Line data Source code
1 : // Copyright 2011 The LevelDB-Go and Pebble Authors. All rights reserved. Use
2 : // of this source code is governed by a BSD-style license that can be found in
3 : // the LICENSE file.
4 :
5 : package pebble
6 :
7 : import (
8 : "bytes"
9 : "fmt"
10 : "io"
11 : "runtime"
12 : "strconv"
13 : "strings"
14 : "time"
15 : "unicode"
16 :
17 : "github.com/cockroachdb/errors"
18 : "github.com/cockroachdb/pebble/internal/base"
19 : "github.com/cockroachdb/pebble/internal/cache"
20 : "github.com/cockroachdb/pebble/internal/humanize"
21 : "github.com/cockroachdb/pebble/internal/keyspan"
22 : "github.com/cockroachdb/pebble/internal/manifest"
23 : "github.com/cockroachdb/pebble/objstorage/remote"
24 : "github.com/cockroachdb/pebble/rangekey"
25 : "github.com/cockroachdb/pebble/sstable"
26 : "github.com/cockroachdb/pebble/vfs"
27 : )
28 :
29 : const (
30 : cacheDefaultSize = 8 << 20 // 8 MB
31 : defaultLevelMultiplier = 10
32 : )
33 :
34 : // Compression exports the base.Compression type.
35 : type Compression = sstable.Compression
36 :
37 : // Exported Compression constants.
38 : const (
39 : DefaultCompression = sstable.DefaultCompression
40 : NoCompression = sstable.NoCompression
41 : SnappyCompression = sstable.SnappyCompression
42 : ZstdCompression = sstable.ZstdCompression
43 : )
44 :
45 : // FilterType exports the base.FilterType type.
46 : type FilterType = base.FilterType
47 :
48 : // Exported TableFilter constants.
49 : const (
50 : TableFilter = base.TableFilter
51 : )
52 :
53 : // FilterWriter exports the base.FilterWriter type.
54 : type FilterWriter = base.FilterWriter
55 :
56 : // FilterPolicy exports the base.FilterPolicy type.
57 : type FilterPolicy = base.FilterPolicy
58 :
59 : // TablePropertyCollector exports the sstable.TablePropertyCollector type.
60 : type TablePropertyCollector = sstable.TablePropertyCollector
61 :
62 : // BlockPropertyCollector exports the sstable.BlockPropertyCollector type.
63 : type BlockPropertyCollector = sstable.BlockPropertyCollector
64 :
65 : // BlockPropertyFilter exports the sstable.BlockPropertyFilter type.
66 : type BlockPropertyFilter = base.BlockPropertyFilter
67 :
68 : // ShortAttributeExtractor exports the base.ShortAttributeExtractor type.
69 : type ShortAttributeExtractor = base.ShortAttributeExtractor
70 :
71 : // UserKeyPrefixBound exports the sstable.UserKeyPrefixBound type.
72 : type UserKeyPrefixBound = sstable.UserKeyPrefixBound
73 :
74 : // IterKeyType configures which types of keys an iterator should surface.
75 : type IterKeyType int8
76 :
77 : const (
78 : // IterKeyTypePointsOnly configures an iterator to iterate over point keys
79 : // only.
80 : IterKeyTypePointsOnly IterKeyType = iota
81 : // IterKeyTypeRangesOnly configures an iterator to iterate over range keys
82 : // only.
83 : IterKeyTypeRangesOnly
84 : // IterKeyTypePointsAndRanges configures an iterator iterate over both point
85 : // keys and range keys simultaneously.
86 : IterKeyTypePointsAndRanges
87 : )
88 :
89 : // String implements fmt.Stringer.
90 1 : func (t IterKeyType) String() string {
91 1 : switch t {
92 1 : case IterKeyTypePointsOnly:
93 1 : return "points-only"
94 1 : case IterKeyTypeRangesOnly:
95 1 : return "ranges-only"
96 1 : case IterKeyTypePointsAndRanges:
97 1 : return "points-and-ranges"
98 0 : default:
99 0 : panic(fmt.Sprintf("unknown key type %d", t))
100 : }
101 : }
102 :
103 : // IterOptions hold the optional per-query parameters for NewIter.
104 : //
105 : // Like Options, a nil *IterOptions is valid and means to use the default
106 : // values.
107 : type IterOptions struct {
108 : // LowerBound specifies the smallest key (inclusive) that the iterator will
109 : // return during iteration. If the iterator is seeked or iterated past this
110 : // boundary the iterator will return Valid()==false. Setting LowerBound
111 : // effectively truncates the key space visible to the iterator.
112 : LowerBound []byte
113 : // UpperBound specifies the largest key (exclusive) that the iterator will
114 : // return during iteration. If the iterator is seeked or iterated past this
115 : // boundary the iterator will return Valid()==false. Setting UpperBound
116 : // effectively truncates the key space visible to the iterator.
117 : UpperBound []byte
118 : // TableFilter can be used to filter the tables that are scanned during
119 : // iteration based on the user properties. Return true to scan the table and
120 : // false to skip scanning. This function must be thread-safe since the same
121 : // function can be used by multiple iterators, if the iterator is cloned.
122 : TableFilter func(userProps map[string]string) bool
123 : // SkipPoint may be used to skip over point keys that don't match an
124 : // arbitrary predicate during iteration. If set, the Iterator invokes
125 : // SkipPoint for keys encountered. If SkipPoint returns true, the iterator
126 : // will skip the key without yielding it to the iterator operation in
127 : // progress.
128 : //
129 : // SkipPoint must be a pure function and always return the same result when
130 : // provided the same arguments. The iterator may call SkipPoint multiple
131 : // times for the same user key.
132 : SkipPoint func(userKey []byte) bool
133 : // PointKeyFilters can be used to avoid scanning tables and blocks in tables
134 : // when iterating over point keys. This slice represents an intersection
135 : // across all filters, i.e., all filters must indicate that the block is
136 : // relevant.
137 : //
138 : // Performance note: When len(PointKeyFilters) > 0, the caller should ensure
139 : // that cap(PointKeyFilters) is at least len(PointKeyFilters)+1. This helps
140 : // avoid allocations in Pebble internal code that mutates the slice.
141 : PointKeyFilters []BlockPropertyFilter
142 : // RangeKeyFilters can be usefd to avoid scanning tables and blocks in tables
143 : // when iterating over range keys. The same requirements that apply to
144 : // PointKeyFilters apply here too.
145 : RangeKeyFilters []BlockPropertyFilter
146 : // KeyTypes configures which types of keys to iterate over: point keys,
147 : // range keys, or both.
148 : KeyTypes IterKeyType
149 : // RangeKeyMasking can be used to enable automatic masking of point keys by
150 : // range keys. Range key masking is only supported during combined range key
151 : // and point key iteration mode (IterKeyTypePointsAndRanges).
152 : RangeKeyMasking RangeKeyMasking
153 :
154 : // OnlyReadGuaranteedDurable is an advanced option that is only supported by
155 : // the Reader implemented by DB. When set to true, only the guaranteed to be
156 : // durable state is visible in the iterator.
157 : // - This definition is made under the assumption that the FS implementation
158 : // is providing a durability guarantee when data is synced.
159 : // - The visible state represents a consistent point in the history of the
160 : // DB.
161 : // - The implementation is free to choose a conservative definition of what
162 : // is guaranteed durable. For simplicity, the current implementation
163 : // ignores memtables. A more sophisticated implementation could track the
164 : // highest seqnum that is synced to the WAL and published and use that as
165 : // the visible seqnum for an iterator. Note that the latter approach is
166 : // not strictly better than the former since we can have DBs that are (a)
167 : // synced more rarely than memtable flushes, (b) have no WAL. (a) is
168 : // likely to be true in a future CockroachDB context where the DB
169 : // containing the state machine may be rarely synced.
170 : // NB: this current implementation relies on the fact that memtables are
171 : // flushed in seqnum order, and any ingested sstables that happen to have a
172 : // lower seqnum than a non-flushed memtable don't have any overlapping keys.
173 : // This is the fundamental level invariant used in other code too, like when
174 : // merging iterators.
175 : //
176 : // Semantically, using this option provides the caller a "snapshot" as of
177 : // the time the most recent memtable was flushed. An alternate interface
178 : // would be to add a NewSnapshot variant. Creating a snapshot is heavier
179 : // weight than creating an iterator, so we have opted to support this
180 : // iterator option.
181 : OnlyReadGuaranteedDurable bool
182 : // UseL6Filters allows the caller to opt into reading filter blocks for L6
183 : // sstables. Helpful if a lot of SeekPrefixGEs are expected in quick
184 : // succession, that are also likely to not yield a single key. Filter blocks in
185 : // L6 can be relatively large, often larger than data blocks, so the benefit of
186 : // loading them in the cache is minimized if the probability of the key
187 : // existing is not low or if we just expect a one-time Seek (where loading the
188 : // data block directly is better).
189 : UseL6Filters bool
190 : // CategoryAndQoS is used for categorized iterator stats. This should not be
191 : // changed by calling SetOptions.
192 : sstable.CategoryAndQoS
193 :
194 : // Internal options.
195 :
196 : logger Logger
197 : // Level corresponding to this file. Only passed in if constructed by a
198 : // levelIter.
199 : level manifest.Level
200 : // disableLazyCombinedIteration is an internal testing option.
201 : disableLazyCombinedIteration bool
202 : // snapshotForHideObsoletePoints is specified for/by levelIter when opening
203 : // files and is used to decide whether to hide obsolete points. A value of 0
204 : // implies obsolete points should not be hidden.
205 : snapshotForHideObsoletePoints uint64
206 :
207 : // NB: If adding new Options, you must account for them in iterator
208 : // construction and Iterator.SetOptions.
209 : }
210 :
211 : // GetLowerBound returns the LowerBound or nil if the receiver is nil.
212 1 : func (o *IterOptions) GetLowerBound() []byte {
213 1 : if o == nil {
214 1 : return nil
215 1 : }
216 1 : return o.LowerBound
217 : }
218 :
219 : // GetUpperBound returns the UpperBound or nil if the receiver is nil.
