2013-10-16 23:59:46 +02:00
|
|
|
// Copyright (c) 2013, Facebook, Inc. All rights reserved.
|
|
|
|
// This source code is licensed under the BSD-style license found in the
|
|
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
|
|
//
|
2011-03-18 23:37:00 +01:00
|
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
|
2013-10-05 07:32:05 +02:00
|
|
|
#pragma once
|
2015-07-17 18:27:24 +02:00
|
|
|
#include <algorithm>
|
2014-01-27 22:53:22 +01:00
|
|
|
#include <string>
|
2015-07-17 18:27:24 +02:00
|
|
|
#include <vector>
|
|
|
|
|
2014-01-27 22:53:22 +01:00
|
|
|
#include "db/dbformat.h"
|
Compaction filter on merge operands
Summary:
Since Andres' internship is over, I took over https://reviews.facebook.net/D42555 and rebased and simplified it a bit.
The behavior in this diff is a bit simpler than in D42555:
* only merge operators are passed through FilterMergeValue(). If fitler function returns true, the merge operator is ignored
* compaction filter is *not* called on: 1) results of merge operations and 2) base values that are getting merged with merge operands (the second case was also true in previous diff)
Do we also need a compaction filter to get called on merge results?
Test Plan: make && make check
Reviewers: lovro, tnovak, rven, yhchiang, sdong
Reviewed By: sdong
Subscribers: noetzli, kolmike, leveldb, dhruba, sdong
Differential Revision: https://reviews.facebook.net/D47847
2015-10-07 18:30:03 +02:00
|
|
|
#include "rocksdb/compaction_filter.h"
|
2013-08-23 17:38:13 +02:00
|
|
|
#include "rocksdb/env.h"
|
2015-07-17 18:27:24 +02:00
|
|
|
#include "rocksdb/iterator.h"
|
2013-08-23 17:38:13 +02:00
|
|
|
#include "rocksdb/slice.h"
|
2015-10-13 00:06:38 +02:00
|
|
|
#include "table/internal_iterator.h"
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
#include "util/mutexlock.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
#include "util/random.h"
|
|
|
|
|
2013-10-04 06:49:15 +02:00
|
|
|
namespace rocksdb {
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
2015-07-18 01:16:11 +02:00
|
|
|
class SequentialFile;
|
|
|
|
class SequentialFileReader;
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
namespace test {
|
|
|
|
|
|
|
|
// Store in *dst a random string of length "len" and return a Slice that
|
|
|
|
// references the generated data.
|
|
|
|
extern Slice RandomString(Random* rnd, int len, std::string* dst);
|
|
|
|
|
2014-09-09 07:24:40 +02:00
|
|
|
extern std::string RandomHumanReadableString(Random* rnd, int len);
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
// Return a random key with the specified length that may contain interesting
|
|
|
|
// characters (e.g. \x00, \xff, etc.).
|
|
|
|
extern std::string RandomKey(Random* rnd, int len);
|
|
|
|
|
|
|
|
// Store in *dst a string of length "len" that will compress to
|
|
|
|
// "N*compressed_fraction" bytes and return a Slice that references
|
|
|
|
// the generated data.
|
|
|
|
extern Slice CompressibleString(Random* rnd, double compressed_fraction,
|
|
|
|
int len, std::string* dst);
|
|
|
|
|
|
|
|
// A wrapper that allows injection of errors.
|
|
|
|
class ErrorEnv : public EnvWrapper {
|
|
|
|
public:
|
|
|
|
bool writable_file_error_;
|
|
|
|
int num_writable_file_errors_;
|
|
|
|
|
|
|
|
ErrorEnv() : EnvWrapper(Env::Default()),
|
|
|
|
writable_file_error_(false),
|
|
|
|
num_writable_file_errors_(0) { }
|
|
|
|
|
|
|
|
virtual Status NewWritableFile(const std::string& fname,
|
2013-03-15 01:00:04 +01:00
|
|
|
unique_ptr<WritableFile>* result,
|
2015-02-26 20:28:41 +01:00
|
|
|
const EnvOptions& soptions) override {
|
2013-01-20 11:07:13 +01:00
|
|
|
result->reset();
|
2011-03-18 23:37:00 +01:00
|
|
|
if (writable_file_error_) {
|
|
|
|
++num_writable_file_errors_;
|
|
|
|
return Status::IOError(fname, "fake error");
|
|
|
|
}
|
2013-03-15 01:00:04 +01:00
|
|
|
return target()->NewWritableFile(fname, result, soptions);
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2014-01-27 22:53:22 +01:00
|
|
|
// An internal comparator that just forward comparing results from the
|
|
|
|
// user comparator in it. Can be used to test entities that have no dependency
|
|
|
|
// on internal key structure but consumes InternalKeyComparator, like
|
|
|
|
// BlockBasedTable.
