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

Merge branch 'release-6.3' into merge-release-6.3-into-master (temporarily discard all changes to BackupContainer.actor.cpp) 

# Conflicts:
#	fdbclient/BackupContainer.actor.cpp
#	fdbserver/Knobs.h
This commit is contained in:
A.J. Beamon 2021-03-15 16:41:04 -07:00
parent 83688c1c30 59a79e698e
commit 25c4880ebe
13 changed files with 184 additions and 102 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
documentation/sphinx/source/release-notes/release-notes-620.rst
View File

@ -2,6 +2,12 @@
Release Notes
#############
6.2.33
======
* Fixed an issue where storage servers could shutdown with ``unknown_error``. `(PR #4437) <https://github.com/apple/foundationdb/pull/4437>`_
* Fix backup agent stall when writing to local filesystem with slow metadata operations. `(PR #4428) <https://github.com/apple/foundationdb/pull/4428>`_
* Backup agent no longer uses 4k block caching layer on local output files so that write operations are larger. `(PR #4428) <https://github.com/apple/foundationdb/pull/4428>`_
6.2.32
======
* Fix an issue where symbolic links in cmake-built RPMs are broken if you unpack the RPM to a custom directory. `(PR #4380) <https://github.com/apple/foundationdb/pull/4380>`_

26
documentation/sphinx/source/release-notes/release-notes-630.rst
View File

@ -8,28 +8,18 @@ Release Notes
6.3.11
======
* Added a hint field in the trace event when all replicas of some data are lost. `(PR #4209) <https://github.com/apple/foundationdb/pull/4209>`_
* Rewrote SQLite injected fault handling. `(PR #4212) <https://github.com/apple/foundationdb/pull/4212>`_
* Add a SevWarnAlways trace line to help debug a rare failure. `(PR #4214) <https://github.com/apple/foundationdb/pull/4214>`_
* Use VFSAsyncFile::checkInjectedError to detect injected faults. `(PR #4253) <https://github.com/apple/foundationdb/pull/4253>`_
* Build on Windows using VS 2019 + LLVM/Clang. `(PR #4258) <https://github.com/apple/foundationdb/pull/4258>`_
* RateControl support in AFCCached to enable write op throttling. The feature is disabled by default. `(PR #4229) <https://github.com/apple/foundationdb/pull/4229>`_
* Add knobs for prefix bloom filters and larger block cache for RocksDB. `(PR #4201) <https://github.com/apple/foundationdb/pull/4201>`_
* Adding debug tools to FDB runtime image. `(PR #4247) <https://github.com/apple/foundationdb/pull/4247>`_
* Fix bug in simulated coordinator selection. `(PR #4285) <https://github.com/apple/foundationdb/pull/4285>`_
* Add option to prevent synchronous file deletes on reads for RocksDB. `(PR #4270) <https://github.com/apple/foundationdb/pull/4270>`_
* Report warning when TLS verification fails. `(PR #4299) <https://github.com/apple/foundationdb/pull/4299>`_
* Support multiple worker threads for each version of client that is loaded so that each cluster will be serviced by a client thread. `(PR #4269) <https://github.com/apple/foundationdb/pull/4269>`_
* Reboot simulated process on io_timeout error. `(PR #4345) <https://github.com/apple/foundationdb/pull/4345>`_
* Fix Snapshot backup test failure. `(PR #4372) <https://github.com/apple/foundationdb/pull/4372>`_
* Support multiple worker threads for each client version that is loaded. `(PR #4269) <https://github.com/apple/foundationdb/pull/4269>`_
* fdbcli: Output errors and warnings to stderr. `(PR #4332) <https://github.com/apple/foundationdb/pull/4332>`_
* Do not generate machine id in locality field if it is set by the user. `(PR #4022) <https://github.com/apple/foundationdb/pull/4022>`_
* Make the RocksDB init method idempotent. `(PR #4400) <https://github.com/apple/foundationdb/pull/4400>`_
* Fix bugs turned up by _GLIBCXX_DEBUG. `(PR #4301) <https://github.com/apple/foundationdb/pull/4301>`_
* Add New Unit and Integration Tests, and associated infrastructure. `(PR #4366) <https://github.com/apple/foundationdb/pull/4366>`_
* Do not rely on shared memory to generate a machine id if it is set explicitly. `(Issue #4022) <https://github.com/apple/foundationdb/pull/4022>`_
* Added ``workload.transactions.rejected_for_queued_too_long`` to status to report the number of transaction commits that failed because they were queued too long and could no longer be checked for conflicts. `(PR #4353) <https://github.com/apple/foundationdb/pull/4353>`_
* Add knobs for prefix bloom filters and larger block cache for RocksDB. `(PR #4201) <https://github.com/apple/foundationdb/pull/4201>`_
* Add option to prevent synchronous file deletes on reads for RocksDB. `(PR #4270) <https://github.com/apple/foundationdb/pull/4270>`_
* Build on Windows using VS 2019 + LLVM/Clang. `(PR #4258) <https://github.com/apple/foundationdb/pull/4258>`_
6.3.10
======
* Make fault tolerance metric calculation in HA clusters consistent with 6.2 branch. `(PR #4175) <https://github.com/apple/foundationdb/pull/4175>`_
* Bug fix, stack overflow in redwood storage engine. `(PR #4161) <https://github.com/apple/foundationdb/pull/4161>`_
* Bug fix, getting certain special keys fail. `(PR #4128) <https://github.com/apple/foundationdb/pull/4128>`_

