internal_stats.cc 17.5 KB
Newer Older
I
Igor Canadi 已提交
1 2 3 4 5 6 7 8 9
//  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.
//
// 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 "db/internal_stats.h"
I
Igor Canadi 已提交
10 11
#define __STDC_FORMAT_MACROS
#include <inttypes.h>
I
Igor Canadi 已提交
12
#include <vector>
13
#include "db/column_family.h"
14
#include "db/db_impl.h"
I
Igor Canadi 已提交
15 16 17

namespace rocksdb {

L
Lei Jin 已提交
18 19 20 21
namespace {
const double kMB = 1048576.0;
const double kGB = kMB * 1024;

22
void PrintLevelStatsHeader(char* buf, size_t len, const std::string& cf_name) {
L
Lei Jin 已提交
23 24
  snprintf(
      buf, len,
25 26
      "\n** Compaction Stats [%s] **\n"
      "Level   Files   Size(MB) Score Read(GB)  Rn(GB) Rnp1(GB) "
I
Igor Canadi 已提交
27
      "Write(GB) Wnew(GB) RW-Amp W-Amp Rd(MB/s) Wr(MB/s)  Rn(cnt) "
L
Lei Jin 已提交
28 29 30 31
      "Rnp1(cnt) Wnp1(cnt) Wnew(cnt)  Comp(sec) Comp(cnt) Avg(sec) "
      "Stall(sec) Stall(cnt) Avg(ms)\n"
      "--------------------------------------------------------------------"
      "--------------------------------------------------------------------"
32 33
      "--------------------------------------------------------------------\n",
      cf_name.c_str());
L
Lei Jin 已提交
34 35 36
}

void PrintLevelStats(char* buf, size_t len, const std::string& name,
37 38
    int num_files, int being_compacted, double total_file_size, double score,
    double rw_amp, double w_amp, double stall_us, uint64_t stalls,
L
Lei Jin 已提交
39
    const InternalStats::CompactionStats& stats) {
40 41
  uint64_t bytes_read = stats.bytes_readn + stats.bytes_readnp1;
  uint64_t bytes_new = stats.bytes_written - stats.bytes_readnp1;
L
Lei Jin 已提交
42 43 44
  double elapsed = (stats.micros + 1) / 1000000.0;

  snprintf(buf, len,
45
    "%4s %5d/%-3d %8.0f %5.1f " /* Level, Files, Size(MB), Score */
L
Lei Jin 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
    "%8.1f " /* Read(GB) */
    "%7.1f " /* Rn(GB) */
    "%8.1f " /* Rnp1(GB) */
    "%9.1f " /* Write(GB) */
    "%8.1f " /* Wnew(GB) */
    "%6.1f " /* RW-Amp */
    "%5.1f " /* W-Amp */
    "%8.1f " /* Rd(MB/s) */
    "%8.1f " /* Wr(MB/s) */
    "%8d " /* Rn(cnt) */
    "%9d " /* Rnp1(cnt) */
    "%9d " /* Wnp1(cnt) */
    "%9d " /* Wnew(cnt) */
    "%10.0f " /* Comp(sec) */
    "%9d " /* Comp(cnt) */
    "%8.3f " /* Avg(sec) */
62 63
    "%10.2f " /* Stall(sec) */
    "%10" PRIu64 " " /* Stall(cnt) */
L
Lei Jin 已提交
64
    "%7.2f\n" /* Avg(ms) */,
65
    name.c_str(), num_files, being_compacted, total_file_size / kMB, score,
L
Lei Jin 已提交
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
    bytes_read / kGB,
    stats.bytes_readn / kGB,
    stats.bytes_readnp1 / kGB,
    stats.bytes_written / kGB,
    bytes_new / kGB,
    rw_amp,
    w_amp,
    bytes_read / kMB / elapsed,
    stats.bytes_written / kMB / elapsed,
    stats.files_in_leveln,
    stats.files_in_levelnp1,
    stats.files_out_levelnp1,
    stats.files_out_levelnp1 - stats.files_in_levelnp1,
    stats.micros / 1000000.0,
    stats.count,
    stats.count == 0 ? 0 : stats.micros / 1000000.0 / stats.count,
    stall_us / 1000000.0,
    stalls,
    stalls == 0 ? 0 : stall_us / 1000.0 / stalls);
}