|
|
|
|
class PlainInternalKeyComparator : public InternalKeyComparator {
|
|
|
|
public:
|
|
|
|
explicit PlainInternalKeyComparator(const Comparator* c)
|
|
|
|
: InternalKeyComparator(c) {}
|
|
|
|
|
|
|
|
virtual ~PlainInternalKeyComparator() {}
|
|
|
|
|
|
|
|
virtual int Compare(const Slice& a, const Slice& b) const override {
|
|
|
|
return user_comparator()->Compare(a, b);
|
|
|
|
}
|
|
|
|
virtual void FindShortestSeparator(std::string* start,
|
|
|
|
const Slice& limit) const override {
|
|
|
|
user_comparator()->FindShortestSeparator(start, limit);
|
|
|
|
}
|
|
|
|
virtual void FindShortSuccessor(std::string* key) const override {
|
|
|
|
user_comparator()->FindShortSuccessor(key);
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
2014-10-29 21:49:45 +01:00
|
|
|
// A test comparator which compare two strings in this way:
|
|
|
|
// (1) first compare prefix of 8 bytes in alphabet order,
|
|
|
|
// (2) if two strings share the same prefix, sort the other part of the string
|
|
|
|
// in the reverse alphabet order.
|
|
|
|
// This helps simulate the case of compounded key of [entity][timestamp] and
|
|
|
|
// latest timestamp first.
|
|
|
|
class SimpleSuffixReverseComparator : public Comparator {
|
|
|
|
public:
|
|
|
|
SimpleSuffixReverseComparator() {}
|
|
|
|
|
2015-02-26 20:28:41 +01:00
|
|
|
virtual const char* Name() const override {
|
|
|
|
return "SimpleSuffixReverseComparator";
|
|
|
|
}
|
2014-10-29 21:49:45 +01:00
|
|
|
|
2015-02-26 20:28:41 +01:00
|
|
|
virtual int Compare(const Slice& a, const Slice& b) const override {
|
2014-10-29 21:49:45 +01:00
|
|
|
Slice prefix_a = Slice(a.data(), 8);
|
|
|
|
Slice prefix_b = Slice(b.data(), 8);
|
|
|
|
int prefix_comp = prefix_a.compare(prefix_b);
|
|
|
|
if (prefix_comp != 0) {
|
|
|
|
return prefix_comp;
|
|
|
|
} else {
|
|
|
|
Slice suffix_a = Slice(a.data() + 8, a.size() - 8);
|
|
|
|
Slice suffix_b = Slice(b.data() + 8, b.size() - 8);
|
|
|
|
return -(suffix_a.compare(suffix_b));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
virtual void FindShortestSeparator(std::string* start,
|
2015-02-26 20:28:41 +01:00
|
|
|
const Slice& limit) const override {}
|
2014-10-29 21:49:45 +01:00
|
|
|
|
2015-02-26 20:28:41 +01:00
|
|
|
virtual void FindShortSuccessor(std::string* key) const override {}
|
2014-10-29 21:49:45 +01:00
|
|
|
};
|
|
|
|
|
2014-08-27 19:39:31 +02:00
|
|
|
// Returns a user key comparator that can be used for comparing two uint64_t
|
|
|
|
// slices. Instead of comparing slices byte-wise, it compares all the 8 bytes
|
|
|
|
// at once. Assumes same endian-ness is used though the database's lifetime.
|
|
|
|
// Symantics of comparison would differ from Bytewise comparator in little
|
|
|
|
// endian machines.