2
fdbclient/FileBackupAgent.actor.cpp
View File

@ -1205,7 +1205,7 @@ struct BackupRangeTaskFunc : BackupTaskFuncBase {
wait(rangeFile.writeKey(nextKey));
if (BUGGIFY) {
rangeFile.padEnd();
wait(rangeFile.padEnd());
}
bool usedFile = wait(

2
fdbclient/Knobs.cpp
View File

@ -124,7 +124,7 @@ void ClientKnobs::initialize(bool randomize) {
init( TASKBUCKET_MAX_TASK_KEYS, 1000 ); if( randomize && BUGGIFY ) TASKBUCKET_MAX_TASK_KEYS = 20;
//Backup
init( BACKUP_LOCAL_FILE_WRITE_BLOCK, 1024*1024 ); if( randomize && BUGGIFY ) BACKUP_LOCAL_FILE_WRITE_BLOCK = 100;
init( BACKUP_LOCAL_FILE_WRITE_BLOCK, 1024*1024 );
init( BACKUP_CONCURRENT_DELETES, 100 );
init( BACKUP_SIMULATED_LIMIT_BYTES, 1e6 ); if( randomize && BUGGIFY ) BACKUP_SIMULATED_LIMIT_BYTES = 1000;
init( BACKUP_GET_RANGE_LIMIT_BYTES, 1e6 );