87

L
Lei Jin 已提交
88 89
}

90 91 92 93
DBPropertyType GetPropertyType(const Slice& property, bool* is_int_property,
                               bool* need_out_of_mutex) {
  assert(is_int_property != nullptr);
  assert(need_out_of_mutex != nullptr);
I
Igor Canadi 已提交
94 95
  Slice in = property;
  Slice prefix("rocksdb.");
96
  *need_out_of_mutex = false;
97
  *is_int_property = false;
S
sdong 已提交
98 99 100
  if (!in.starts_with(prefix)) {
    return kUnknown;
  }
I
Igor Canadi 已提交
101 102 103
  in.remove_prefix(prefix.size());

  if (in.starts_with("num-files-at-level")) {
104
    return kNumFilesAtLevel;
I
Igor Canadi 已提交
105
  } else if (in == "levelstats") {
106
    return kLevelStats;
I
Igor Canadi 已提交
107
  } else if (in == "stats") {
108
    return kStats;
109 110 111 112
  } else if (in == "cfstats") {
    return kCFStats;
  } else if (in == "dbstats") {
    return kDBStats;
113 114
  } else if (in == "sstables") {
    return kSsTables;
115 116 117 118
  }

  *is_int_property = true;
  if (in == "num-immutable-mem-table") {
119 120
    return kNumImmutableMemTable;
  } else if (in == "mem-table-flush-pending") {
121
    return kMemtableFlushPending;
122
  } else if (in == "compaction-pending") {
123 124 125
    return kCompactionPending;
  } else if (in == "background-errors") {
    return kBackgroundErrors;
126 127
  } else if (in == "cur-size-active-mem-table") {
    return kCurSizeActiveMemTable;
128 129 130 131
  } else if (in == "num-entries-active-mem-table") {
    return kNumEntriesInMutableMemtable;
  } else if (in == "num-entries-imm-mem-tables") {
    return kNumEntriesInImmutableMemtable;
S
sdong 已提交
132 133
  } else if (in == "estimate-num-keys") {
    return kEstimatedNumKeys;
134 135 136
  } else if (in == "estimate-table-readers-mem") {
    *need_out_of_mutex = true;
    return kEstimatedUsageByTableReaders;
137 138
  } else if (in == "is-file-deletions-enabled") {
    return kIsFileDeletionEnabled;
139 140 141 142
  }
  return kUnknown;
}

143 144 145 146 147 148
bool InternalStats::GetIntPropertyOutOfMutex(DBPropertyType property_type,
                                             Version* version,
                                             uint64_t* value) const {
  assert(value != nullptr);
  if (property_type != kEstimatedUsageByTableReaders) {
    return false;
149
  }
150 151 152 153 154 155 156
  if (version == nullptr) {
    *value = 0;
  } else {
    *value = version->GetMemoryUsageByTableReaders();
  }
  return true;
}
157

158 159 160 161
bool InternalStats::GetStringProperty(DBPropertyType property_type,
                                      const Slice& property,
                                      std::string* value) {
  assert(value != nullptr);
162
  Version* current = cfd_->current();
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
  Slice in = property;

  switch (property_type) {
    case kNumFilesAtLevel: {
      in.remove_prefix(strlen("rocksdb.num-files-at-level"));
      uint64_t level;
      bool ok = ConsumeDecimalNumber(&in, &level) && in.empty();
      if (!ok || (int)level >= number_levels_) {
        return false;
      } else {
        char buf[100];
        snprintf(buf, sizeof(buf), "%d",
                 current->NumLevelFiles(static_cast<int>(level)));
        *value = buf;
        return true;
      }
I
Igor Canadi 已提交
179
    }
180 181 182 183 184 185
    case kLevelStats: {
      char buf[1000];
      snprintf(buf, sizeof(buf),
               "Level Files Size(MB)\n"
               "--------------------\n");
      value->append(buf);
I
Igor Canadi 已提交
186

187 188 189
      for (int level = 0; level < number_levels_; level++) {
        snprintf(buf, sizeof(buf), "%3d %8d %8.0f\n", level,
                 current->NumLevelFiles(level),
L
Lei Jin 已提交
190
                 current->NumLevelBytes(level) / kMB);
I
Igor Canadi 已提交
191 192
        value->append(buf);
      }
193
      return true;
I
Igor Canadi 已提交
194
    }
195
    case kStats: {
196
      if (!GetStringProperty(kCFStats, "rocksdb.cfstats", value)) {
197
        return false;
198
      }
199
      if (!GetStringProperty(kDBStats, "rocksdb.dbstats", value)) {
200
        return false;
L
Lei Jin 已提交
201
      }
202 203 204
      return true;
    }
    case kCFStats: {
205
      DumpCFStats(value);
206 207 208 209
      return true;
    }
    case kDBStats: {
      DumpDBStats(value);
210 211 212 213 214
      return true;
    }
    case kSsTables:
      *value = current->DebugString();
      return true;
215 216 217 218 219 220
    default:
      return false;
  }
}