|
|
|
|
extern const Comparator* Uint64Comparator();
|
|
|
|
|
2015-07-17 18:27:24 +02:00
|
|
|
// Iterator over a vector of keys/values
|
2015-10-13 00:06:38 +02:00
|
|
|
class VectorIterator : public InternalIterator {
|
2015-07-17 18:27:24 +02:00
|
|
|
public:
|
|
|
|
explicit VectorIterator(const std::vector<std::string>& keys)
|
|
|
|
: keys_(keys), current_(keys.size()) {
|
|
|
|
std::sort(keys_.begin(), keys_.end());
|
|
|
|
values_.resize(keys.size());
|
|
|
|
}
|
|
|
|
|
|
|
|
VectorIterator(const std::vector<std::string>& keys,
|
|
|
|
const std::vector<std::string>& values)
|
|
|
|
: keys_(keys), values_(values), current_(keys.size()) {
|
|
|
|
assert(keys_.size() == values_.size());
|
|
|
|
}
|
|
|
|
|
|
|
|
virtual bool Valid() const override { return current_ < keys_.size(); }
|
|
|
|
|
|
|
|
virtual void SeekToFirst() override { current_ = 0; }
|
|
|
|
virtual void SeekToLast() override { current_ = keys_.size() - 1; }
|
|
|
|
|
|
|
|
virtual void Seek(const Slice& target) override {
|
|
|
|
current_ = std::lower_bound(keys_.begin(), keys_.end(), target.ToString()) -
|
|
|
|
keys_.begin();
|
|
|
|
}
|
|
|
|
|
|
|
|
virtual void Next() override { current_++; }
|
|
|
|
virtual void Prev() override { current_--; }
|
|
|
|
|
|
|
|
virtual Slice key() const override { return Slice(keys_[current_]); }
|
|
|
|
virtual Slice value() const override { return Slice(values_[current_]); }
|
|
|
|
|
|
|
|
virtual Status status() const override { return Status::OK(); }
|
|
|
|
|
|
|
|
private:
|
|
|
|
std::vector<std::string> keys_;
|
|
|
|
std::vector<std::string> values_;
|
|
|
|
size_t current_;
|
|
|
|
};
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
2015-07-18 01:16:11 +02:00
|
|
|
extern WritableFileWriter* GetWritableFileWriter(WritableFile* wf);
|
|
|
|
|
|
|
|
extern RandomAccessFileReader* GetRandomAccessFileReader(RandomAccessFile* raf);
|
|
|
|
|
|
|
|
extern SequentialFileReader* GetSequentialFileReader(SequentialFile* se);
|
2015-07-17 18:27:24 +02:00
|
|
|
|
2015-08-05 16:33:27 +02:00
|
|
|
class StringSink: public WritableFile {
|
|
|
|
public:
|
|
|
|
std::string contents_;
|
|
|
|
|
|
|
|
explicit StringSink(Slice* reader_contents = nullptr) :
|
|
|
|
WritableFile(),
|
|
|
|
contents_(""),
|
|
|
|
reader_contents_(reader_contents),
|
|
|
|
last_flush_(0) {
|
|
|
|
if (reader_contents_ != nullptr) {
|
|
|
|
*reader_contents_ = Slice(contents_.data(), 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
const std::string& contents() const { return contents_; }
|
|
|
|
|
2015-09-11 18:57:02 +02:00
|
|
|
virtual Status Truncate(uint64_t size) override {
|
|
|
|
contents_.resize(size);
|
|
|
|
return Status::OK();
|
|
|
|
}
|
2015-08-05 16:33:27 +02:00
|
|
|
virtual Status Close() override { return Status::OK(); }
|
|
|
|
virtual Status Flush() override {
|
|
|
|
if (reader_contents_ != nullptr) {
|
|
|
|
assert(reader_contents_->size() <= last_flush_);
|
|
|
|
size_t offset = last_flush_ - reader_contents_->size();
|
|
|
|
*reader_contents_ = Slice(
|
|
|
|
contents_.data() + offset,
|
|
|
|
contents_.size() - offset);
|
|
|
|
last_flush_ = contents_.size();
|
|
|
|
}
|
|
|
|
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
virtual Status Sync() override { return Status::OK(); }
|
|
|
|
virtual Status Append(const Slice& slice) override {
|
|
|
|
contents_.append(slice.data(), slice.size());
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
void Drop(size_t bytes) {
|
|
|
|
if (reader_contents_ != nullptr) {
|
|
|
|
contents_.resize(contents_.size() - bytes);
|
|
|
|
*reader_contents_ = Slice(
|
|
|
|
reader_contents_->data(), reader_contents_->size() - bytes);
|
|
|
|
last_flush_ = contents_.size();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
Slice* reader_contents_;
|
|
|
|
size_t last_flush_;
|
|
|
|
};
|
|
|
|
|
|
|
|
class StringSource: public RandomAccessFile {
|
|
|
|
public:
|
Simplify querying of merge results
Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.
Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.