220 1 : func (o *IterOptions) GetUpperBound() []byte {
221 1 : if o == nil {
222 1 : return nil
223 1 : }
224 1 : return o.UpperBound
225 : }
226 :
227 1 : func (o *IterOptions) pointKeys() bool {
228 1 : if o == nil {
229 0 : return true
230 0 : }
231 1 : return o.KeyTypes == IterKeyTypePointsOnly || o.KeyTypes == IterKeyTypePointsAndRanges
232 : }
233 :
234 1 : func (o *IterOptions) rangeKeys() bool {
235 1 : if o == nil {
236 0 : return false
237 0 : }
238 1 : return o.KeyTypes == IterKeyTypeRangesOnly || o.KeyTypes == IterKeyTypePointsAndRanges
239 : }
240 :
241 1 : func (o *IterOptions) getLogger() Logger {
242 1 : if o == nil || o.logger == nil {
243 1 : return DefaultLogger
244 1 : }
245 1 : return o.logger
246 : }
247 :
248 : // SpanIterOptions creates a SpanIterOptions from this IterOptions.
249 1 : func (o *IterOptions) SpanIterOptions() keyspan.SpanIterOptions {
250 1 : if o == nil {
251 0 : return keyspan.SpanIterOptions{}
252 0 : }
253 1 : return keyspan.SpanIterOptions{
254 1 : RangeKeyFilters: o.RangeKeyFilters,
255 1 : }
256 : }
257 :
258 : // scanInternalOptions is similar to IterOptions, meant for use with
259 : // scanInternalIterator.
260 : type scanInternalOptions struct {
261 : sstable.CategoryAndQoS
262 : IterOptions
263 :
264 : visitPointKey func(key *InternalKey, value LazyValue, iterInfo IteratorLevel) error
265 : visitRangeDel func(start, end []byte, seqNum uint64) error
266 : visitRangeKey func(start, end []byte, keys []rangekey.Key) error
267 : visitSharedFile func(sst *SharedSSTMeta) error
268 :
269 : // skipSharedLevels skips levels that are shareable (level >=
270 : // sharedLevelStart).
271 : skipSharedLevels bool
272 :
273 : // includeObsoleteKeys specifies whether keys shadowed by newer internal keys
274 : // are exposed. If false, only one internal key per user key is exposed.
275 : includeObsoleteKeys bool
276 :
277 : // rateLimitFunc is used to limit the amount of bytes read per second.
278 : rateLimitFunc func(key *InternalKey, value LazyValue) error
279 : }
280 :
281 : // RangeKeyMasking configures automatic hiding of point keys by range keys. A
282 : // non-nil Suffix enables range-key masking. When enabled, range keys with
283 : // suffixes ≥ Suffix behave as masks. All point keys that are contained within a
284 : // masking range key's bounds and have suffixes greater than the range key's
285 : // suffix are automatically skipped.
286 : //
287 : // Specifically, when configured with a RangeKeyMasking.Suffix _s_, and there
288 : // exists a range key with suffix _r_ covering a point key with suffix _p_, and
289 : //
290 : // _s_ ≤ _r_ < _p_
291 : //
292 : // then the point key is elided.
293 : //
294 : // Range-key masking may only be used when iterating over both point keys and
295 : // range keys with IterKeyTypePointsAndRanges.
296 : type RangeKeyMasking struct {
297 : // Suffix configures which range keys may mask point keys. Only range keys
298 : // that are defined at suffixes greater than or equal to Suffix will mask
299 : // point keys.
300 : Suffix []byte
301 : // Filter is an optional field that may be used to improve performance of
302 : // range-key masking through a block-property filter defined over key
303 : // suffixes. If non-nil, Filter is called by Pebble to construct a
304 : // block-property filter mask at iterator creation. The filter is used to
305 : // skip whole point-key blocks containing point keys with suffixes greater
306 : // than a covering range-key's suffix.
307 : //
308 : // To use this functionality, the caller must create and configure (through
309 : // Options.BlockPropertyCollectors) a block-property collector that records
310 : // the maxmimum suffix contained within a block. The caller then must write
311 : // and provide a BlockPropertyFilterMask implementation on that same
312 : // property. See the BlockPropertyFilterMask type for more information.
313 : Filter func() BlockPropertyFilterMask
314 : }
315 :
316 : // BlockPropertyFilterMask extends the BlockPropertyFilter interface for use
317 : // with range-key masking. Unlike an ordinary block property filter, a
318 : // BlockPropertyFilterMask's filtering criteria is allowed to change when Pebble
319 : // invokes its SetSuffix method.
320 : //
321 : // When a Pebble iterator steps into a range key's bounds and the range key has
322 : // a suffix greater than or equal to RangeKeyMasking.Suffix, the range key acts
323 : // as a mask. The masking range key hides all point keys that fall within the
324 : // range key's bounds and have suffixes > the range key's suffix. Without a
325 : // filter mask configured, Pebble performs this hiding by stepping through point
326 : // keys and comparing suffixes. If large numbers of point keys are masked, this
327 : // requires Pebble to load, iterate through and discard a large number of
328 : // sstable blocks containing masked point keys.
329 : //
330 : // If a block-property collector and a filter mask are configured, Pebble may
331 : // skip loading some point-key blocks altogether. If a block's keys are known to
332 : // all fall within the bounds of the masking range key and the block was
333 : // annotated by a block-property collector with the maximal suffix, Pebble can
334 : // ask the filter mask to compare the property to the current masking range
335 : // key's suffix. If the mask reports no intersection, the block may be skipped.
336 : //
337 : // If unsuffixed and suffixed keys are written to the database, care must be
338 : // taken to avoid unintentionally masking un-suffixed keys located in the same
339 : // block as suffixed keys. One solution is to interpret unsuffixed keys as
340 : // containing the maximal suffix value, ensuring that blocks containing
341 : // unsuffixed keys are always loaded.
342 : type BlockPropertyFilterMask interface {
343 : BlockPropertyFilter
344 :
345 : // SetSuffix configures the mask with the suffix of a range key. The filter
346 : // should return false from Intersects whenever it's provided with a
347 : // property encoding a block's minimum suffix that's greater (according to
348 : // Compare) than the provided suffix.
349 : SetSuffix(suffix []byte) error
350 : }
351 :
352 : // WriteOptions hold the optional per-query parameters for Set and Delete
353 : // operations.
354 : //
355 : // Like Options, a nil *WriteOptions is valid and means to use the default
356 : // values.
357 : type WriteOptions struct {
358 : // Sync is whether to sync writes through the OS buffer cache and down onto
359 : // the actual disk, if applicable. Setting Sync is required for durability of
360 : // individual write operations but can result in slower writes.
361 : //
362 : // If false, and the process or machine crashes, then a recent write may be
363 : // lost. This is due to the recently written data being buffered inside the
364 : // process running Pebble. This differs from the semantics of a write system
365 : // call in which the data is buffered in the OS buffer cache and would thus
366 : // survive a process crash.
367 : //
368 : // The default value is true.
369 : Sync bool
370 : }
371 :
372 : // Sync specifies the default write options for writes which synchronize to
373 : // disk.
374 : var Sync = &WriteOptions{Sync: true}
375 :
376 : // NoSync specifies the default write options for writes which do not
377 : // synchronize to disk.
378 : var NoSync = &WriteOptions{Sync: false}
379 :
380 : // GetSync returns the Sync value or true if the receiver is nil.
381 1 : func (o *WriteOptions) GetSync() bool {
382 1 : return o == nil || o.Sync
383 1 : }
384 :
385 : // LevelOptions holds the optional per-level parameters.
386 : type LevelOptions struct {
387 : // BlockRestartInterval is the number of keys between restart points
388 : // for delta encoding of keys.
389 : //
390 : // The default value is 16.
391 : BlockRestartInterval int
392 :
393 : // BlockSize is the target uncompressed size in bytes of each table block.
394 : //
395 : // The default value is 4096.
396 : BlockSize int
397 :
398 : // BlockSizeThreshold finishes a block if the block size is larger than the
399 : // specified percentage of the target block size and adding the next entry
400 : // would cause the block to be larger than the target block size.
401 : //
402 : // The default value is 90
403 : BlockSizeThreshold int
404 :
405 : // Compression defines the per-block compression to use.
406 : //
407 : // The default value (DefaultCompression) uses snappy compression.
408 : Compression Compression
409 :
410 : // FilterPolicy defines a filter algorithm (such as a Bloom filter) that can
411 : // reduce disk reads for Get calls.
412 : //
413 : // One such implementation is bloom.FilterPolicy(10) from the pebble/bloom
414 : // package.
415 : //
416 : // The default value means to use no filter.
417 : FilterPolicy FilterPolicy
418 :
419 : // FilterType defines whether an existing filter policy is applied at a
420 : // block-level or table-level. Block-level filters use less memory to create,
421 : // but are slower to access as a check for the key in the index must first be
422 : // performed to locate the filter block. A table-level filter will require
423 : // memory proportional to the number of keys in an sstable to create, but
424 : // avoids the index lookup when determining if a key is present. Table-level
425 : // filters should be preferred except under constrained memory situations.
426 : FilterType FilterType
427 :
428 : // IndexBlockSize is the target uncompressed size in bytes of each index
429 : // block. When the index block size is larger than this target, two-level
430 : // indexes are automatically enabled. Setting this option to a large value
431 : // (such as math.MaxInt32) disables the automatic creation of two-level
432 : // indexes.
433 : //
434 : // The default value is the value of BlockSize.
435 : IndexBlockSize int
436 :
437 : // The target file size for the level.
438 : TargetFileSize int64
439 : }
440 :
441 : // EnsureDefaults ensures that the default values for all of the options have
442 : // been initialized. It is valid to call EnsureDefaults on a nil receiver. A
443 : // non-nil result will always be returned.
444 1 : func (o *LevelOptions) EnsureDefaults() *LevelOptions {
445 1 : if o == nil {
446 0 : o = &LevelOptions{}
447 0 : }
448 1 : if o.BlockRestartInterval <= 0 {
449 1 : o.BlockRestartInterval = base.DefaultBlockRestartInterval
450 1 : }
451 1 : if o.BlockSize <= 0 {
452 1 : o.BlockSize = base.DefaultBlockSize
453 1 : } else if o.BlockSize > sstable.MaximumBlockSize {
454 0 : panic(errors.Errorf("BlockSize %d exceeds MaximumBlockSize", o.BlockSize))
455 : }
456 1 : if o.BlockSizeThreshold <= 0 {
457 1 : o.BlockSizeThreshold = base.DefaultBlockSizeThreshold
458 1 : }
459 1 : if o.Compression <= DefaultCompression || o.Compression >= sstable.NCompression {
460 1 : o.Compression = SnappyCompression
461 1 : }
462 1 : if o.IndexBlockSize <= 0 {
463 1 : o.IndexBlockSize = o.BlockSize
464 1 : }
465 1 : if o.TargetFileSize <= 0 {
466 1 : o.TargetFileSize = 2 << 20 // 2 MB
467 1 : }
468 1 : return o
469 : }
470 :
471 : // Options holds the optional parameters for configuring pebble. These options
472 : // apply to the DB at large; per-query options are defined by the IterOptions
473 : // and WriteOptions types.