105
fdbclient/MultiVersionTransaction.actor.cpp
View File

@ -1236,52 +1236,64 @@ std::vector<std::pair<std::string, bool>> MultiVersionApi::copyExternalLibraryPe
ASSERT_GE(threadCount, 1);
// Copy library for each thread configured per version
std::vector<std::pair<std::string, bool>> paths;
// It's tempting to use the so once without copying. However, we don't know
// if the thing we're about to copy is the shared object executing this code
// or not, so this optimization is unsafe.
// paths.push_back({path, false});
for (int ii = 0; ii < threadCount; ++ii) {
std::string filename = basename(path);
char tempName[PATH_MAX + 12];
sprintf(tempName, "/tmp/%s-XXXXXX", filename.c_str());
int tempFd = mkstemp(tempName);
int fd;
if (threadCount == 1) {
paths.push_back({ path, false });
} else {
// It's tempting to use the so once without copying. However, we don't know
// if the thing we're about to copy is the shared object executing this code
// or not, so this optimization is unsafe.
// paths.push_back({path, false});
for (int ii = 0; ii < threadCount; ++ii) {
std::string filename = basename(path);
if ((fd = open(path.c_str(), O_RDONLY)) == -1) {
TraceEvent("ExternalClientNotFound").detail("LibraryPath", path);
throw file_not_found();
}
char tempName[PATH_MAX + 12];
sprintf(tempName, "/tmp/%s-XXXXXX", filename.c_str());
int tempFd = mkstemp(tempName);
int fd;
constexpr size_t buf_sz = 4096;
char buf[buf_sz];
while (1) {
ssize_t readCount = read(fd, buf, buf_sz);
if (readCount == 0) {
// eof
break;
if ((fd = open(path.c_str(), O_RDONLY)) == -1) {
TraceEvent("ExternalClientNotFound").detail("LibraryPath", path);
throw file_not_found();
}
if (readCount == -1) {
TraceEvent(SevError, "ExternalClientCopyFailedReadError").GetLastError().detail("LibraryPath", path);
throw platform_error();
}
ssize_t written = 0;
while (written != readCount) {
ssize_t writeCount = write(tempFd, buf + written, readCount - written);
if (writeCount == -1) {
TraceEvent(SevError, "ExternalClientCopyFailedWriteError")
TraceEvent("CopyingExternalClient")
.detail("FileName", filename)
.detail("LibraryPath", path)
.detail("TempPath", tempName);
constexpr size_t buf_sz = 4096;
char buf[buf_sz];
while (1) {
ssize_t readCount = read(fd, buf, buf_sz);
if (readCount == 0) {
// eof
break;
}
if (readCount == -1) {
TraceEvent(SevError, "ExternalClientCopyFailedReadError")
.GetLastError()
.detail("LibraryPath", path);
throw platform_error();
}
written += writeCount;
ssize_t written = 0;
while (written != readCount) {
ssize_t writeCount = write(tempFd, buf + written, readCount - written);
if (writeCount == -1) {
TraceEvent(SevError, "ExternalClientCopyFailedWriteError")
.GetLastError()
.detail("LibraryPath", path);
throw platform_error();
}
written += writeCount;
}
}
close(fd);
close(tempFd);
paths.push_back({ tempName, true }); // use + delete temporary copies of the library.
}
close(fd);
close(tempFd);
paths.push_back({ tempName, true }); // use + delete temporary copies of the library.
}
return paths;
@ -1415,16 +1427,24 @@ void MultiVersionApi::setupNetwork() {
if (externalClients.count(filename) == 0) {
externalClients[filename] = {};
for (const auto& tmp : copyExternalLibraryPerThread(path)) {
TraceEvent("AddingExternalClient")
.detail("FileName", filename)
.detail("LibraryPath", path)
.detail("TempPath", tmp.first);
externalClients[filename].push_back(Reference<ClientInfo>(
new ClientInfo(new DLApi(tmp.first, tmp.second /*unlink on load*/), path)));
}
}
}
if (externalClients.empty() && localClientDisabled) {
// SOMEDAY: this should be allowed when it's possible to add external clients after the
// network is setup.
//
// Typically we would create a more specific error for this case, but since we expect
// this case to go away soon, we can use a trace event and a generic error.
TraceEvent(SevWarn, "CannotSetupNetwork")
.detail("Reason", "Local client is disabled and no external clients configured");
throw client_invalid_operation();
}
networkStartSetup = true;
if (externalClients.empty()) {
@ -1545,8 +1565,7 @@ Reference<IDatabase> MultiVersionApi::createDatabase(const char* clusterFilePath
}
std::string clusterFile(clusterFilePath);
if (threadCount > 1 || localClientDisabled) {
ASSERT(localClientDisabled);
if (localClientDisabled) {
ASSERT(!bypassMultiClientApi);
int threadIdx = nextThread;
@ -1562,6 +1581,8 @@ Reference<IDatabase> MultiVersionApi::createDatabase(const char* clusterFilePath
lock.leave();
ASSERT_LE(threadCount, 1);
auto db = localClient->api->createDatabase(clusterFilePath);
if (bypassMultiClientApi) {
return db;