bool InternalStats::GetIntProperty(DBPropertyType property_type,
221
                                   uint64_t* value, DBImpl* db) const {
222 223 224
  Version* current = cfd_->current();

  switch (property_type) {
225
    case kNumImmutableMemTable:
226
      *value = cfd_->imm()->size();
227
      return true;
228
    case kMemtableFlushPending:
229
      // Return number of mem tables that are ready to flush (made immutable)
230
      *value = (cfd_->imm()->IsFlushPending() ? 1 : 0);
231
      return true;
232
    case kCompactionPending:
233 234
      // 1 if the system already determines at least one compacdtion is needed.
      // 0 otherwise,
235
      *value = (current->NeedsCompaction() ? 1 : 0);
236
      return true;
237 238
    case kBackgroundErrors:
      // Accumulated number of  errors in background flushes or compactions.
239
      *value = GetBackgroundErrorCount();
240
      return true;
241 242
    case kCurSizeActiveMemTable:
      // Current size of the active memtable
243
      *value = cfd_->mem()->ApproximateMemoryUsage();
244
      return true;
245 246
    case kNumEntriesInMutableMemtable:
      // Current size of the active memtable
247
      *value = cfd_->mem()->GetNumEntries();
248 249 250
      return true;
    case kNumEntriesInImmutableMemtable:
      // Current size of the active memtable
251
      *value = cfd_->imm()->current()->GetTotalNumEntries();
252
      return true;
S
sdong 已提交
253 254 255
    case kEstimatedNumKeys:
      // Estimate number of entries in the column family:
      // Use estimated entries in tables + total entries in memtables.
256 257 258
      *value = cfd_->mem()->GetNumEntries() +
               cfd_->imm()->current()->GetTotalNumEntries() +
               current->GetEstimatedActiveKeys();
S
sdong 已提交
259
      return true;
I
Igor Canadi 已提交
260
#ifndef ROCKSDB_LITE
261 262 263
    case kIsFileDeletionEnabled:
      *value = db->IsFileDeletionsEnabled();
      return true;
I
Igor Canadi 已提交
264
#endif
265 266 267
    default:
      return false;
  }
I
Igor Canadi 已提交
268 269
}

270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
void InternalStats::DumpDBStats(std::string* value) {
  char buf[1000];
  // DB-level stats, only available from default column family
  double seconds_up = (env_->NowMicros() - started_at_ + 1) / 1000000.0;
  double interval_seconds_up = seconds_up - db_stats_snapshot_.seconds_up;
  snprintf(buf, sizeof(buf),
           "\n** DB Stats **\nUptime(secs): %.1f total, %.1f interval\n",
           seconds_up, interval_seconds_up);
  value->append(buf);
  // Cumulative
  uint64_t user_bytes_written = db_stats_[InternalStats::BYTES_WRITTEN];
  uint64_t write_other = db_stats_[InternalStats::WRITE_DONE_BY_OTHER];
  uint64_t write_self = db_stats_[InternalStats::WRITE_DONE_BY_SELF];
  uint64_t wal_bytes = db_stats_[InternalStats::WAL_FILE_BYTES];
  uint64_t wal_synced = db_stats_[InternalStats::WAL_FILE_SYNCED];
  uint64_t write_with_wal = db_stats_[InternalStats::WRITE_WITH_WAL];
  // Data
  snprintf(buf, sizeof(buf),
           "Cumulative writes: %" PRIu64 " writes, %" PRIu64 " batches, "
           "%.1f writes per batch, %.2f GB user ingest\n",
           write_other + write_self, write_self,
           (write_other + write_self) / static_cast<double>(write_self + 1),
           user_bytes_written / kGB);
  value->append(buf);
  // WAL
  snprintf(buf, sizeof(buf),
           "Cumulative WAL: %" PRIu64 " writes, %" PRIu64 " syncs, "
           "%.2f writes per sync, %.2f GB written\n",
           write_with_wal, wal_synced,
           write_with_wal / static_cast<double>(wal_synced + 1),
           wal_bytes / kGB);
  value->append(buf);