474 : type Options struct {
475 : // Sync sstables periodically in order to smooth out writes to disk. This
476 : // option does not provide any persistency guarantee, but is used to avoid
477 : // latency spikes if the OS automatically decides to write out a large chunk
478 : // of dirty filesystem buffers. This option only controls SSTable syncs; WAL
479 : // syncs are controlled by WALBytesPerSync.
480 : //
481 : // The default value is 512KB.
482 : BytesPerSync int
483 :
484 : // Cache is used to cache uncompressed blocks from sstables.
485 : //
486 : // The default cache size is 8 MB.
487 : Cache *cache.Cache
488 :
489 : // Cleaner cleans obsolete files.
490 : //
491 : // The default cleaner uses the DeleteCleaner.
492 : Cleaner Cleaner
493 :
494 : // Comparer defines a total ordering over the space of []byte keys: a 'less
495 : // than' relationship. The same comparison algorithm must be used for reads
496 : // and writes over the lifetime of the DB.
497 : //
498 : // The default value uses the same ordering as bytes.Compare.
499 : Comparer *Comparer
500 :
501 : // DebugCheck is invoked, if non-nil, whenever a new version is being
502 : // installed. Typically, this is set to pebble.DebugCheckLevels in tests
503 : // or tools only, to check invariants over all the data in the database.
504 : DebugCheck func(*DB) error
505 :
506 : // Disable the write-ahead log (WAL). Disabling the write-ahead log prohibits
507 : // crash recovery, but can improve performance if crash recovery is not
508 : // needed (e.g. when only temporary state is being stored in the database).
509 : //
510 : // TODO(peter): untested
511 : DisableWAL bool
512 :
513 : // ErrorIfExists causes an error on Open if the database already exists.
514 : // The error can be checked with errors.Is(err, ErrDBAlreadyExists).
515 : //
516 : // The default value is false.
517 : ErrorIfExists bool
518 :
519 : // ErrorIfNotExists causes an error on Open if the database does not already
520 : // exist. The error can be checked with errors.Is(err, ErrDBDoesNotExist).
521 : //
522 : // The default value is false which will cause a database to be created if it
523 : // does not already exist.
524 : ErrorIfNotExists bool
525 :
526 : // ErrorIfNotPristine causes an error on Open if the database already exists
527 : // and any operations have been performed on the database. The error can be
528 : // checked with errors.Is(err, ErrDBNotPristine).
529 : //
530 : // Note that a database that contained keys that were all subsequently deleted
531 : // may or may not trigger the error. Currently, we check if there are any live
532 : // SSTs or log records to replay.
533 : ErrorIfNotPristine bool
534 :
535 : // EventListener provides hooks to listening to significant DB events such as
536 : // flushes, compactions, and table deletion.
537 : EventListener *EventListener
538 :
539 : // Experimental contains experimental options which are off by default.
540 : // These options are temporary and will eventually either be deleted, moved
541 : // out of the experimental group, or made the non-adjustable default. These
542 : // options may change at any time, so do not rely on them.
543 : Experimental struct {
544 : // The threshold of L0 read-amplification at which compaction concurrency
545 : // is enabled (if CompactionDebtConcurrency was not already exceeded).
546 : // Every multiple of this value enables another concurrent
547 : // compaction up to MaxConcurrentCompactions.
548 : L0CompactionConcurrency int
549 :
550 : // CompactionDebtConcurrency controls the threshold of compaction debt
551 : // at which additional compaction concurrency slots are added. For every
552 : // multiple of this value in compaction debt bytes, an additional
553 : // concurrent compaction is added. This works "on top" of
554 : // L0CompactionConcurrency, so the higher of the count of compaction
555 : // concurrency slots as determined by the two options is chosen.
556 : CompactionDebtConcurrency uint64
557 :
558 : // IngestSplit, if it returns true, allows for ingest-time splitting of
559 : // existing sstables into two virtual sstables to allow ingestion sstables to
560 : // slot into a lower level than they otherwise would have.
561 : IngestSplit func() bool
562 :
563 : // ReadCompactionRate controls the frequency of read triggered
564 : // compactions by adjusting `AllowedSeeks` in manifest.FileMetadata:
565 : //
566 : // AllowedSeeks = FileSize / ReadCompactionRate
567 : //
568 : // From LevelDB:
569 : // ```
570 : // We arrange to automatically compact this file after
571 : // a certain number of seeks. Let's assume:
572 : // (1) One seek costs 10ms
573 : // (2) Writing or reading 1MB costs 10ms (100MB/s)
574 : // (3) A compaction of 1MB does 25MB of IO:
575 : // 1MB read from this level
576 : // 10-12MB read from next level (boundaries may be misaligned)
577 : // 10-12MB written to next level
578 : // This implies that 25 seeks cost the same as the compaction
579 : // of 1MB of data. I.e., one seek costs approximately the
580 : // same as the compaction of 40KB of data. We are a little
581 : // conservative and allow approximately one seek for every 16KB
582 : // of data before triggering a compaction.
583 : // ```
584 : ReadCompactionRate int64
585 :
586 : // ReadSamplingMultiplier is a multiplier for the readSamplingPeriod in
587 : // iterator.maybeSampleRead() to control the frequency of read sampling
588 : // to trigger a read triggered compaction. A value of -1 prevents sampling
589 : // and disables read triggered compactions. The default is 1 << 4. which
590 : // gets multiplied with a constant of 1 << 16 to yield 1 << 20 (1MB).
591 : ReadSamplingMultiplier int64
592 :
593 : // TableCacheShards is the number of shards per table cache.
594 : // Reducing the value can reduce the number of idle goroutines per DB
595 : // instance which can be useful in scenarios with a lot of DB instances
596 : // and a large number of CPUs, but doing so can lead to higher contention
597 : // in the table cache and reduced performance.
598 : //
599 : // The default value is the number of logical CPUs, which can be
600 : // limited by runtime.GOMAXPROCS.
601 : TableCacheShards int
602 :
603 : // KeyValidationFunc is a function to validate a user key in an SSTable.
604 : //
605 : // Currently, this function is used to validate the smallest and largest
606 : // keys in an SSTable undergoing compaction. In this case, returning an
607 : // error from the validation function will result in a panic at runtime,
608 : // given that there is rarely any way of recovering from malformed keys
609 : // present in compacted files. By default, validation is not performed.
610 : //
611 : // Additional use-cases may be added in the future.
612 : //
613 : // NOTE: callers should take care to not mutate the key being validated.
614 : KeyValidationFunc func(userKey []byte) error
615 :
616 : // ValidateOnIngest schedules validation of sstables after they have
617 : // been ingested.
618 : //
619 : // By default, this value is false.
620 : ValidateOnIngest bool
621 :
622 : // LevelMultiplier configures the size multiplier used to determine the
623 : // desired size of each level of the LSM. Defaults to 10.
624 : LevelMultiplier int
625 :
626 : // MultiLevelCompactionHeuristic determines whether to add an additional
627 : // level to a conventional two level compaction. If nil, a multilevel
628 : // compaction will never get triggered.
629 : MultiLevelCompactionHeuristic MultiLevelHeuristic
630 :
631 : // MaxWriterConcurrency is used to indicate the maximum number of
632 : // compression workers the compression queue is allowed to use. If
633 : // MaxWriterConcurrency > 0, then the Writer will use parallelism, to
634 : // compress and write blocks to disk. Otherwise, the writer will
635 : // compress and write blocks to disk synchronously.
636 : MaxWriterConcurrency int
637 :
638 : // ForceWriterParallelism is used to force parallelism in the sstable
639 : // Writer for the metamorphic tests. Even with the MaxWriterConcurrency
640 : // option set, we only enable parallelism in the sstable Writer if there
641 : // is enough CPU available, and this option bypasses that.
642 : ForceWriterParallelism bool
643 :
644 : // CPUWorkPermissionGranter should be set if Pebble should be given the
645 : // ability to optionally schedule additional CPU. See the documentation
646 : // for CPUWorkPermissionGranter for more details.
647 : CPUWorkPermissionGranter CPUWorkPermissionGranter
648 :
649 : // EnableValueBlocks is used to decide whether to enable writing
650 : // TableFormatPebblev3 sstables. This setting is only respected by a
651 : // specific subset of format major versions: FormatSSTableValueBlocks,
652 : // FormatFlushableIngest and FormatPrePebblev1MarkedCompacted. In lower
653 : // format major versions, value blocks are never enabled. In higher
654 : // format major versions, value blocks are always enabled.
655 : EnableValueBlocks func() bool
656 :
657 : // ShortAttributeExtractor is used iff EnableValueBlocks() returns true
658 : // (else ignored). If non-nil, a ShortAttribute can be extracted from the
659 : // value and stored with the key, when the value is stored elsewhere.
660 : ShortAttributeExtractor ShortAttributeExtractor
661 :
662 : // RequiredInPlaceValueBound specifies an optional span of user key
663 : // prefixes that are not-MVCC, but have a suffix. For these the values
664 : // must be stored with the key, since the concept of "older versions" is
665 : // not defined. It is also useful for statically known exclusions to value
666 : // separation. In CockroachDB, this will be used for the lock table key
667 : // space that has non-empty suffixes, but those locks don't represent
668 : // actual MVCC versions (the suffix ordering is arbitrary). We will also
669 : // need to add support for dynamically configured exclusions (we want the
670 : // default to be to allow Pebble to decide whether to separate the value
671 : // or not, hence this is structured as exclusions), for example, for users
672 : // of CockroachDB to dynamically exclude certain tables.
673 : //
674 : // Any change in exclusion behavior takes effect only on future written
675 : // sstables, and does not start rewriting existing sstables.
676 : //
677 : // Even ignoring changes in this setting, exclusions are interpreted as a
678 : // guidance by Pebble, and not necessarily honored. Specifically, user
679 : // keys with multiple Pebble-versions *may* have the older versions stored
680 : // in value blocks.
681 : RequiredInPlaceValueBound UserKeyPrefixBound
682 :
683 : // DisableIngestAsFlushable disables lazy ingestion of sstables through
684 : // a WAL write and memtable rotation. Only effectual if the the format
685 : // major version is at least `FormatFlushableIngest`.
686 : DisableIngestAsFlushable func() bool
687 :
688 : // RemoteStorage enables use of remote storage (e.g. S3) for storing
689 : // sstables. Setting this option enables use of CreateOnShared option and
690 : // allows ingestion of external files.