48
fdbrpc/AsyncFileNonDurable.actor.h
View File

@ -136,6 +136,8 @@ public:
// The address of the machine that opened the file
NetworkAddress openedAddress;
bool aio;
private:
// The wrapped IAsyncFile
Reference<IAsyncFile> file;
@ -173,8 +175,10 @@ private:
AsyncFileNonDurable(const std::string& filename,
Reference<IAsyncFile> file,
Reference<DiskParameters> diskParameters,
NetworkAddress openedAddress)
: openedAddress(openedAddress), pendingModifications(uint64_t(-1)), approximateSize(0), reponses(false) {
NetworkAddress openedAddress,
bool aio)
: openedAddress(openedAddress), pendingModifications(uint64_t(-1)), approximateSize(0), reponses(false),
aio(aio) {
// This is only designed to work in simulation
ASSERT(g_network->isSimulated());
@ -198,7 +202,8 @@ public:
ACTOR static Future<Reference<IAsyncFile>> open(std::string filename,
std::string actualFilename,
Future<Reference<IAsyncFile>> wrappedFile,
Reference<DiskParameters> diskParameters) {
Reference<DiskParameters> diskParameters,
bool aio) {
state ISimulator::ProcessInfo* currentProcess = g_simulator.getCurrentProcess();
state TaskPriority currentTaskID = g_network->getCurrentTask();
state Future<Void> shutdown = success(currentProcess->shutdownSignal.getFuture());
@ -225,7 +230,7 @@ public:
}
state Reference<AsyncFileNonDurable> nonDurableFile(
new AsyncFileNonDurable(filename, file, diskParameters, currentProcess->address));
new AsyncFileNonDurable(filename, file, diskParameters, currentProcess->address, aio));
// Causes the approximateSize member to be set
state Future<int64_t> sizeFuture = nonDurableFile->size();
@ -462,20 +467,39 @@ private:
debugFileCheck("AsyncFileNonDurableWriteAfterWait", self->filename, dataCopy.begin(), offset, length);
// Only page-aligned writes are supported
ASSERT(offset % 4096 == 0 && length % 4096 == 0);
// In AIO mode, only page-aligned writes are supported
ASSERT(!self->aio || (offset % 4096 == 0 && length % 4096 == 0));
// Non-durable writes should introduce errors at the page level and corrupt at the sector level
// Otherwise, we can perform the entire write at once
int pageLength = saveDurable ? length : 4096;
int sectorLength = saveDurable ? length : 512;
int diskPageLength = saveDurable ? length : 4096;
int diskSectorLength = saveDurable ? length : 512;
vector<Future<Void>> writeFutures;
for (int writeOffset = 0; writeOffset < length; writeOffset += pageLength) {
for (int writeOffset = 0; writeOffset < length;) {
// Number of bytes until the next diskPageLength file offset within the write or the end of the write.
int pageLength = diskPageLength;
if (!self->aio && !saveDurable) {
// If not in AIO mode, and the save is not durable, then we can't perform the entire write all at once
// and the first and last pages touched by the write could be partial.
pageLength = std::min<int64_t>((int64_t)length - writeOffset,
diskPageLength - ((offset + writeOffset) % diskPageLength));
}
// choose a random action to perform on this page write (write correctly, corrupt, or don't write)
KillMode pageKillMode = (KillMode)deterministicRandom()->randomInt(0, self->killMode + 1);
for (int pageOffset = 0; pageOffset < pageLength; pageOffset += sectorLength) {
for (int pageOffset = 0; pageOffset < pageLength;) {
// Number of bytes until the next diskSectorLength file offset within the write or the end of the write.
int sectorLength = diskSectorLength;
if (!self->aio && !saveDurable) {
// If not in AIO mode, and the save is not durable, then we can't perform the entire write all at
// once and the first and last sectors touched by the write could be partial.
sectorLength =
std::min<int64_t>((int64_t)length - (writeOffset + pageOffset),
diskSectorLength - ((offset + writeOffset + pageOffset) % diskSectorLength));
}
// If saving durable, then perform the write correctly. Otherwise, perform the write correcly with a
// probability of 1/3. If corrupting the write, then this sector will be written correctly with a 1/4
// chance
@ -550,7 +574,11 @@ private:
.detail("Filename", self->filename);
TEST(true); // AsyncFileNonDurable dropped write
}
pageOffset += sectorLength;
}
writeOffset += pageLength;
}
wait(waitForAll(writeFutures));