Test Plan: make clean all check
Reviewers: rven, sdong, yhchiang, anthony, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43353
2015-08-18 02:34:38 +02:00
|
|
|
explicit StringSource(const Slice& contents, uint64_t uniq_id = 0,
|
|
|
|
bool mmap = false)
|
|
|
|
: contents_(contents.data(), contents.size()),
|
|
|
|
uniq_id_(uniq_id),
|
|
|
|
mmap_(mmap) {}
|
2015-08-05 16:33:27 +02:00
|
|
|
|
|
|
|
virtual ~StringSource() { }
|
|
|
|
|
|
|
|
uint64_t Size() const { return contents_.size(); }
|
|
|
|
|
|
|
|
virtual Status Read(uint64_t offset, size_t n, Slice* result,
|
|
|
|
char* scratch) const override {
|
|
|
|
if (offset > contents_.size()) {
|
|
|
|
return Status::InvalidArgument("invalid Read offset");
|
|
|
|
}
|
|
|
|
if (offset + n > contents_.size()) {
|
|
|
|
n = contents_.size() - offset;
|
|
|
|
}
|
|
|
|
if (!mmap_) {
|
|
|
|
memcpy(scratch, &contents_[offset], n);
|
|
|
|
*result = Slice(scratch, n);
|
|
|
|
} else {
|
|
|
|
*result = Slice(&contents_[offset], n);
|
|
|
|
}
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
virtual size_t GetUniqueId(char* id, size_t max_size) const override {
|
|
|
|
if (max_size < 20) {
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
char* rid = id;
|
|
|
|
rid = EncodeVarint64(rid, uniq_id_);
|
|
|
|
rid = EncodeVarint64(rid, 0);
|
|
|
|
return static_cast<size_t>(rid-id);
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
std::string contents_;
|
|
|
|
uint64_t uniq_id_;
|
|
|
|
bool mmap_;
|
|
|
|
};
|
|
|
|
|
|
|
|
class NullLogger : public Logger {
|
|
|
|
public:
|
|
|
|
using Logger::Logv;
|
|
|
|
virtual void Logv(const char* format, va_list ap) override {}
|
|
|
|
virtual size_t GetLogFileSize() const override { return 0; }
|
|
|
|
};
|
|
|
|
|
Simplify querying of merge results
Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.
Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.
Test Plan: make clean all check
Reviewers: rven, sdong, yhchiang, anthony, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43353
2015-08-18 02:34:38 +02:00
|
|
|
// Corrupts key by changing the type
|
|
|
|
extern void CorruptKeyType(InternalKey* ikey);
|
|
|
|
|
Support for SingleDelete()
Summary:
This patch fixes #7460559. It introduces SingleDelete as a new database
operation. This operation can be used to delete keys that were never
overwritten (no put following another put of the same key). If an overwritten
key is single deleted the behavior is undefined. Single deletion of a
non-existent key has no effect but multiple consecutive single deletions are
not allowed (see limitations).
In contrast to the conventional Delete() operation, the deletion entry is
removed along with the value when the two are lined up in a compaction. Note:
The semantics are similar to @igor's prototype that allowed to have this
behavior on the granularity of a column family (
https://reviews.facebook.net/D42093 ). This new patch, however, is more
aggressive when it comes to removing tombstones: It removes the SingleDelete
together with the value whenever there is no snapshot between them while the
older patch only did this when the sequence number of the deletion was older
than the earliest snapshot.
Most of the complex additions are in the Compaction Iterator, all other changes
should be relatively straightforward. The patch also includes basic support for
single deletions in db_stress and db_bench.