691 : RemoteStorage remote.StorageFactory
692 :
693 : // If CreateOnShared is non-zero, new sstables are created on remote storage
694 : // (using CreateOnSharedLocator and with the appropriate
695 : // CreateOnSharedStrategy). These sstables can be shared between different
696 : // Pebble instances; the lifecycle of such objects is managed by the
697 : // remote.Storage constructed by options.RemoteStorage.
698 : //
699 : // Can only be used when RemoteStorage is set (and recognizes
700 : // CreateOnSharedLocator).
701 : CreateOnShared remote.CreateOnSharedStrategy
702 : CreateOnSharedLocator remote.Locator
703 :
704 : // CacheSizeBytesBytes is the size of the on-disk block cache for objects
705 : // on shared storage in bytes. If it is 0, no cache is used.
706 : SecondaryCacheSizeBytes int64
707 :
708 : // IneffectualPointDeleteCallback is called in compactions/flushes if any
709 : // single delete is being elided without deleting a point set/merge.
710 : IneffectualSingleDeleteCallback func(userKey []byte)
711 :
712 : // SingleDeleteInvariantViolationCallback is called in compactions/flushes if any
713 : // single delete has consumed a Set/Merge, and there is another immediately older
714 : // Set/SetWithDelete/Merge. The user of Pebble has violated the invariant under
715 : // which SingleDelete can be used correctly.
716 : //
717 : // Consider the sequence SingleDelete#3, Set#2, Set#1. There are three
718 : // ways some of these keys can first meet in a compaction.
719 : //
720 : // - All 3 keys in the same compaction: this callback will detect the
721 : // violation.
722 : //
723 : // - SingleDelete#3, Set#2 meet in a compaction first: Both keys will
724 : // disappear. The violation will not be detected, and the DB will have
725 : // Set#1 which is likely incorrect (from the user's perspective).
726 : //
727 : // - Set#2, Set#1 meet in a compaction first: The output will be Set#2,
728 : // which will later be consumed by SingleDelete#3. The violation will
729 : // not be detected and the DB will be correct.
730 : SingleDeleteInvariantViolationCallback func(userKey []byte)
731 : }
732 :
733 : // Filters is a map from filter policy name to filter policy. It is used for
734 : // debugging tools which may be used on multiple databases configured with
735 : // different filter policies. It is not necessary to populate this filters
736 : // map during normal usage of a DB.
737 : Filters map[string]FilterPolicy
738 :
739 : // FlushDelayDeleteRange configures how long the database should wait before
740 : // forcing a flush of a memtable that contains a range deletion. Disk space
741 : // cannot be reclaimed until the range deletion is flushed. No automatic
742 : // flush occurs if zero.
743 : FlushDelayDeleteRange time.Duration
744 :
745 : // FlushDelayRangeKey configures how long the database should wait before
746 : // forcing a flush of a memtable that contains a range key. Range keys in
747 : // the memtable prevent lazy combined iteration, so it's desirable to flush
748 : // range keys promptly. No automatic flush occurs if zero.
749 : FlushDelayRangeKey time.Duration
750 :
751 : // FlushSplitBytes denotes the target number of bytes per sublevel in
752 : // each flush split interval (i.e. range between two flush split keys)
753 : // in L0 sstables. When set to zero, only a single sstable is generated
754 : // by each flush. When set to a non-zero value, flushes are split at
755 : // points to meet L0's TargetFileSize, any grandparent-related overlap
756 : // options, and at boundary keys of L0 flush split intervals (which are
757 : // targeted to contain around FlushSplitBytes bytes in each sublevel
758 : // between pairs of boundary keys). Splitting sstables during flush
759 : // allows increased compaction flexibility and concurrency when those
760 : // tables are compacted to lower levels.
761 : FlushSplitBytes int64
762 :
763 : // FormatMajorVersion sets the format of on-disk files. It is
764 : // recommended to set the format major version to an explicit
765 : // version, as the default may change over time.
766 : //
767 : // At Open if the existing database is formatted using a later
768 : // format major version that is known to this version of Pebble,
769 : // Pebble will continue to use the later format major version. If
770 : // the existing database's version is unknown, the caller may use
771 : // FormatMostCompatible and will be able to open the database
772 : // regardless of its actual version.
773 : //
774 : // If the existing database is formatted using a format major
775 : // version earlier than the one specified, Open will automatically
776 : // ratchet the database to the specified format major version.
777 : FormatMajorVersion FormatMajorVersion
778 :
779 : // FS provides the interface for persistent file storage.
780 : //
781 : // The default value uses the underlying operating system's file system.
782 : FS vfs.FS
783 :
784 : // Lock, if set, must be a database lock acquired through LockDirectory for
785 : // the same directory passed to Open. If provided, Open will skip locking
786 : // the directory. Closing the database will not release the lock, and it's
787 : // the responsibility of the caller to release the lock after closing the
788 : // database.
789 : //
790 : // Open will enforce that the Lock passed locks the same directory passed to
791 : // Open. Concurrent calls to Open using the same Lock are detected and
792 : // prohibited.
793 : Lock *Lock
794 :
795 : // The count of L0 files necessary to trigger an L0 compaction.
796 : L0CompactionFileThreshold int
797 :
798 : // The amount of L0 read-amplification necessary to trigger an L0 compaction.
799 : L0CompactionThreshold int
800 :
801 : // Hard limit on L0 read-amplification, computed as the number of L0
802 : // sublevels. Writes are stopped when this threshold is reached.
803 : L0StopWritesThreshold int
804 :
805 : // The maximum number of bytes for LBase. The base level is the level which
806 : // L0 is compacted into. The base level is determined dynamically based on
807 : // the existing data in the LSM. The maximum number of bytes for other levels
808 : // is computed dynamically based on the base level's maximum size. When the
809 : // maximum number of bytes for a level is exceeded, compaction is requested.
810 : LBaseMaxBytes int64
811 :
812 : // Per-level options. Options for at least one level must be specified. The
813 : // options for the last level are used for all subsequent levels.
814 : Levels []LevelOptions
815 :
816 : // LoggerAndTracer will be used, if non-nil, else Logger will be used and
817 : // tracing will be a noop.
818 :
819 : // Logger used to write log messages.
820 : //
821 : // The default logger uses the Go standard library log package.
822 : Logger Logger
823 : // LoggerAndTracer is used for writing log messages and traces.
824 : LoggerAndTracer LoggerAndTracer
825 :
826 : // MaxManifestFileSize is the maximum size the MANIFEST file is allowed to
827 : // become. When the MANIFEST exceeds this size it is rolled over and a new
828 : // MANIFEST is created.
829 : MaxManifestFileSize int64
830 :
831 : // MaxOpenFiles is a soft limit on the number of open files that can be
832 : // used by the DB.
833 : //
834 : // The default value is 1000.
835 : MaxOpenFiles int
836 :
837 : // The size of a MemTable in steady state. The actual MemTable size starts at
838 : // min(256KB, MemTableSize) and doubles for each subsequent MemTable up to
839 : // MemTableSize. This reduces the memory pressure caused by MemTables for
840 : // short lived (test) DB instances. Note that more than one MemTable can be
841 : // in existence since flushing a MemTable involves creating a new one and
842 : // writing the contents of the old one in the
843 : // background. MemTableStopWritesThreshold places a hard limit on the size of
844 : // the queued MemTables.
845 : //
846 : // The default value is 4MB.
847 : MemTableSize uint64
848 :
849 : // Hard limit on the number of queued of MemTables. Writes are stopped when
850 : // the sum of the queued memtable sizes exceeds:
851 : // MemTableStopWritesThreshold * MemTableSize.
852 : //
853 : // This value should be at least 2 or writes will stop whenever a MemTable is
854 : // being flushed.
855 : //
856 : // The default value is 2.
857 : MemTableStopWritesThreshold int
858 :
859 : // Merger defines the associative merge operation to use for merging values
860 : // written with {Batch,DB}.Merge.
861 : //
862 : // The default merger concatenates values.
863 : Merger *Merger
864 :
865 : // MaxConcurrentCompactions specifies the maximum number of concurrent
866 : // compactions. The default is 1. Concurrent compactions are performed
867 : // - when L0 read-amplification passes the L0CompactionConcurrency threshold
868 : // - for automatic background compactions
869 : // - when a manual compaction for a level is split and parallelized
870 : // MaxConcurrentCompactions must be greater than 0.
871 : MaxConcurrentCompactions func() int
872 :
873 : // DisableAutomaticCompactions dictates whether automatic compactions are
874 : // scheduled or not. The default is false (enabled). This option is only used
875 : // externally when running a manual compaction, and internally for tests.
876 : DisableAutomaticCompactions bool
877 :
878 : // NoSyncOnClose decides whether the Pebble instance will enforce a
879 : // close-time synchronization (e.g., fdatasync() or sync_file_range())
880 : // on files it writes to. Setting this to true removes the guarantee for a
881 : // sync on close. Some implementations can still issue a non-blocking sync.
882 : NoSyncOnClose bool
883 :
884 : // NumPrevManifest is the number of non-current or older manifests which
885 : // we want to keep around for debugging purposes. By default, we're going
886 : // to keep one older manifest.
887 : NumPrevManifest int
888 :
889 : // ReadOnly indicates that the DB should be opened in read-only mode. Writes
890 : // to the DB will return an error, background compactions are disabled, and
891 : // the flush that normally occurs after replaying the WAL at startup is
892 : // disabled.
893 : ReadOnly bool
894 :
895 : // TableCache is an initialized TableCache which should be set as an
896 : // option if the DB needs to be initialized with a pre-existing table cache.
897 : // If TableCache is nil, then a table cache which is unique to the DB instance
898 : // is created. TableCache can be shared between db instances by setting it here.
899 : // The TableCache set here must use the same underlying cache as Options.Cache
900 : // and pebble will panic otherwise.
901 : TableCache *TableCache
902 :
903 : // TablePropertyCollectors is a list of TablePropertyCollector creation
904 : // functions. A new TablePropertyCollector is created for each sstable built
905 : // and lives for the lifetime of the table.
906 : TablePropertyCollectors []func() TablePropertyCollector
907 :
908 : // BlockPropertyCollectors is a list of BlockPropertyCollector creation
909 : // functions. A new BlockPropertyCollector is created for each sstable
910 : // built and lives for the lifetime of writing that table.
911 : BlockPropertyCollectors []func() BlockPropertyCollector
912 :
913 : // WALBytesPerSync sets the number of bytes to write to a WAL before calling
914 : // Sync on it in the background. Just like with BytesPerSync above, this
915 : // helps smooth out disk write latencies, and avoids cases where the OS
916 : // writes a lot of buffered data to disk at once. However, this is less
917 : // necessary with WALs, as many write operations already pass in
918 : // Sync = true.