  // Interval
  uint64_t interval_write_other = write_other - db_stats_snapshot_.write_other;
  uint64_t interval_write_self = write_self - db_stats_snapshot_.write_self;
  snprintf(buf, sizeof(buf),
           "Interval writes: %" PRIu64 " writes, %" PRIu64 " batches, "
           "%.1f writes per batch, %.1f MB user ingest\n",
           interval_write_other + interval_write_self,
           interval_write_self,
           static_cast<double>(interval_write_other + interval_write_self) /
               (interval_write_self + 1),
           (user_bytes_written - db_stats_snapshot_.ingest_bytes) / kMB);
  value->append(buf);

  uint64_t interval_write_with_wal =
      write_with_wal - db_stats_snapshot_.write_with_wal;
  uint64_t interval_wal_synced = wal_synced - db_stats_snapshot_.wal_synced;
  uint64_t interval_wal_bytes = wal_bytes - db_stats_snapshot_.wal_bytes;

  snprintf(buf, sizeof(buf),
           "Interval WAL: %" PRIu64 " writes, %" PRIu64 " syncs, "
           "%.2f writes per sync, %.2f MB written\n",
           interval_write_with_wal,
           interval_wal_synced,
           interval_write_with_wal /
              static_cast<double>(interval_wal_synced + 1),
           interval_wal_bytes / kGB);
  value->append(buf);

  db_stats_snapshot_.seconds_up = seconds_up;
  db_stats_snapshot_.ingest_bytes = user_bytes_written;
  db_stats_snapshot_.write_other = write_other;
  db_stats_snapshot_.write_self = write_self;
  db_stats_snapshot_.wal_bytes = wal_bytes;
  db_stats_snapshot_.wal_synced = wal_synced;
  db_stats_snapshot_.write_with_wal = write_with_wal;
}

340 341
void InternalStats::DumpCFStats(std::string* value) {
  Version* current = cfd_->current();
342 343

  int num_levels_to_check =
344 345
      (cfd_->options()->compaction_style != kCompactionStyleUniversal &&
       cfd_->options()->compaction_style != kCompactionStyleFIFO)
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
          ? current->NumberLevels() - 1
          : 1;
  // Compaction scores are sorted base on its value. Restore them to the
  // level order
  std::vector<double> compaction_score(number_levels_, 0);
  for (int i = 0; i < num_levels_to_check; ++i) {
    compaction_score[current->compaction_level_[i]] =
      current->compaction_score_[i];
  }
  // Count # of files being compacted for each level
  std::vector<int> files_being_compacted(number_levels_, 0);
  for (int level = 0; level < num_levels_to_check; ++level) {
    for (auto* f : current->files_[level]) {
      if (f->being_compacted) {
        ++files_being_compacted[level];
      }
    }
  }

  char buf[1000];
  // Per-ColumnFamily stats
367
  PrintLevelStatsHeader(buf, sizeof(buf), cfd_->GetName());
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477
  value->append(buf);

  CompactionStats stats_sum(0);
  int total_files = 0;
  int total_files_being_compacted = 0;
  double total_file_size = 0;
  uint64_t total_slowdown_soft = 0;
  uint64_t total_slowdown_count_soft = 0;
  uint64_t total_slowdown_hard = 0;
  uint64_t total_slowdown_count_hard = 0;
  uint64_t total_stall_count = 0;
  double total_stall_us = 0;
  for (int level = 0; level < number_levels_; level++) {
    int files = current->NumLevelFiles(level);
    total_files += files;
    total_files_being_compacted += files_being_compacted[level];
    if (comp_stats_[level].micros > 0 || files > 0) {
      uint64_t stalls = level == 0 ?
        (cf_stats_count_[LEVEL0_SLOWDOWN] +
         cf_stats_count_[LEVEL0_NUM_FILES] +
         cf_stats_count_[MEMTABLE_COMPACTION])
        : (stall_leveln_slowdown_count_soft_[level] +
           stall_leveln_slowdown_count_hard_[level]);

      double stall_us = level == 0 ?
         (cf_stats_value_[LEVEL0_SLOWDOWN] +
          cf_stats_value_[LEVEL0_NUM_FILES] +
          cf_stats_value_[MEMTABLE_COMPACTION])
         : (stall_leveln_slowdown_soft_[level] +
            stall_leveln_slowdown_hard_[level]);

