2016-02-09 23:12:00 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-15 23:03:42 +00:00
|
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
|
|
// (found in the LICENSE.Apache file in the root directory).
|
2014-05-09 00:25:13 +00:00
|
|
|
|
|
|
|
#ifndef GFLAGS
|
|
|
|
#include <cstdio>
|
|
|
|
int main() {
|
|
|
|
fprintf(stderr, "Please install gflags to run rocksdb tools\n");
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
|
2014-10-27 22:12:20 +00:00
|
|
|
#include <atomic>
|
2018-04-13 00:55:14 +00:00
|
|
|
#include <cstdio>
|
2012-12-11 19:57:35 +00:00
|
|
|
|
|
|
|
#include "db/write_batch_internal.h"
|
2013-08-23 15:38:13 +00:00
|
|
|
#include "rocksdb/db.h"
|
|
|
|
#include "rocksdb/types.h"
|
2019-05-30 18:21:38 +00:00
|
|
|
#include "test_util/testutil.h"
|
2019-05-31 00:39:43 +00:00
|
|
|
#include "util/gflags_compat.h"
|
2012-12-11 19:57:35 +00:00
|
|
|
|
|
|
|
// Run a thread to perform Put's.
|
|
|
|
// Another thread uses GetUpdatesSince API to keep getting the updates.
|
|
|
|
// options :
|
|
|
|
// --num_inserts = the num of inserts the first thread should perform.
|
|
|
|
// --wal_ttl = the wal ttl for the run.
|
|
|
|
|
2020-12-22 08:19:44 +00:00
|
|
|
DEFINE_uint64(num_inserts, 1000,
|
|
|
|
"the num of inserts the first thread should"
|
|
|
|
" perform.");
|
|
|
|
DEFINE_uint64(wal_ttl_seconds, 1000, "the wal ttl for the run(in seconds)");
|
|
|
|
DEFINE_uint64(wal_size_limit_MB, 10,
|
|
|
|
"the wal size limit for the run"
|
|
|
|
"(in MB)");
|
|
|
|
|
2022-01-12 17:28:09 +00:00
|
|
|
using ROCKSDB_NAMESPACE::BatchResult;
|
|
|
|
using ROCKSDB_NAMESPACE::DB;
|
|
|
|
using ROCKSDB_NAMESPACE::DestroyDB;
|
|
|
|
using ROCKSDB_NAMESPACE::Env;
|
|
|
|
using ROCKSDB_NAMESPACE::Options;
|
|
|
|
using ROCKSDB_NAMESPACE::Random;
|
|
|
|
using ROCKSDB_NAMESPACE::SequenceNumber;
|
|
|
|
using ROCKSDB_NAMESPACE::Slice;
|
|
|
|
using ROCKSDB_NAMESPACE::Status;
|
|
|
|
using ROCKSDB_NAMESPACE::TransactionLogIterator;
|
|
|
|
using ROCKSDB_NAMESPACE::WriteOptions;
|
2012-12-11 19:57:35 +00:00
|
|
|
|
2017-12-01 18:40:45 +00:00
|
|
|
using GFLAGS_NAMESPACE::ParseCommandLineFlags;
|
|
|
|
using GFLAGS_NAMESPACE::SetUsageMessage;
|
2014-05-09 00:25:13 +00:00
|
|
|
|
2012-12-11 19:57:35 +00:00
|
|
|
struct DataPumpThread {
|
2018-04-13 00:55:14 +00:00
|
|
|
DB* db; // Assumption DB is Open'ed already.
|
2012-12-11 19:57:35 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
static void DataPumpThreadBody(void* arg) {
|
Prefer static_cast in place of most reinterpret_cast (#12308)
Summary:
The following are risks associated with pointer-to-pointer reinterpret_cast:
* Can produce the "wrong result" (crash or memory corruption). IIRC, in theory this can happen for any up-cast or down-cast for a non-standard-layout type, though in practice would only happen for multiple inheritance cases (where the base class pointer might be "inside" the derived object). We don't use multiple inheritance a lot, but we do.
* Can mask useful compiler errors upon code change, including converting between unrelated pointer types that you are expecting to be related, and converting between pointer and scalar types unintentionally.
I can only think of some obscure cases where static_cast could be troublesome when it compiles as a replacement:
* Going through `void*` could plausibly cause unnecessary or broken pointer arithmetic. Suppose we have
`struct Derived: public Base1, public Base2`. If we have `Derived*` -> `void*` -> `Base2*` -> `Derived*` through reinterpret casts, this could plausibly work (though technical UB) assuming the `Base2*` is not dereferenced. Changing to static cast could introduce breaking pointer arithmetic.
* Unnecessary (but safe) pointer arithmetic could arise in a case like `Derived*` -> `Base2*` -> `Derived*` where before the Base2 pointer might not have been dereferenced. This could potentially affect performance.
With some light scripting, I tried replacing pointer-to-pointer reinterpret_casts with static_cast and kept the cases that still compile. Most occurrences of reinterpret_cast have successfully been changed (except for java/ and third-party/). 294 changed, 257 remain.
A couple of related interventions included here:
* Previously Cache::Handle was not actually derived from in the implementations and just used as a `void*` stand-in with reinterpret_cast. Now there is a relationship to allow static_cast. In theory, this could introduce pointer arithmetic (as described above) but is unlikely without multiple inheritance AND non-empty Cache::Handle.