919 : //
920 : // The default value is 0, i.e. no background syncing. This matches the
921 : // default behaviour in RocksDB.
922 : WALBytesPerSync int
923 :
924 : // WALDir specifies the directory to store write-ahead logs (WALs) in. If
925 : // empty (the default), WALs will be stored in the same directory as sstables
926 : // (i.e. the directory passed to pebble.Open).
927 : WALDir string
928 :
929 : // WALMinSyncInterval is the minimum duration between syncs of the WAL. If
930 : // WAL syncs are requested faster than this interval, they will be
931 : // artificially delayed. Introducing a small artificial delay (500us) between
932 : // WAL syncs can allow more operations to arrive and reduce IO operations
933 : // while having a minimal impact on throughput. This option is supplied as a
934 : // closure in order to allow the value to be changed dynamically. The default
935 : // value is 0.
936 : //
937 : // TODO(peter): rather than a closure, should there be another mechanism for
938 : // changing options dynamically?
939 : WALMinSyncInterval func() time.Duration
940 :
941 : // TargetByteDeletionRate is the rate (in bytes per second) at which sstable file
942 : // deletions are limited to (under normal circumstances).
943 : //
944 : // Deletion pacing is used to slow down deletions when compactions finish up
945 : // or readers close and newly-obsolete files need cleaning up. Deleting lots
946 : // of files at once can cause disk latency to go up on some SSDs, which this
947 : // functionality guards against.
948 : //
949 : // This value is only a best-effort target; the effective rate can be
950 : // higher if deletions are falling behind or disk space is running low.
951 : //
952 : // Setting this to 0 disables deletion pacing, which is also the default.
953 : TargetByteDeletionRate int
954 :
955 : // private options are only used by internal tests or are used internally
956 : // for facilitating upgrade paths of unconfigurable functionality.
957 : private struct {
958 : // strictWALTail configures whether or not a database's WALs created
959 : // prior to the most recent one should be interpreted strictly,
960 : // requiring a clean EOF. RocksDB 6.2.1 and the version of Pebble
961 : // included in CockroachDB 20.1 do not guarantee that closed WALs end
962 : // cleanly. If this option is set within an OPTIONS file, Pebble
963 : // interprets previous WALs strictly, requiring a clean EOF.
964 : // Otherwise, it interprets them permissively in the same manner as
965 : // RocksDB 6.2.1.
966 : strictWALTail bool
967 :
968 : // disableDeleteOnlyCompactions prevents the scheduling of delete-only
969 : // compactions that drop sstables wholy covered by range tombstones or
970 : // range key tombstones.
971 : disableDeleteOnlyCompactions bool
972 :
973 : // disableElisionOnlyCompactions prevents the scheduling of elision-only
974 : // compactions that rewrite sstables in place in order to elide obsolete
975 : // keys.
976 : disableElisionOnlyCompactions bool
977 :
978 : // disableLazyCombinedIteration is a private option used by the
979 : // metamorphic tests to test equivalence between lazy-combined iteration
980 : // and constructing the range-key iterator upfront. It's a private
981 : // option to avoid littering the public interface with options that we
982 : // do not want to allow users to actually configure.
983 : disableLazyCombinedIteration bool
984 :
985 : // A private option to disable stats collection.
986 : disableTableStats bool
987 :
988 : // testingAlwaysWaitForCleanup is set by some tests to force waiting for
989 : // obsolete file deletion (to make events deterministic).
990 : testingAlwaysWaitForCleanup bool
991 :
992 : // fsCloser holds a closer that should be invoked after a DB using these
993 : // Options is closed. This is used to automatically stop the
994 : // long-running goroutine associated with the disk-health-checking FS.
995 : // See the initialization of FS in EnsureDefaults. Note that care has
996 : // been taken to ensure that it is still safe to continue using the FS
997 : // after this closer has been invoked. However, if write operations
998 : // against the FS are made after the DB is closed, the FS may leak a
999 : // goroutine indefinitely.
1000 : fsCloser io.Closer
1001 :
1002 : // efosAlwaysCreatesIterators is set by some tests to force
1003 : // EventuallyFileOnlySnapshots to always create iterators, even after a
1004 : // conflicting excise.
1005 : efosAlwaysCreatesIterators bool
1006 : }
1007 : }
1008 :
1009 : // DebugCheckLevels calls CheckLevels on the provided database.
1010 : // It may be set in the DebugCheck field of Options to check
1011 : // level invariants whenever a new version is installed.
1012 1 : func DebugCheckLevels(db *DB) error {
1013 1 : return db.CheckLevels(nil)
1014 1 : }
1015 :
1016 : // EnsureDefaults ensures that the default values for all options are set if a
1017 : // valid value was not already specified. Returns the new options.
1018 1 : func (o *Options) EnsureDefaults() *Options {
1019 1 : if o == nil {
1020 1 : o = &Options{}
1021 1 : }
1022 1 : if o.BytesPerSync <= 0 {
1023 1 : o.BytesPerSync = 512 << 10 // 512 KB
1024 1 : }
1025 1 : if o.Cleaner == nil {
1026 1 : o.Cleaner = DeleteCleaner{}
1027 1 : }
1028 1 : if o.Comparer == nil {
1029 1 : o.Comparer = DefaultComparer
1030 1 : }
1031 1 : if o.Experimental.DisableIngestAsFlushable == nil {
1032 1 : o.Experimental.DisableIngestAsFlushable = func() bool { return false }
1033 : }
1034 1 : if o.Experimental.L0CompactionConcurrency <= 0 {
1035 1 : o.Experimental.L0CompactionConcurrency = 10
1036 1 : }
1037 1 : if o.Experimental.CompactionDebtConcurrency <= 0 {
1038 1 : o.Experimental.CompactionDebtConcurrency = 1 << 30 // 1 GB
1039 1 : }
1040 1 : if o.Experimental.KeyValidationFunc == nil {
1041 1 : o.Experimental.KeyValidationFunc = func([]byte) error { return nil }
1042 : }
1043 1 : if o.L0CompactionThreshold <= 0 {
1044 1 : o.L0CompactionThreshold = 4
1045 1 : }
1046 1 : if o.L0CompactionFileThreshold <= 0 {
1047 1 : // Some justification for the default of 500:
1048 1 : // Why not smaller?:
1049 1 : // - The default target file size for L0 is 2MB, so 500 files is <= 1GB
1050 1 : // of data. At observed compaction speeds of > 20MB/s, L0 can be
1051 1 : // cleared of all files in < 1min, so this backlog is not huge.
1052 1 : // - 500 files is low overhead for instantiating L0 sublevels from
1053 1 : // scratch.
1054 1 : // - Lower values were observed to cause excessive and inefficient
1055 1 : // compactions out of L0 in a TPCC import benchmark.
1056 1 : // Why not larger?:
1057 1 : // - More than 1min to compact everything out of L0.
1058 1 : // - CockroachDB's admission control system uses a threshold of 1000
1059 1 : // files to start throttling writes to Pebble. Using 500 here gives
1060 1 : // us headroom between when Pebble should start compacting L0 and
1061 1 : // when the admission control threshold is reached.
1062 1 : //
1063 1 : // We can revisit this default in the future based on better
1064 1 : // experimental understanding.
1065 1 : //
1066 1 : // TODO(jackson): Experiment with slightly lower thresholds [or higher
1067 1 : // admission control thresholds] to see whether a higher L0 score at the
1068 1 : // threshold (currently 2.0) is necessary for some workloads to avoid
1069 1 : // starving L0 in favor of lower-level compactions.
1070 1 : o.L0CompactionFileThreshold = 500
1071 1 : }
1072 1 : if o.L0StopWritesThreshold <= 0 {
1073 1 : o.L0StopWritesThreshold = 12
1074 1 : }
1075 1 : if o.LBaseMaxBytes <= 0 {
1076 1 : o.LBaseMaxBytes = 64 << 20 // 64 MB
1077 1 : }
1078 1 : if o.Levels == nil {
1079 1 : o.Levels = make([]LevelOptions, 1)
1080 1 : for i := range o.Levels {
1081 1 : if i > 0 {
1082 0 : l := &o.Levels[i]
1083 0 : if l.TargetFileSize <= 0 {
1084 0 : l.TargetFileSize = o.Levels[i-1].TargetFileSize * 2
1085 0 : }
1086 : }
1087 1 : o.Levels[i].EnsureDefaults()
1088 : }
1089 1 : } else {
1090 1 : for i := range o.Levels {
1091 1 : o.Levels[i].EnsureDefaults()
1092 1 : }
1093 : }
1094 1 : if o.Logger == nil {
1095 1 : o.Logger = DefaultLogger
1096 1 : }
1097 1 : if o.EventListener == nil {
1098 1 : o.EventListener = &EventListener{}
1099 1 : }
1100 1 : o.EventListener.EnsureDefaults(o.Logger)
1101 1 : if o.MaxManifestFileSize == 0 {
1102 1 : o.MaxManifestFileSize = 128 << 20 // 128 MB
1103 1 : }
1104 1 : if o.MaxOpenFiles == 0 {
1105 1 : o.MaxOpenFiles = 1000
1106 1 : }
1107 1 : if o.MemTableSize <= 0 {
1108 1 : o.MemTableSize = 4 << 20 // 4 MB
1109 1 : }
1110 1 : if o.MemTableStopWritesThreshold <= 0 {
1111 1 : o.MemTableStopWritesThreshold = 2
1112 1 : }
1113 1 : if o.Merger == nil {
1114 1 : o.Merger = DefaultMerger
1115 1 : }
1116 1 : o.private.strictWALTail = true
1117 1 : if o.MaxConcurrentCompactions == nil {
1118 1 : o.MaxConcurrentCompactions = func() int { return 1 }
1119 : }
1120 1 : if o.NumPrevManifest <= 0 {
1121 1 : o.NumPrevManifest = 1
1122 1 : }
1123 :
1124 1 : if o.FormatMajorVersion == FormatDefault {
1125 1 : o.FormatMajorVersion = FormatMinSupported
1126 1 : }
1127 :
1128 1 : if o.FS == nil {
1129 1 : o.WithFSDefaults()
1130 1 : }
1131 1 : if o.FlushSplitBytes <= 0 {
1132 1 : o.FlushSplitBytes = 2 * o.Levels[0].TargetFileSize
1133 1 : }
1134 1 : if o.Experimental.LevelMultiplier <= 0 {
1135 1 : o.Experimental.LevelMultiplier = defaultLevelMultiplier
1136 1 : }
1137 1 : if o.Experimental.ReadCompactionRate == 0 {
1138 1 : o.Experimental.ReadCompactionRate = 16000
1139 1 : }
1140 1 : if o.Experimental.ReadSamplingMultiplier == 0 {
1141 1 : o.Experimental.ReadSamplingMultiplier = 1 << 4
1142 1 : }
1143 1 : if o.Experimental.TableCacheShards <= 0 {
1144 1 : o.Experimental.TableCacheShards = runtime.GOMAXPROCS(0)
1145 1 : }
1146 1 : if o.Experimental.CPUWorkPermissionGranter == nil {
1147 1 : o.Experimental.CPUWorkPermissionGranter = defaultCPUWorkGranter{}
1148 1 : }
1149 1 : if o.Experimental.MultiLevelCompactionHeuristic == nil {
1150 1 : o.Experimental.MultiLevelCompactionHeuristic = WriteAmpHeuristic{}
1151 1 : }
1152 :
1153 1 : o.initMaps()
1154 1 : return o
1155 : }
1156 :
1157 : // WithFSDefaults configures the Options to wrap the configured filesystem with
1158 : // the default virtual file system middleware, like disk-health checking.