      stats_sum.Add(comp_stats_[level]);
      total_file_size += current->NumLevelBytes(level);
      total_stall_us += stall_us;
      total_stall_count += stalls;
      total_slowdown_soft += stall_leveln_slowdown_soft_[level];
      total_slowdown_count_soft += stall_leveln_slowdown_count_soft_[level];
      total_slowdown_hard += stall_leveln_slowdown_hard_[level];
      total_slowdown_count_hard += stall_leveln_slowdown_count_hard_[level];
      int64_t bytes_read = comp_stats_[level].bytes_readn +
                           comp_stats_[level].bytes_readnp1;
      double rw_amp = (comp_stats_[level].bytes_readn == 0) ? 0.0
          : (comp_stats_[level].bytes_written + bytes_read) /
            static_cast<double>(comp_stats_[level].bytes_readn);
      double w_amp = (comp_stats_[level].bytes_readn == 0) ? 0.0
          : comp_stats_[level].bytes_written /
            static_cast<double>(comp_stats_[level].bytes_readn);
      PrintLevelStats(buf, sizeof(buf), "L" + std::to_string(level),
          files, files_being_compacted[level], current->NumLevelBytes(level),
          compaction_score[level], rw_amp, w_amp, stall_us, stalls,
          comp_stats_[level]);
      value->append(buf);
    }
  }
  uint64_t curr_ingest = cf_stats_value_[BYTES_FLUSHED];
  // Cumulative summary
  double rw_amp = (stats_sum.bytes_written + stats_sum.bytes_readn +
      stats_sum.bytes_readnp1) / static_cast<double>(curr_ingest + 1);
  double w_amp = stats_sum.bytes_written / static_cast<double>(curr_ingest + 1);
  // Stats summary across levels
  PrintLevelStats(buf, sizeof(buf), "Sum", total_files,
      total_files_being_compacted, total_file_size, 0, rw_amp, w_amp,
      total_stall_us, total_stall_count, stats_sum);
  value->append(buf);
  // Interval summary
  uint64_t interval_ingest =
      curr_ingest - cf_stats_snapshot_.ingest_bytes + 1;
  CompactionStats interval_stats(stats_sum);
  interval_stats.Subtract(cf_stats_snapshot_.comp_stats);
  rw_amp = (interval_stats.bytes_written +
      interval_stats.bytes_readn + interval_stats.bytes_readnp1) /
      static_cast<double>(interval_ingest);
  w_amp = interval_stats.bytes_written / static_cast<double>(interval_ingest);
  PrintLevelStats(buf, sizeof(buf), "Int", 0, 0, 0, 0,
      rw_amp, w_amp, total_stall_us - cf_stats_snapshot_.stall_us,
      total_stall_count - cf_stats_snapshot_.stall_count, interval_stats);
  value->append(buf);

  snprintf(buf, sizeof(buf),
           "Flush(GB): accumulative %.3f, interval %.3f\n",
           curr_ingest / kGB, interval_ingest / kGB);
  value->append(buf);
  snprintf(buf, sizeof(buf),
           "Stalls(secs): %.3f level0_slowdown, %.3f level0_numfiles, "
           "%.3f memtable_compaction, %.3f leveln_slowdown_soft, "
           "%.3f leveln_slowdown_hard\n",
           cf_stats_value_[LEVEL0_SLOWDOWN] / 1000000.0,
           cf_stats_value_[LEVEL0_NUM_FILES] / 1000000.0,
           cf_stats_value_[MEMTABLE_COMPACTION] / 1000000.0,
           total_slowdown_soft / 1000000.0,
           total_slowdown_hard / 1000000.0);
  value->append(buf);

  snprintf(buf, sizeof(buf),
           "Stalls(count): %" PRIu64 " level0_slowdown, "
           "%" PRIu64 " level0_numfiles, %" PRIu64 " memtable_compaction, "
           "%" PRIu64 " leveln_slowdown_soft, "
           "%" PRIu64 " leveln_slowdown_hard\n",
           cf_stats_count_[LEVEL0_SLOWDOWN],
           cf_stats_count_[LEVEL0_NUM_FILES],
           cf_stats_count_[MEMTABLE_COMPACTION],
           total_slowdown_count_soft, total_slowdown_count_hard);
  value->append(buf);

  cf_stats_snapshot_.ingest_bytes = curr_ingest;
  cf_stats_snapshot_.comp_stats = stats_sum;
  cf_stats_snapshot_.stall_us = total_stall_us;
  cf_stats_snapshot_.stall_count = total_stall_count;
}

I
Igor Canadi 已提交
478
}  // namespace rocksdb