7
fdbrpc/sim2.actor.cpp
View File

@ -681,8 +681,8 @@ private:
opId.shortString().c_str(),
size);
if (size == 0) {
// KAIO will return EINVAL, as len==0 is an error.
// KAIO will return EINVAL, as len==0 is an error.
if ((self->flags & IAsyncFile::OPEN_NO_AIO) == 0 && size == 0) {
throw io_error();
}
@ -2457,7 +2457,8 @@ Future<Reference<class IAsyncFile>> Sim2FileSystem::open(const std::string& file
AsyncFileNonDurable::open(filename,
actualFilename,
SimpleFile::open(filename, flags, mode, diskParameters, false),
diskParameters);
diskParameters,
(flags & IAsyncFile::OPEN_NO_AIO) == 0);
}
Future<Reference<IAsyncFile>> f = AsyncFileDetachable::open(machineCache[actualFilename]);
if (FLOW_KNOBS->PAGE_WRITE_CHECKSUM_HISTORY > 0)

1
fdbserver/Knobs.cpp
View File

@ -44,6 +44,7 @@ void ServerKnobs::initialize(bool randomize, ClientKnobs* clientKnobs, bool isSi
// TLogs
init( TLOG_TIMEOUT, 0.4 ); //cannot buggify because of availability
init( TLOG_SLOW_REJOIN_WARN_TIMEOUT_SECS, 60 ); if( randomize && BUGGIFY ) TLOG_SLOW_REJOIN_WARN_TIMEOUT_SECS = deterministicRandom()->randomInt(5,10);
init( RECOVERY_TLOG_SMART_QUORUM_DELAY, 0.25 ); if( randomize && BUGGIFY ) RECOVERY_TLOG_SMART_QUORUM_DELAY = 0.0; // smaller might be better for bug amplification
init( TLOG_STORAGE_MIN_UPDATE_INTERVAL, 0.5 );
init( BUGGIFY_TLOG_STORAGE_MIN_UPDATE_INTERVAL, 30 );

1
fdbserver/Knobs.h
View File

@ -42,6 +42,7 @@ public:
// TLogs
double TLOG_TIMEOUT; // tlog OR commit proxy failure - master's reaction time
double TLOG_SLOW_REJOIN_WARN_TIMEOUT_SECS; // Warns if a tlog takes too long to rejoin
double RECOVERY_TLOG_SMART_QUORUM_DELAY; // smaller might be better for bug amplification
double TLOG_STORAGE_MIN_UPDATE_INTERVAL;
double BUGGIFY_TLOG_STORAGE_MIN_UPDATE_INTERVAL;