1159 1 : func (o *Options) WithFSDefaults() *Options {
1160 1 : if o.FS == nil {
1161 1 : o.FS = vfs.Default
1162 1 : }
1163 1 : o.FS, o.private.fsCloser = vfs.WithDiskHealthChecks(o.FS, 5*time.Second,
1164 1 : func(info vfs.DiskSlowInfo) {
1165 0 : o.EventListener.DiskSlow(info)
1166 0 : })
1167 1 : return o
1168 : }
1169 :
1170 : // AddEventListener adds the provided event listener to the Options, in addition
1171 : // to any existing event listener.
1172 1 : func (o *Options) AddEventListener(l EventListener) {
1173 1 : if o.EventListener != nil {
1174 1 : l = TeeEventListener(l, *o.EventListener)
1175 1 : }
1176 1 : o.EventListener = &l
1177 : }
1178 :
1179 : // TestingAlwaysCreateEFOSIterators is used to toggle a private option for
1180 : // having EventuallyFileOnlySnapshots always create iterators. Meant to only
1181 : // be used in tests.
1182 1 : func (o *Options) TestingAlwaysCreateEFOSIterators(value bool) {
1183 1 : o.private.efosAlwaysCreatesIterators = value
1184 1 : }
1185 :
1186 1 : func (o *Options) equal() Equal {
1187 1 : if o.Comparer.Equal == nil {
1188 1 : return bytes.Equal
1189 1 : }
1190 1 : return o.Comparer.Equal
1191 : }
1192 :
1193 : // initMaps initializes the Comparers, Filters, and Mergers maps.
1194 1 : func (o *Options) initMaps() {
1195 1 : for i := range o.Levels {
1196 1 : l := &o.Levels[i]
1197 1 : if l.FilterPolicy != nil {
1198 1 : if o.Filters == nil {
1199 1 : o.Filters = make(map[string]FilterPolicy)
1200 1 : }
1201 1 : name := l.FilterPolicy.Name()
1202 1 : if _, ok := o.Filters[name]; !ok {
1203 1 : o.Filters[name] = l.FilterPolicy
1204 1 : }
1205 : }
1206 : }
1207 : }
1208 :
1209 : // Level returns the LevelOptions for the specified level.
1210 1 : func (o *Options) Level(level int) LevelOptions {
1211 1 : if level < len(o.Levels) {
1212 1 : return o.Levels[level]
1213 1 : }
1214 1 : n := len(o.Levels) - 1
1215 1 : l := o.Levels[n]
1216 1 : for i := n; i < level; i++ {
1217 1 : l.TargetFileSize *= 2
1218 1 : }
1219 1 : return l
1220 : }
1221 :
1222 : // Clone creates a shallow-copy of the supplied options.
1223 1 : func (o *Options) Clone() *Options {
1224 1 : n := &Options{}
1225 1 : if o != nil {
1226 1 : *n = *o
1227 1 : }
1228 1 : return n
1229 : }
1230 :
1231 1 : func filterPolicyName(p FilterPolicy) string {
1232 1 : if p == nil {
1233 1 : return "none"
1234 1 : }
1235 1 : return p.Name()
1236 : }
1237 :
1238 1 : func (o *Options) String() string {
1239 1 : var buf bytes.Buffer
1240 1 :
1241 1 : cacheSize := int64(cacheDefaultSize)
1242 1 : if o.Cache != nil {
1243 1 : cacheSize = o.Cache.MaxSize()
1244 1 : }
1245 :
1246 1 : fmt.Fprintf(&buf, "[Version]\n")
1247 1 : fmt.Fprintf(&buf, " pebble_version=0.1\n")
1248 1 : fmt.Fprintf(&buf, "\n")
1249 1 : fmt.Fprintf(&buf, "[Options]\n")
1250 1 : fmt.Fprintf(&buf, " bytes_per_sync=%d\n", o.BytesPerSync)
1251 1 : fmt.Fprintf(&buf, " cache_size=%d\n", cacheSize)
1252 1 : fmt.Fprintf(&buf, " cleaner=%s\n", o.Cleaner)
1253 1 : fmt.Fprintf(&buf, " compaction_debt_concurrency=%d\n", o.Experimental.CompactionDebtConcurrency)
1254 1 : fmt.Fprintf(&buf, " comparer=%s\n", o.Comparer.Name)
1255 1 : fmt.Fprintf(&buf, " disable_wal=%t\n", o.DisableWAL)
1256 1 : if o.Experimental.DisableIngestAsFlushable != nil && o.Experimental.DisableIngestAsFlushable() {
1257 1 : fmt.Fprintf(&buf, " disable_ingest_as_flushable=%t\n", true)
1258 1 : }
1259 1 : fmt.Fprintf(&buf, " flush_delay_delete_range=%s\n", o.FlushDelayDeleteRange)
1260 1 : fmt.Fprintf(&buf, " flush_delay_range_key=%s\n", o.FlushDelayRangeKey)
1261 1 : fmt.Fprintf(&buf, " flush_split_bytes=%d\n", o.FlushSplitBytes)
1262 1 : fmt.Fprintf(&buf, " format_major_version=%d\n", o.FormatMajorVersion)
1263 1 : fmt.Fprintf(&buf, " l0_compaction_concurrency=%d\n", o.Experimental.L0CompactionConcurrency)
1264 1 : fmt.Fprintf(&buf, " l0_compaction_file_threshold=%d\n", o.L0CompactionFileThreshold)
1265 1 : fmt.Fprintf(&buf, " l0_compaction_threshold=%d\n", o.L0CompactionThreshold)
1266 1 : fmt.Fprintf(&buf, " l0_stop_writes_threshold=%d\n", o.L0StopWritesThreshold)
1267 1 : fmt.Fprintf(&buf, " lbase_max_bytes=%d\n", o.LBaseMaxBytes)
1268 1 : if o.Experimental.LevelMultiplier != defaultLevelMultiplier {
1269 1 : fmt.Fprintf(&buf, " level_multiplier=%d\n", o.Experimental.LevelMultiplier)
1270 1 : }
1271 1 : fmt.Fprintf(&buf, " max_concurrent_compactions=%d\n", o.MaxConcurrentCompactions())
1272 1 : fmt.Fprintf(&buf, " max_manifest_file_size=%d\n", o.MaxManifestFileSize)
1273 1 : fmt.Fprintf(&buf, " max_open_files=%d\n", o.MaxOpenFiles)
1274 1 : fmt.Fprintf(&buf, " mem_table_size=%d\n", o.MemTableSize)
1275 1 : fmt.Fprintf(&buf, " mem_table_stop_writes_threshold=%d\n", o.MemTableStopWritesThreshold)
1276 1 : fmt.Fprintf(&buf, " min_deletion_rate=%d\n", o.TargetByteDeletionRate)
1277 1 : fmt.Fprintf(&buf, " merger=%s\n", o.Merger.Name)
1278 1 : if o.Experimental.MultiLevelCompactionHeuristic != nil {
1279 1 : fmt.Fprintf(&buf, " multilevel_compaction_heuristic=%s\n", o.Experimental.MultiLevelCompactionHeuristic.String())
1280 1 : }
1281 1 : fmt.Fprintf(&buf, " read_compaction_rate=%d\n", o.Experimental.ReadCompactionRate)
1282 1 : fmt.Fprintf(&buf, " read_sampling_multiplier=%d\n", o.Experimental.ReadSamplingMultiplier)
1283 1 : fmt.Fprintf(&buf, " strict_wal_tail=%t\n", o.private.strictWALTail)
1284 1 : fmt.Fprintf(&buf, " table_cache_shards=%d\n", o.Experimental.TableCacheShards)
1285 1 : fmt.Fprintf(&buf, " table_property_collectors=[")
1286 1 : for i := range o.TablePropertyCollectors {
1287 1 : if i > 0 {
1288 0 : fmt.Fprintf(&buf, ",")
1289 0 : }
1290 : // NB: This creates a new TablePropertyCollector, but Options.String() is
1291 : // called rarely so the overhead of doing so is not consequential.
1292 1 : fmt.Fprintf(&buf, "%s", o.TablePropertyCollectors[i]().Name())
1293 : }
1294 1 : fmt.Fprintf(&buf, "]\n")
1295 1 : fmt.Fprintf(&buf, " validate_on_ingest=%t\n", o.Experimental.ValidateOnIngest)
1296 1 : fmt.Fprintf(&buf, " wal_dir=%s\n", o.WALDir)
1297 1 : fmt.Fprintf(&buf, " wal_bytes_per_sync=%d\n", o.WALBytesPerSync)
1298 1 : fmt.Fprintf(&buf, " max_writer_concurrency=%d\n", o.Experimental.MaxWriterConcurrency)
1299 1 : fmt.Fprintf(&buf, " force_writer_parallelism=%t\n", o.Experimental.ForceWriterParallelism)
1300 1 : fmt.Fprintf(&buf, " secondary_cache_size_bytes=%d\n", o.Experimental.SecondaryCacheSizeBytes)
1301 1 : fmt.Fprintf(&buf, " create_on_shared=%d\n", o.Experimental.CreateOnShared)
1302 1 :
1303 1 : // Private options.
1304 1 : //
1305 1 : // These options are only encoded if true, because we do not want them to
1306 1 : // appear in production serialized Options files, since they're testing-only
1307 1 : // options. They're only serialized when true, which still ensures that the
1308 1 : // metamorphic tests may propagate them to subprocesses.
1309 1 : if o.private.disableDeleteOnlyCompactions {
1310 1 : fmt.Fprintln(&buf, " disable_delete_only_compactions=true")
1311 1 : }
1312 1 : if o.private.disableElisionOnlyCompactions {
1313 1 : fmt.Fprintln(&buf, " disable_elision_only_compactions=true")
1314 1 : }
1315 1 : if o.private.disableLazyCombinedIteration {
1316 1 : fmt.Fprintln(&buf, " disable_lazy_combined_iteration=true")
1317 1 : }
1318 :
1319 1 : for i := range o.Levels {
1320 1 : l := &o.Levels[i]
1321 1 : fmt.Fprintf(&buf, "\n")
1322 1 : fmt.Fprintf(&buf, "[Level \"%d\"]\n", i)
1323 1 : fmt.Fprintf(&buf, " block_restart_interval=%d\n", l.BlockRestartInterval)
1324 1 : fmt.Fprintf(&buf, " block_size=%d\n", l.BlockSize)
1325 1 : fmt.Fprintf(&buf, " block_size_threshold=%d\n", l.BlockSizeThreshold)
1326 1 : fmt.Fprintf(&buf, " compression=%s\n", l.Compression)
1327 1 : fmt.Fprintf(&buf, " filter_policy=%s\n", filterPolicyName(l.FilterPolicy))
1328 1 : fmt.Fprintf(&buf, " filter_type=%s\n", l.FilterType)
1329 1 : fmt.Fprintf(&buf, " index_block_size=%d\n", l.IndexBlockSize)
1330 1 : fmt.Fprintf(&buf, " target_file_size=%d\n", l.TargetFileSize)
1331 1 : }
1332 :
1333 1 : return buf.String()
1334 : }
1335 :
1336 1 : func parseOptions(s string, fn func(section, key, value string) error) error {
1337 1 : var section string
1338 1 : for _, line := range strings.Split(s, "\n") {
1339 1 : line = strings.TrimSpace(line)
1340 1 : if len(line) == 0 {
1341 1 : // Skip blank lines.
1342 1 : continue
1343 : }
1344 1 : if line[0] == ';' || line[0] == '#' {
1345 0 : // Skip comments.
1346 0 : continue
1347 : }
1348 1 : n := len(line)
1349 1 : if line[0] == '[' && line[n-1] == ']' {
1350 1 : // Parse section.
1351 1 : section = line[1 : n-1]
1352 1 : continue
1353 : }
1354 :
1355 1 : pos := strings.Index(line, "=")
1356 1 : if pos < 0 {
1357 1 : const maxLen = 50
1358 1 : if len(line) > maxLen {
1359 0 : line = line[:maxLen-3] + "..."
1360 0 : }
1361 1 : return base.CorruptionErrorf("invalid key=value syntax: %q", errors.Safe(line))
1362 : }
1363 :
1364 1 : key := strings.TrimSpace(line[:pos])
1365 1 : value := strings.TrimSpace(line[pos+1:])
1366 1 :
1367 1 : // RocksDB uses a similar (INI-style) syntax for the OPTIONS file, but
1368 1 : // different section names and keys. The "CFOptions ..." paths are the
1369 1 : // RocksDB versions which we map to the Pebble paths.
1370 1 : mappedSection := section
1371 1 : if section == `CFOptions "default"` {
1372 1 : mappedSection = "Options"
1373 1 : switch key {
1374 1 : case "comparator":
1375 1 : key = "comparer"
1376 1 : case "merge_operator":
1377 1 : key = "merger"
1378 : }
1379 : }
1380 :
1381 1 : if err := fn(mappedSection, key, value); err != nil {
1382 1 : return err
1383 1 : }
1384 : }
1385 1 : return nil
1386 : }
1387 :
1388 : // ParseHooks contains callbacks to create options fields which can have
1389 : // user-defined implementations.
1390 : type ParseHooks struct {
1391 : NewCache func(size int64) *Cache
1392 : NewCleaner func(name string) (Cleaner, error)
1393 : NewComparer func(name string) (*Comparer, error)
1394 : NewFilterPolicy func(name string) (FilterPolicy, error)
1395 : NewMerger func(name string) (*Merger, error)
1396 : SkipUnknown func(name, value string) bool
1397 : }
1398 :
1399 : // Parse parses the options from the specified string. Note that certain
1400 : // options cannot be parsed into populated fields. For example, comparer and
1401 : // merger.
1402 1 : func (o *Options) Parse(s string, hooks *ParseHooks) error {
1403 1 : return parseOptions(s, func(section, key, value string) error {
1404 1 : // WARNING: DO NOT remove entries from the switches below because doing so
1405 1 : // causes a key previously written to the OPTIONS file to be considered unknown,
1406 1 : // a backwards incompatible change. Instead, leave in support for parsing the
1407 1 : // key but simply don't parse the value.
1408 1 :
1409 1 : switch {
1410 1 : case section == "Version":
1411 1 : switch key {
1412 1 : case "pebble_version":
1413 0 : default:
1414 0 : if hooks != nil && hooks.SkipUnknown != nil && hooks.SkipUnknown(section+"."+key, value) {
1415 0 : return nil
1416 0 : }
1417 0 : return errors.Errorf("pebble: unknown option: %s.%s",
1418 0 : errors.Safe(section), errors.Safe(key))
1419 : }
1420 1 : return nil
1421 :
1422 1 : case section == "Options":
1423 1 : var err error
1424 1 : switch key {
1425 1 : case "bytes_per_sync":
1426 1 : o.BytesPerSync, err = strconv.Atoi(value)
1427 1 : case "cache_size":
1428 1 : var n int64
1429 1 : n, err = strconv.ParseInt(value, 10, 64)
1430 1 : if err == nil && hooks != nil && hooks.NewCache != nil {
1431 1 : if o.Cache != nil {
1432 0 : o.Cache.Unref()
1433 0 : }
1434 1 : o.Cache = hooks.NewCache(n)
1435 : }
1436 : // We avoid calling cache.New in parsing because it makes it
1437 : // too easy to leak a cache.
1438 1 : case "cleaner":
1439 1 : switch value {
1440 1 : case "archive":
1441 1 : o.Cleaner = ArchiveCleaner{}
1442 1 : case "delete":
1443 1 : o.Cleaner = DeleteCleaner{}
1444 0 : default:
1445 0 : if hooks != nil && hooks.NewCleaner != nil {
1446 0 : o.Cleaner, err = hooks.NewCleaner(value)
1447 0 : }
1448 : }
1449 1 : case "comparer":
1450 1 : switch value {
1451 1 : case "leveldb.BytewiseComparator":
1452 1 : o.Comparer = DefaultComparer
1453 1 : default:
1454 1 : if hooks != nil && hooks.NewComparer != nil {
1455 1 : o.Comparer, err = hooks.NewComparer(value)
1456 1 : }
1457 : }
1458 1 : case "compaction_debt_concurrency":
1459 1 : o.Experimental.CompactionDebtConcurrency, err = strconv.ParseUint(value, 10, 64)
1460 0 : case "delete_range_flush_delay":
1461 0 : // NB: This is a deprecated serialization of the
1462 0 : // `flush_delay_delete_range`.
1463 0 : o.FlushDelayDeleteRange, err = time.ParseDuration(value)
1464 1 : case "disable_delete_only_compactions":
1465 1 : o.private.disableDeleteOnlyCompactions, err = strconv.ParseBool(value)
1466 1 : case "disable_elision_only_compactions":
1467 1 : o.private.disableElisionOnlyCompactions, err = strconv.ParseBool(value)
1468 1 : case "disable_ingest_as_flushable":
1469 1 : var v bool
1470 1 : v, err = strconv.ParseBool(value)
1471 1 : if err == nil {
1472 1 : o.Experimental.DisableIngestAsFlushable = func() bool { return v }
1473 : }
1474 1 : case "disable_lazy_combined_iteration":
1475 1 : o.private.disableLazyCombinedIteration, err = strconv.ParseBool(value)
1476 1 : case "disable_wal":
1477 1 : o.DisableWAL, err = strconv.ParseBool(value)
1478 1 : case "flush_delay_delete_range":
1479 1 : o.FlushDelayDeleteRange, err = time.ParseDuration(value)
1480 1 : case "flush_delay_range_key":
1481 1 : o.FlushDelayRangeKey, err = time.ParseDuration(value)
1482 1 : case "flush_split_bytes":
1483 1 : o.FlushSplitBytes, err = strconv.ParseInt(value, 10, 64)
1484 1 : case "format_major_version":
1485 1 : // NB: The version written here may be stale. Open does
1486 1 : // not use the format major version encoded in the
1487 1 : // OPTIONS file other than to validate that the encoded
1488 1 : // version is valid right here.
1489 1 : var v uint64
1490 1 : v, err = strconv.ParseUint(value, 10, 64)
1491 1 : if vers := FormatMajorVersion(v); vers > internalFormatNewest || vers == FormatDefault {
1492 0 : err = errors.Newf("unsupported format major version %d", o.FormatMajorVersion)
1493 0 : }
1494 1 : if err == nil {
1495 1 : o.FormatMajorVersion = FormatMajorVersion(v)
1496 1 : }
1497 1 : case "l0_compaction_concurrency":
1498 1 : o.Experimental.L0CompactionConcurrency, err = strconv.Atoi(value)
1499 1 : case "l0_compaction_file_threshold":
1500 1 : o.L0CompactionFileThreshold, err = strconv.Atoi(value)
1501 1 : case "l0_compaction_threshold":
1502 1 : o.L0CompactionThreshold, err = strconv.Atoi(value)
1503 1 : case "l0_stop_writes_threshold":
1504 1 : o.L0StopWritesThreshold, err = strconv.Atoi(value)
1505 0 : case "l0_sublevel_compactions":
1506 : // Do nothing; option existed in older versions of pebble.
1507 1 : case "lbase_max_bytes":
1508 1 : o.LBaseMaxBytes, err = strconv.ParseInt(value, 10, 64)
1509 1 : case "level_multiplier":
1510 1 : o.Experimental.LevelMultiplier, err = strconv.Atoi(value)
1511 1 : case "max_concurrent_compactions":
1512 1 : var concurrentCompactions int
1513 1 : concurrentCompactions, err = strconv.Atoi(value)
1514 1 : if concurrentCompactions <= 0 {
1515 0 : err = errors.New("max_concurrent_compactions cannot be <= 0")
1516 1 : } else {
1517 1 : o.MaxConcurrentCompactions = func() int { return concurrentCompactions }
1518 : }
1519 1 : case "max_manifest_file_size":
1520 1 : o.MaxManifestFileSize, err = strconv.ParseInt(value, 10, 64)
1521 1 : case "max_open_files":
1522 1 : o.MaxOpenFiles, err = strconv.Atoi(value)
1523 1 : case "mem_table_size":
1524 1 : o.MemTableSize, err = strconv.ParseUint(value, 10, 64)
1525 1 : case "mem_table_stop_writes_threshold":
1526 1 : o.MemTableStopWritesThreshold, err = strconv.Atoi(value)
1527 0 : case "min_compaction_rate":
1528 : // Do nothing; option existed in older versions of pebble, and
1529 : // may be meaningful again eventually.
