1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
|
#include <algorithm>
#include <chrono>
#include <iostream>
#include <map>
#include <vector>
#include "simdjson.h"
#define NB_ITERATION 20
#define MIN_BATCH_SIZE 10000
#define MAX_BATCH_SIZE 10000000
bool test_baseline = false;
bool test_per_batch = true;
bool test_best_batch = false;
bool compare(std::pair<size_t, double> i, std::pair<size_t, double> j) {
return i.second > j.second;
}
int main(int argc, char *argv[]) {
if (argc <= 1) {
std::cerr << "Usage: " << argv[0] << " <jsonfile>" << std::endl;
exit(1);
}
const char *filename = argv[1];
simdjson::padded_string p;
if (simdjson::padded_string::load(filename).get(p)) {
std::cerr << "Could not load the file " << filename << std::endl;
return EXIT_FAILURE;
}
if (test_baseline) {
std::wclog << "Baseline: Getline + normal parse... " << std::endl;
std::cout << "Gigabytes/second\t"
<< "Nb of documents parsed" << std::endl;
for (auto i = 0; i < 3; i++) {
// Actual test
simdjson::dom::parser parser;
simdjson::error_code alloc_error = parser.allocate(p.size());
if (alloc_error) {
std::cerr << alloc_error << std::endl;
return EXIT_FAILURE;
}
std::istringstream ss(std::string(p.data(), p.size()));
auto start = std::chrono::steady_clock::now();
int count = 0;
std::string line;
int parse_res = simdjson::SUCCESS;
while (getline(ss, line)) {
// TODO we're likely triggering simdjson's padding reallocation here. Is
// that intentional?
parser.parse(line);
count++;
}
auto end = std::chrono::steady_clock::now();
std::chrono::duration<double> secs = end - start;
double speedinGBs = static_cast<double>(p.size()) /
(static_cast<double>(secs.count()) * 1000000000.0);
std::cout << speedinGBs << "\t\t\t\t" << count << std::endl;
if (parse_res != simdjson::SUCCESS) {
std::cerr << "Parsing failed" << std::endl;
exit(1);
}
}
}
std::map<size_t, double> batch_size_res;
if (test_per_batch) {
std::wclog << "parse_many: Speed per batch_size... from " << MIN_BATCH_SIZE
<< " bytes to " << MAX_BATCH_SIZE << " bytes..." << std::endl;
std::cout << "Batch Size\t"
<< "Gigabytes/second\t"
<< "Nb of documents parsed" << std::endl;
for (size_t i = MIN_BATCH_SIZE; i <= MAX_BATCH_SIZE;
i += (MAX_BATCH_SIZE - MIN_BATCH_SIZE) / 100) {
batch_size_res.insert(std::pair<size_t, double>(i, 0));
int count;
for (size_t j = 0; j < 5; j++) {
// Actual test
simdjson::dom::parser parser;
simdjson::error_code error;
auto start = std::chrono::steady_clock::now();
count = 0;
simdjson::dom::document_stream docs;
if ((error = parser.parse_many(p, i).get(docs))) {
std::wcerr << "Parsing failed with: " << error << std::endl;
exit(1);
}
for (auto result : docs) {
error = result.error();
if (error) {
std::wcerr << "Parsing failed with: " << error << std::endl;
exit(1);
}
count++;
}
auto end = std::chrono::steady_clock::now();
std::chrono::duration<double> secs = end - start;
double speedinGBs = static_cast<double>(p.size()) /
(static_cast<double>(secs.count()) * 1000000000.0);
if (speedinGBs > batch_size_res.at(i))
batch_size_res[i] = speedinGBs;
}
std::cout << i << "\t\t" << std::fixed << std::setprecision(3)
<< batch_size_res.at(i) << "\t\t\t\t" << count << std::endl;
}
}
size_t optimal_batch_size{};
double best_speed{};
if (test_per_batch) {
std::pair<size_t, double> best_results;
best_results =
(*min_element(batch_size_res.begin(), batch_size_res.end(), compare));
optimal_batch_size = best_results.first;
best_speed = best_results.second;
} else {
optimal_batch_size = MIN_BATCH_SIZE;
}
std::wclog << "Seemingly optimal batch_size: " << optimal_batch_size << "..."
<< std::endl;
std::wclog << "Best speed: " << best_speed << "..." << std::endl;
if (test_best_batch) {
std::wclog << "Starting speed test... Best of " << NB_ITERATION
<< " iterations..." << std::endl;
std::vector<double> res;
for (int i = 0; i < NB_ITERATION; i++) {
// Actual test
simdjson::dom::parser parser;
simdjson::error_code error;
auto start = std::chrono::steady_clock::now();
// This includes allocation of the parser
simdjson::dom::document_stream docs;
if ((error = parser.parse_many(p, optimal_batch_size).get(docs))) {
std::wcerr << "Parsing failed with: " << error << std::endl;
exit(1);
}
for (auto result : docs) {
error = result.error();
if (error) {
std::wcerr << "Parsing failed with: " << error << std::endl;
exit(1);
}
}
auto end = std::chrono::steady_clock::now();
std::chrono::duration<double> secs = end - start;
res.push_back(secs.count());
}
double min_result = *min_element(res.begin(), res.end());
double speedinGBs =
static_cast<double>(p.size()) / (min_result * 1000000000.0);
std::cout << "Min: " << min_result << " bytes read: " << p.size()
<< " Gigabytes/second: " << speedinGBs << std::endl;
}
#ifdef SIMDJSON_THREADS_ENABLED
// Multithreading probably does not help matters for small files (less than 10
// MB).
if (p.size() < 10000000) {
std::cout << std::endl;
std::cout << "Warning: your file is small and the performance results are "
"probably meaningless"
<< std::endl;
std::cout << "as far as multithreaded performance goes." << std::endl;
std::cout << std::endl;
std::cout
<< "Try to concatenate the file with itself to generate a large one."
<< std::endl;
std::cout << "In bash: " << std::endl;
std::cout << "for i in {1..1000}; do cat '" << filename
<< "' >> bar.ndjson; done" << std::endl;
std::cout << argv[0] << " bar.ndjson" << std::endl;
}
#endif
return 0;
}
|