65
fdbserver/TagPartitionedLogSystem.actor.cpp
View File

@ -3027,35 +3027,52 @@ struct TagPartitionedLogSystem : ILogSystem, ReferenceCounted<TagPartitionedLogS
logServers,
FutureStream<struct TLogRejoinRequest> rejoinRequests) {
state std::map<UID, ReplyPromise<TLogRejoinReply>> lastReply;
state std::set<UID> logsWaiting;
state double startTime = now();
state Future<Void> warnTimeout = delay(SERVER_KNOBS->TLOG_SLOW_REJOIN_WARN_TIMEOUT_SECS);
for (const auto& log : logServers) {
logsWaiting.insert(log.first->get().id());
}
try {
loop {
TLogRejoinRequest req = waitNext(rejoinRequests);
int pos = -1;
for (int i = 0; i < logServers.size(); i++) {
if (logServers[i].first->get().id() == req.myInterface.id()) {
pos = i;
break;
loop choose {
when(TLogRejoinRequest req = waitNext(rejoinRequests)) {
int pos = -1;
for (int i = 0; i < logServers.size(); i++) {
if (logServers[i].first->get().id() == req.myInterface.id()) {
pos = i;
logsWaiting.erase(logServers[i].first->get().id());
break;
}
}
if (pos != -1) {
TraceEvent("TLogJoinedMe", dbgid)
.detail("TLog", req.myInterface.id())
.detail("Address", req.myInterface.commit.getEndpoint().getPrimaryAddress().toString());
if (!logServers[pos].first->get().present() ||
req.myInterface.commit.getEndpoint() !=
logServers[pos].first->get().interf().commit.getEndpoint()) {
TLogInterface interf = req.myInterface;
filterLocalityDataForPolicyDcAndProcess(logServers[pos].second, &interf.filteredLocality);
logServers[pos].first->setUnconditional(OptionalInterface<TLogInterface>(interf));
}
lastReply[req.myInterface.id()].send(TLogRejoinReply{ false });
lastReply[req.myInterface.id()] = req.reply;
} else {
TraceEvent("TLogJoinedMeUnknown", dbgid)
.detail("TLog", req.myInterface.id())
.detail("Address", req.myInterface.commit.getEndpoint().getPrimaryAddress().toString());
req.reply.send(true);
}
}
if (pos != -1) {
TraceEvent("TLogJoinedMe", dbgid)
.detail("TLog", req.myInterface.id())
.detail("Address", req.myInterface.commit.getEndpoint().getPrimaryAddress().toString());
if (!logServers[pos].first->get().present() ||
req.myInterface.commit.getEndpoint() !=
logServers[pos].first->get().interf().commit.getEndpoint()) {
TLogInterface interf = req.myInterface;
filterLocalityDataForPolicyDcAndProcess(logServers[pos].second, &interf.filteredLocality);
logServers[pos].first->setUnconditional(OptionalInterface<TLogInterface>(interf));
when(wait(warnTimeout)) {
for (const auto& logId : logsWaiting) {
TraceEvent(SevWarnAlways, "TLogRejoinSlow", dbgid)
.detail("Elapsed", startTime - now())
.detail("LogId", logId);
}
lastReply[req.myInterface.id()].send(TLogRejoinReply{ false });
lastReply[req.myInterface.id()] = req.reply;
} else {
TraceEvent("TLogJoinedMeUnknown", dbgid)
.detail("TLog", req.myInterface.id())
.detail("Address", req.myInterface.commit.getEndpoint().getPrimaryAddress().toString());
req.reply.send(true);
warnTimeout = Never();
}
}
} catch (...) {

11
fdbserver/storageserver.actor.cpp
View File

@ -394,12 +394,19 @@ public:
UID UIDofLongest;
for (const auto& kv : startTimeMap) {
const double currentRunningTime = currentTime - kv.second;
if (longest < currentRunningTime) {
if (longest <= currentRunningTime) {
longest = currentRunningTime;
UIDofLongest = kv.first;
}
}
return { longest, keyRangeMap.at(UIDofLongest) };
if (BUGGIFY) {
UIDofLongest = deterministicRandom()->randomUniqueID();
}
auto it = keyRangeMap.find(UIDofLongest);
if (it != keyRangeMap.end()) {
return { longest, it->second };
}
return { -1, emptyKeyRange };
}
int numRunning() const { return startTimeMap.size(); }

10
packaging/docker/Dockerfile
View File

@ -84,3 +84,13 @@ ENV FDB_COORDINATOR ""
ENV FDB_COORDINATOR_PORT 4500
ENV FDB_CLUSTER_FILE_CONTENTS ""
ENV FDB_PROCESS_CLASS unset
# Adding tini as PID 1 https://github.com/krallin/tini
ARG TINI_VERSION=v0.19.0
RUN curl -sLO https://github.com/krallin/tini/releases/download/${TINI_VERSION}/tini-amd64 && \
curl -sLO https://github.com/krallin/tini/releases/download/${TINI_VERSION}/tini-amd64.sha256sum && \
sha256sum -c tini-amd64.sha256sum && \
rm -f tini-amd64.sha256sum && \
chmod +x tini-amd64 && \
mv tini-amd64 /usr/bin/tini
ENTRYPOINT ["/usr/bin/tini", "-g", "--"]

2
tests/python_tests/multithreaded_client.py
View File

@ -40,7 +40,7 @@ fdb.options.set_trace_enable(args.client_log_dir)
fdb.options.set_knob("min_trace_severity=5")
if not args.skip_so_files:
print "Loading .so files"
print("Loading .so files")
fdb.options.set_external_client_directory(args.build_dir + '/lib')
if args.threads > 0: