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.
|
|
|
|
|
|
|
|
#include <stdio.h>
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "port/port.h"
|
|
|
|
#include "util/coding.h"
|
[RocksDB] Added nano second stopwatch and new perf counters to track block read cost
Summary: The pupose of this diff is to expose per user-call level precise timing of block read, so that we can answer questions like: a Get() costs me 100ms, is that somehow related to loading blocks from file system, or sth else? We will answer that with EXACTLY how many blocks have been read, how much time was spent on transfering the bytes from os, how much time was spent on checksum verification and how much time was spent on block decompression, just for that one Get. A nano second stopwatch was introduced to track time with higher precision. The cost/precision of the stopwatch is also measured in unit-test. On my dev box, retrieving one time instance costs about 30ns, on average. The deviation of timing results is good enough to track 100ns-1us level events. And the overhead could be safely ignored for 100us level events (10000 instances/s), for example, a viewstate thrift call.
Test Plan: perf_context_test, also testing with viewstate shadow traffic.
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D12351
2013-06-04 08:09:15 +02:00
|
|
|
#include "util/perf_context_imp.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2013-10-04 06:49:15 +02:00
|
|
|
namespace rocksdb {
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
static uint64_t PackSequenceAndType(uint64_t seq, ValueType t) {
|
|
|
|
assert(seq <= kMaxSequenceNumber);
|
|
|
|
assert(t <= kValueTypeForSeek);
|
|
|
|
return (seq << 8) | t;
|
|
|
|
}
|
|
|
|
|
|
|
|
void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
|
|
|
|
result->append(key.user_key.data(), key.user_key.size());
|
|
|
|
PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
|
|
|
|
}
|
|
|
|
|
2012-12-16 03:28:36 +01:00
|
|
|
std::string ParsedInternalKey::DebugString(bool hex) const {
|
2011-03-18 23:37:00 +01:00
|
|
|
char buf[50];
|
|
|
|
snprintf(buf, sizeof(buf), "' @ %llu : %d",
|
|
|
|
(unsigned long long) sequence,
|
|
|
|
int(type));
|
|
|
|
std::string result = "'";
|
2012-12-16 03:28:36 +01:00
|
|
|
result += user_key.ToString(hex);
|
2011-03-18 23:37:00 +01:00
|
|
|
result += buf;
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2012-12-16 03:28:36 +01:00
|
|
|
std::string InternalKey::DebugString(bool hex) const {
|
2011-10-06 01:30:28 +02:00
|
|
|
std::string result;
|
|
|
|
ParsedInternalKey parsed;
|
|
|
|
if (ParseInternalKey(rep_, &parsed)) {
|
2012-12-16 03:28:36 +01:00
|
|
|
result = parsed.DebugString(hex);
|
2011-10-06 01:30:28 +02:00
|
|
|
} else {
|
|
|
|
result = "(bad)";
|
|
|
|
result.append(EscapeString(rep_));
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
const char* InternalKeyComparator::Name() const {
|
2013-06-10 22:28:58 +02:00
|
|
|
return name_.c_str();
|
2011-03-18 23:37:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
int InternalKeyComparator::Compare(const Slice& akey, const Slice& bkey) const {
|
|
|
|
// Order by:
|
|
|
|
// increasing user key (according to user-supplied comparator)
|
|
|
|
// decreasing sequence number
|
|
|
|
// decreasing type (though sequence# should be enough to disambiguate)
|
|
|
|
int r = user_comparator_->Compare(ExtractUserKey(akey), ExtractUserKey(bkey));
|
[RocksDB] Added nano second stopwatch and new perf counters to track block read cost
Summary: The pupose of this diff is to expose per user-call level precise timing of block read, so that we can answer questions like: a Get() costs me 100ms, is that somehow related to loading blocks from file system, or sth else? We will answer that with EXACTLY how many blocks have been read, how much time was spent on transfering the bytes from os, how much time was spent on checksum verification and how much time was spent on block decompression, just for that one Get. A nano second stopwatch was introduced to track time with higher precision. The cost/precision of the stopwatch is also measured in unit-test. On my dev box, retrieving one time instance costs about 30ns, on average. The deviation of timing results is good enough to track 100ns-1us level events. And the overhead could be safely ignored for 100us level events (10000 instances/s), for example, a viewstate thrift call.
Test Plan: perf_context_test, also testing with viewstate shadow traffic.