Limitations:
- Not compatible with cuckoo hash tables
- Single deletions cannot be used in combination with merges and normal
deletions on the same key (other keys are not affected by this)
- Consecutive single deletions are currently not allowed (and older version of
this patch supported this so it could be resurrected if needed)
Test Plan: make all check
Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor
Reviewed By: igor
Subscribers: maykov, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
|
|
|
extern std::string KeyStr(const std::string& user_key,
|
|
|
|
const SequenceNumber& seq, const ValueType& t,
|
|
|
|
bool corrupt = false);
|
|
|
|
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
class SleepingBackgroundTask {
|
|
|
|
public:
|
|
|
|
SleepingBackgroundTask()
|
2015-09-25 19:29:44 +02:00
|
|
|
: bg_cv_(&mutex_),
|
|
|
|
should_sleep_(true),
|
|
|
|
done_with_sleep_(false),
|
|
|
|
sleeping_(false) {}
|
|
|
|
|
|
|
|
bool IsSleeping() {
|
|
|
|
MutexLock l(&mutex_);
|
|
|
|
return sleeping_;
|
|
|
|
}
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
void DoSleep() {
|
|
|
|
MutexLock l(&mutex_);
|
2015-09-25 19:29:44 +02:00
|
|
|
sleeping_ = true;
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
while (should_sleep_) {
|
|
|
|
bg_cv_.Wait();
|
|
|
|
}
|
2015-09-25 19:29:44 +02:00
|
|
|
sleeping_ = false;
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
done_with_sleep_ = true;
|
|
|
|
bg_cv_.SignalAll();
|
|
|
|
}
|
|
|
|
void WakeUp() {
|
|
|
|
MutexLock l(&mutex_);
|
|
|
|
should_sleep_ = false;
|
|
|
|
bg_cv_.SignalAll();
|
|
|
|
}
|
|
|
|
void WaitUntilDone() {
|
|
|
|
MutexLock l(&mutex_);
|
|
|
|
while (!done_with_sleep_) {
|
|
|
|
bg_cv_.Wait();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
bool WokenUp() {
|
|
|
|
MutexLock l(&mutex_);
|
|
|
|
return should_sleep_ == false;
|
|
|
|
}
|
|
|
|
|
|
|
|
void Reset() {
|
|
|
|
MutexLock l(&mutex_);
|
|
|
|
should_sleep_ = true;
|
|
|
|
done_with_sleep_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void DoSleepTask(void* arg) {
|
|
|
|
reinterpret_cast<SleepingBackgroundTask*>(arg)->DoSleep();
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
port::Mutex mutex_;
|
|
|
|
port::CondVar bg_cv_; // Signalled when background work finishes
|
|
|
|
bool should_sleep_;
|
|
|
|
bool done_with_sleep_;
|
2015-09-25 19:29:44 +02:00
|
|
|
bool sleeping_;
|
LogAndApply() should fail if the column family has been dropped
Summary:
This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically.
Here's what happens:
1. We start the flush for the column family
2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149
3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply()
4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process
5. Drop column family goes through LogAndApply() first, marking the column family as dropped.
6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975
7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK.
8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file.
The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped".
The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit.
Test Plan:
1. new test
2. make check
3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386
Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
|
|
|
};
|
|
|
|
|
Compaction filter on merge operands
Summary:
Since Andres' internship is over, I took over https://reviews.facebook.net/D42555 and rebased and simplified it a bit.
The behavior in this diff is a bit simpler than in D42555:
* only merge operators are passed through FilterMergeValue(). If fitler function returns true, the merge operator is ignored
* compaction filter is *not* called on: 1) results of merge operations and 2) base values that are getting merged with merge operands (the second case was also true in previous diff)
Do we also need a compaction filter to get called on merge results?
Test Plan: make && make check
Reviewers: lovro, tnovak, rven, yhchiang, sdong
Reviewed By: sdong
Subscribers: noetzli, kolmike, leveldb, dhruba, sdong
Differential Revision: https://reviews.facebook.net/D47847
2015-10-07 18:30:03 +02:00
|
|
|
// Filters merge operands and values that are equal to `num`.
|
|
|
|
class FilterNumber : public CompactionFilter {
|
|
|
|
public:
|
|
|
|
explicit FilterNumber(uint64_t num) : num_(num) {}
|
|
|
|
|
|
|
|
std::string last_merge_operand_key() { return last_merge_operand_key_; }
|
|
|
|
|
|
|
|
bool Filter(int level, const rocksdb::Slice& key, const rocksdb::Slice& value,
|
|
|
|
std::string* new_value, bool* value_changed) const override {
|
|
|
|
if (value.size() == sizeof(uint64_t)) {
|
|
|
|
return num_ == DecodeFixed64(value.data());
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool FilterMergeOperand(int level, const rocksdb::Slice& key,
|
|
|
|
const rocksdb::Slice& value) const override {
|
|
|
|
last_merge_operand_key_ = key.ToString();
|
|
|
|
if (value.size() == sizeof(uint64_t)) {
|
|
|
|
return num_ == DecodeFixed64(value.data());
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
const char* Name() const override { return "FilterBadMergeOperand"; }
|
|
|
|
|
|
|
|
private:
|
|
|
|
mutable std::string last_merge_operand_key_;
|
|
|
|
uint64_t num_;
|
|
|
|
};
|
|
|
|
|
|
|
|
inline std::string EncodeInt(uint64_t x) {
|
|
|
|
std::string result;
|
|
|
|
PutFixed64(&result, x);
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2011-10-31 18:22:06 +01:00
|
|
|
} // namespace test
|
2013-10-04 06:49:15 +02:00
|
|
|
} // namespace rocksdb
|