* Remove some unnecessary casts to void* as this is allowed to be implicit (for better or worse).
Most of the remaining reinterpret_casts are for converting to/from raw bytes of objects. We could consider better idioms for these patterns in follow-up work.
I wish there were a way to implement a template variant of static_cast that would only compile if no pointer arithmetic is generated, but best I can tell, this is not possible. AFAIK the best you could do is a dynamic check that the void* conversion after the static cast is unchanged.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12308
Test Plan: existing tests, CI
Reviewed By: ltamasi
Differential Revision: D53204947
Pulled By: pdillinger
fbshipit-source-id: 9de23e618263b0d5b9820f4e15966876888a16e2
2024-02-07 18:44:11 +00:00
|
|
|
DataPumpThread* t = static_cast<DataPumpThread*>(arg);
|
2012-12-11 19:57:35 +00:00
|
|
|
DB* db = t->db;
|
|
|
|
Random rnd(301);
|
2020-12-22 08:19:44 +00:00
|
|
|
uint64_t i = 0;
|
|
|
|
while (i++ < FLAGS_num_inserts) {
|
2020-07-09 21:33:42 +00:00
|
|
|
if (!db->Put(WriteOptions(), Slice(rnd.RandomString(500)),
|
|
|
|
Slice(rnd.RandomString(500)))
|
2018-04-13 00:55:14 +00:00
|
|
|
.ok()) {
|
2013-08-06 19:54:37 +00:00
|
|
|
fprintf(stderr, "Error in put\n");
|
|
|
|
exit(1);
|
|
|
|
}
|
2012-12-11 19:57:35 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-10-24 14:43:14 +00:00
|
|
|
int main(int argc, const char** argv) {
|
2014-05-09 00:25:13 +00:00
|
|
|
SetUsageMessage(
|
|
|
|
std::string("\nUSAGE:\n") + std::string(argv[0]) +
|
|
|
|
" --num_inserts=<num_inserts> --wal_ttl_seconds=<WAL_ttl_seconds>" +
|
|
|
|
" --wal_size_limit_MB=<WAL_size_limit_MB>");
|
|
|
|
ParseCommandLineFlags(&argc, const_cast<char***>(&argv), true);
|
2012-12-11 19:57:35 +00:00
|
|
|
|
|
|
|
Env* env = Env::Default();
|
|
|
|
std::string default_db_path;
|
|
|
|
env->GetTestDirectory(&default_db_path);
|
|
|
|
default_db_path += "db_repl_stress";
|
|
|
|
Options options;
|
|
|
|
options.create_if_missing = true;
|
2013-11-07 02:46:28 +00:00
|
|
|
options.WAL_ttl_seconds = FLAGS_wal_ttl_seconds;
|
|
|
|
options.WAL_size_limit_MB = FLAGS_wal_size_limit_MB;
|
2012-12-11 19:57:35 +00:00
|
|
|
DB* db;
|
2013-08-06 19:54:37 +00:00
|
|
|
DestroyDB(default_db_path, options);
|
2012-12-11 19:57:35 +00:00
|
|
|
|
|
|
|
Status s = DB::Open(options, default_db_path, &db);
|
|
|
|
|
|
|
|
if (!s.ok()) {
|
|
|
|
fprintf(stderr, "Could not open DB due to %s\n", s.ToString().c_str());
|
2013-08-06 19:54:37 +00:00
|
|
|
exit(1);
|
2012-12-11 19:57:35 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
DataPumpThread dataPump;
|
|
|
|
dataPump.db = db;
|
|
|
|
env->StartThread(DataPumpThreadBody, &dataPump);
|
|
|
|
|
2020-12-22 08:19:44 +00:00
|
|
|
std::unique_ptr<TransactionLogIterator> iter;
|
|
|
|
SequenceNumber currentSeqNum = 1;
|
|
|
|
uint64_t num_read = 0;
|
|
|
|
for (;;) {
|
|
|
|
iter.reset();
|
|
|
|
// Continue to probe a bit more after all received
|
|
|
|
size_t probes = 0;
|
|
|
|
while (!db->GetUpdatesSince(currentSeqNum, &iter).ok()) {
|
|
|
|
probes++;
|
|
|
|
if (probes > 100 && num_read >= FLAGS_num_inserts) {
|
|
|
|
if (num_read > FLAGS_num_inserts) {
|
|
|
|
fprintf(stderr, "Too many updates read: %ld expected: %ld\n",
|
|
|
|
(long)num_read, (long)FLAGS_num_inserts);
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
fprintf(stderr, "Successful!\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
fprintf(stderr, "Refreshing iterator\n");
|
|
|
|
for (; iter->Valid(); iter->Next(), num_read++, currentSeqNum++) {
|
|
|
|
BatchResult res = iter->GetBatch();
|
|
|
|
if (res.sequence != currentSeqNum) {
|
|
|
|
fprintf(stderr, "Missed a seq no. b/w %ld and %ld\n",
|
|
|
|
(long)currentSeqNum, (long)res.sequence);
|
|
|
|
exit(1);
|
|
|
|
}
|
|
|
|
}
|
2012-12-11 19:57:35 +00:00
|
|
|
}
|
|
|
|
}
|
2014-05-09 00:25:13 +00:00
|
|
|
|
|
|
|
#endif // GFLAGS
|
2014-11-12 21:05:12 +00:00
|
|
|
|