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D12351
2013-06-04 08:09:15 +02:00
|
|
|
BumpPerfCount(&perf_context.user_key_comparison_count);
|
2011-03-18 23:37:00 +01:00
|
|
|
if (r == 0) {
|
|
|
|
const uint64_t anum = DecodeFixed64(akey.data() + akey.size() - 8);
|
|
|
|
const uint64_t bnum = DecodeFixed64(bkey.data() + bkey.size() - 8);
|
|
|
|
if (anum > bnum) {
|
|
|
|
r = -1;
|
|
|
|
} else if (anum < bnum) {
|
|
|
|
r = +1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
void InternalKeyComparator::FindShortestSeparator(
|
|
|
|
std::string* start,
|
|
|
|
const Slice& limit) const {
|
|
|
|
// Attempt to shorten the user portion of the key
|
|
|
|
Slice user_start = ExtractUserKey(*start);
|
|
|
|
Slice user_limit = ExtractUserKey(limit);
|
|
|
|
std::string tmp(user_start.data(), user_start.size());
|
|
|
|
user_comparator_->FindShortestSeparator(&tmp, user_limit);
|
2011-11-14 18:06:16 +01:00
|
|
|
if (tmp.size() < user_start.size() &&
|
|
|
|
user_comparator_->Compare(user_start, tmp) < 0) {
|
|
|
|
// User key has become shorter physically, but larger logically.
|
|
|
|
// Tack on the earliest possible number to the shortened user key.
|
2011-03-18 23:37:00 +01:00
|
|
|
PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
|
|
|
|
assert(this->Compare(*start, tmp) < 0);
|
|
|
|
assert(this->Compare(tmp, limit) < 0);
|
|
|
|
start->swap(tmp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void InternalKeyComparator::FindShortSuccessor(std::string* key) const {
|
|
|
|
Slice user_key = ExtractUserKey(*key);
|
|
|
|
std::string tmp(user_key.data(), user_key.size());
|
|
|
|
user_comparator_->FindShortSuccessor(&tmp);
|
2011-11-14 18:06:16 +01:00
|
|
|
if (tmp.size() < user_key.size() &&
|
|
|
|
user_comparator_->Compare(user_key, tmp) < 0) {
|
|
|
|
// User key has become shorter physically, but larger logically.
|
|
|
|
// Tack on the earliest possible number to the shortened user key.
|
2011-03-18 23:37:00 +01:00
|
|
|
PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
|
|
|
|
assert(this->Compare(*key, tmp) < 0);
|
|
|
|
key->swap(tmp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-04-17 17:36:46 +02:00
|
|
|
const char* InternalFilterPolicy::Name() const {
|
|
|
|
return user_policy_->Name();
|
|
|
|
}
|
|
|
|
|
|
|
|
void InternalFilterPolicy::CreateFilter(const Slice* keys, int n,
|
|
|
|
std::string* dst) const {
|
|
|
|
// We rely on the fact that the code in table.cc does not mind us
|
|
|
|
// adjusting keys[].
|
|
|
|
Slice* mkey = const_cast<Slice*>(keys);
|
|
|
|
for (int i = 0; i < n; i++) {
|
|
|
|
mkey[i] = ExtractUserKey(keys[i]);
|
|
|
|
// TODO(sanjay): Suppress dups?
|
|
|
|
}
|
|
|
|
user_policy_->CreateFilter(keys, n, dst);
|
|
|
|
}
|
|
|
|
|
|
|
|
bool InternalFilterPolicy::KeyMayMatch(const Slice& key, const Slice& f) const {
|
|
|
|
return user_policy_->KeyMayMatch(ExtractUserKey(key), f);
|
|
|
|
}
|
|
|
|
|
2011-06-22 04:36:45 +02:00
|
|
|
LookupKey::LookupKey(const Slice& user_key, SequenceNumber s) {
|
|
|
|
size_t usize = user_key.size();
|
|
|
|
size_t needed = usize + 13; // A conservative estimate
|
|
|
|
char* dst;
|
|
|
|
if (needed <= sizeof(space_)) {
|
|
|
|
dst = space_;
|
|
|
|
} else {
|
|
|
|
dst = new char[needed];
|
|
|
|
}
|
|
|
|
start_ = dst;
|
|
|
|
dst = EncodeVarint32(dst, usize + 8);
|
|
|
|
kstart_ = dst;
|
|
|
|
memcpy(dst, user_key.data(), usize);
|
|
|
|
dst += usize;
|
|
|
|
EncodeFixed64(dst, PackSequenceAndType(s, kValueTypeForSeek));
|
|
|
|
dst += 8;
|
|
|
|
end_ = dst;
|
|
|
|
}
|
|
|
|
|
2013-10-04 06:49:15 +02:00
|
|
|
} // namespace rocksdb
|