queue,
dbInfo,
locality,
logData.back().requests,
s.storeID,
interf.id(),
true,
oldLog,
recovery,
folder,
degraded,
activeSharedTLog);
recoveries.push_back(recovery.getFuture());
activeSharedTLog->set(s.storeID);
tl = handleIOErrors(tl, kv, s.storeID);
tl = handleIOErrors(tl, queue, s.storeID);
if (!logData.actor.isValid() || logData.actor.isReady()) {
logData.actor = oldLog.getFuture() || tl;
logData.uid = s.storeID;
}
logData.back().actor = oldLog.getFuture() || tl;
logData.back().uid = s.storeID;
errorForwarders.add(forwardError(errors, Role::SHARED_TRANSACTION_LOG, s.storeID, tl));
}
}
@ -2156,8 +2153,10 @@ ACTOR Future<Void> workerServer(Reference<IClusterConnectionRecord> connRecord,
TLogOptions tLogOptions(req.logVersion, req.spillType);
TLogFn tLogFn = tLogFnForOptions(tLogOptions);
auto& logData = sharedLogs[SharedLogsKey(tLogOptions, req.storeType)];
logData.requests.send(req);
if (!logData.actor.isValid() || logData.actor.isReady()) {
while (!logData.empty() && (!logData.back().actor.isValid() || logData.back().actor.isReady())) {
logData.pop_back();
}
if (logData.empty()) {
UID logId = deterministicRandom()->randomUniqueID();
std::map<std::string, std::string> details;
details["ForMaster"] = req.recruitmentID.shortString();
@ -2183,11 +2182,12 @@ ACTOR Future<Void> workerServer(Reference<IClusterConnectionRecord> connRecord,
filesClosed.add(data->onClosed());
filesClosed.add(queue->onClosed());
logData.push_back(SharedLogsValue());
Future<Void> tLogCore = tLogFn(data,
queue,
dbInfo,
locality,
logData.requests,
logData.back().requests,
logId,
interf.id(),
false,
@ -2199,10 +2199,11 @@ ACTOR Future<Void> workerServer(Reference<IClusterConnectionRecord> connRecord,
tLogCore = handleIOErrors(tLogCore, data, logId);
tLogCore = handleIOErrors(tLogCore, queue, logId);
errorForwarders.add(forwardError(errors, Role::SHARED_TRANSACTION_LOG, logId, tLogCore));
logData.actor = tLogCore;
logData.uid = logId;
logData.back().actor = tLogCore;
logData.back().uid = logId;
}
activeSharedTLog->set(logData.uid);
logData.back().requests.send(req);
activeSharedTLog->set(logData.back().uid);
}
when(InitializeStorageRequest req = waitNext(interf.storage.getFuture())) {
// We want to prevent double recruiting on a worker unless we try to recruit something