1530 1 : case "min_deletion_rate":
1531 1 : o.TargetByteDeletionRate, err = strconv.Atoi(value)
1532 0 : case "min_flush_rate":
1533 : // Do nothing; option existed in older versions of pebble, and
1534 : // may be meaningful again eventually.
1535 1 : case "multilevel_compaction_heuristic":
1536 1 : switch {
1537 1 : case value == "none":
1538 1 : o.Experimental.MultiLevelCompactionHeuristic = NoMultiLevel{}
1539 1 : case strings.HasPrefix(value, "wamp"):
1540 1 : fields := strings.FieldsFunc(strings.TrimPrefix(value, "wamp"), func(r rune) bool {
1541 1 : return unicode.IsSpace(r) || r == ',' || r == '(' || r == ')'
1542 1 : })
1543 1 : if len(fields) != 2 {
1544 0 : err = errors.Newf("require 2 arguments")
1545 0 : }
1546 1 : var h WriteAmpHeuristic
1547 1 : if err == nil {
1548 1 : h.AddPropensity, err = strconv.ParseFloat(fields[0], 64)
1549 1 : }
1550 1 : if err == nil {
1551 1 : h.AllowL0, err = strconv.ParseBool(fields[1])
1552 1 : }
1553 1 : if err == nil {
1554 1 : o.Experimental.MultiLevelCompactionHeuristic = h
1555 1 : } else {
1556 0 : err = errors.Wrapf(err, "unexpected wamp heuristic arguments: %s", value)
1557 0 : }
1558 0 : default:
1559 0 : err = errors.Newf("unrecognized multilevel compaction heuristic: %s", value)
1560 : }
1561 0 : case "point_tombstone_weight":
1562 : // Do nothing; deprecated.
1563 1 : case "strict_wal_tail":
1564 1 : o.private.strictWALTail, err = strconv.ParseBool(value)
1565 1 : case "merger":
1566 1 : switch value {
1567 0 : case "nullptr":
1568 0 : o.Merger = nil
1569 1 : case "pebble.concatenate":
1570 1 : o.Merger = DefaultMerger
1571 1 : default:
1572 1 : if hooks != nil && hooks.NewMerger != nil {
1573 1 : o.Merger, err = hooks.NewMerger(value)
1574 1 : }
1575 : }
1576 1 : case "read_compaction_rate":
1577 1 : o.Experimental.ReadCompactionRate, err = strconv.ParseInt(value, 10, 64)
1578 1 : case "read_sampling_multiplier":
1579 1 : o.Experimental.ReadSamplingMultiplier, err = strconv.ParseInt(value, 10, 64)
1580 1 : case "table_cache_shards":
1581 1 : o.Experimental.TableCacheShards, err = strconv.Atoi(value)
1582 0 : case "table_format":
1583 0 : switch value {
1584 0 : case "leveldb":
1585 0 : case "rocksdbv2":
1586 0 : default:
1587 0 : return errors.Errorf("pebble: unknown table format: %q", errors.Safe(value))
1588 : }
1589 1 : case "table_property_collectors":
1590 : // TODO(peter): set o.TablePropertyCollectors
1591 1 : case "validate_on_ingest":
1592 1 : o.Experimental.ValidateOnIngest, err = strconv.ParseBool(value)
1593 1 : case "wal_dir":
1594 1 : o.WALDir = value
1595 1 : case "wal_bytes_per_sync":
1596 1 : o.WALBytesPerSync, err = strconv.Atoi(value)
1597 1 : case "max_writer_concurrency":
1598 1 : o.Experimental.MaxWriterConcurrency, err = strconv.Atoi(value)
1599 1 : case "force_writer_parallelism":
1600 1 : o.Experimental.ForceWriterParallelism, err = strconv.ParseBool(value)
1601 1 : case "secondary_cache_size_bytes":
1602 1 : o.Experimental.SecondaryCacheSizeBytes, err = strconv.ParseInt(value, 10, 64)
1603 1 : case "create_on_shared":
1604 1 : var createOnSharedInt int64
1605 1 : createOnSharedInt, err = strconv.ParseInt(value, 10, 64)
1606 1 : o.Experimental.CreateOnShared = remote.CreateOnSharedStrategy(createOnSharedInt)
1607 0 : default:
1608 0 : if hooks != nil && hooks.SkipUnknown != nil && hooks.SkipUnknown(section+"."+key, value) {
1609 0 : return nil
1610 0 : }
1611 0 : return errors.Errorf("pebble: unknown option: %s.%s",
1612 0 : errors.Safe(section), errors.Safe(key))
1613 : }
1614 1 : return err
1615 :
1616 1 : case strings.HasPrefix(section, "Level "):
1617 1 : var index int
1618 1 : if n, err := fmt.Sscanf(section, `Level "%d"`, &index); err != nil {
1619 0 : return err
1620 1 : } else if n != 1 {
1621 0 : if hooks != nil && hooks.SkipUnknown != nil && hooks.SkipUnknown(section, value) {
1622 0 : return nil
1623 0 : }
1624 0 : return errors.Errorf("pebble: unknown section: %q", errors.Safe(section))
1625 : }
1626 :
1627 1 : if len(o.Levels) <= index {
1628 1 : newLevels := make([]LevelOptions, index+1)
1629 1 : copy(newLevels, o.Levels)
1630 1 : o.Levels = newLevels
1631 1 : }
1632 1 : l := &o.Levels[index]
1633 1 :
1634 1 : var err error
1635 1 : switch key {
1636 1 : case "block_restart_interval":
1637 1 : l.BlockRestartInterval, err = strconv.Atoi(value)
1638 1 : case "block_size":
1639 1 : l.BlockSize, err = strconv.Atoi(value)
1640 1 : case "block_size_threshold":
1641 1 : l.BlockSizeThreshold, err = strconv.Atoi(value)
1642 1 : case "compression":
1643 1 : switch value {
1644 0 : case "Default":
1645 0 : l.Compression = DefaultCompression
1646 1 : case "NoCompression":
1647 1 : l.Compression = NoCompression
1648 1 : case "Snappy":
1649 1 : l.Compression = SnappyCompression
1650 1 : case "ZSTD":
1651 1 : l.Compression = ZstdCompression
1652 0 : default:
1653 0 : return errors.Errorf("pebble: unknown compression: %q", errors.Safe(value))
1654 : }
1655 1 : case "filter_policy":
1656 1 : if hooks != nil && hooks.NewFilterPolicy != nil {
1657 1 : l.FilterPolicy, err = hooks.NewFilterPolicy(value)
1658 1 : }
1659 1 : case "filter_type":
1660 1 : switch value {
1661 1 : case "table":
1662 1 : l.FilterType = TableFilter
1663 0 : default:
1664 0 : return errors.Errorf("pebble: unknown filter type: %q", errors.Safe(value))
1665 : }
1666 1 : case "index_block_size":
1667 1 : l.IndexBlockSize, err = strconv.Atoi(value)
1668 1 : case "target_file_size":
1669 1 : l.TargetFileSize, err = strconv.ParseInt(value, 10, 64)
1670 0 : default:
1671 0 : if hooks != nil && hooks.SkipUnknown != nil && hooks.SkipUnknown(section+"."+key, value) {
1672 0 : return nil
1673 0 : }
1674 0 : return errors.Errorf("pebble: unknown option: %s.%s", errors.Safe(section), errors.Safe(key))
1675 : }
1676 1 : return err
1677 : }
1678 1 : if hooks != nil && hooks.SkipUnknown != nil && hooks.SkipUnknown(section+"."+key, value) {
1679 1 : return nil
1680 1 : }
1681 0 : return errors.Errorf("pebble: unknown section: %q", errors.Safe(section))
1682 : })
1683 : }
1684 :
1685 1 : func (o *Options) checkOptions(s string) (strictWALTail bool, err error) {
1686 1 : // TODO(jackson): Refactor to avoid awkwardness of the strictWALTail return value.
1687 1 : return strictWALTail, parseOptions(s, func(section, key, value string) error {
1688 1 : switch section + "." + key {
1689 1 : case "Options.comparer":
1690 1 : if value != o.Comparer.Name {
1691 1 : return errors.Errorf("pebble: comparer name from file %q != comparer name from options %q",
1692 1 : errors.Safe(value), errors.Safe(o.Comparer.Name))
1693 1 : }
1694 1 : case "Options.merger":
1695 1 : // RocksDB allows the merge operator to be unspecified, in which case it
1696 1 : // shows up as "nullptr".
1697 1 : if value != "nullptr" && value != o.Merger.Name {
1698 1 : return errors.Errorf("pebble: merger name from file %q != merger name from options %q",
1699 1 : errors.Safe(value), errors.Safe(o.Merger.Name))
1700 1 : }
1701 1 : case "Options.strict_wal_tail":
1702 1 : strictWALTail, err = strconv.ParseBool(value)
1703 1 : if err != nil {
1704 0 : return errors.Errorf("pebble: error parsing strict_wal_tail value %q: %w", value, err)
1705 0 : }
1706 : }
1707 1 : return nil
1708 : })
1709 : }
1710 :
1711 : // Check verifies the options are compatible with the previous options
1712 : // serialized by Options.String(). For example, the Comparer and Merger must be
1713 : // the same, or data will not be able to be properly read from the DB.
1714 1 : func (o *Options) Check(s string) error {
1715 1 : _, err := o.checkOptions(s)
1716 1 : return err
1717 1 : }
1718 :
1719 : // Validate verifies that the options are mutually consistent. For example,
1720 : // L0StopWritesThreshold must be >= L0CompactionThreshold, otherwise a write
1721 : // stall would persist indefinitely.
1722 1 : func (o *Options) Validate() error {
1723 1 : // Note that we can presume Options.EnsureDefaults has been called, so there
1724 1 : // is no need to check for zero values.
1725 1 :
1726 1 : var buf strings.Builder
1727 1 : if o.Experimental.L0CompactionConcurrency < 1 {
1728 1 : fmt.Fprintf(&buf, "L0CompactionConcurrency (%d) must be >= 1\n",
1729 1 : o.Experimental.L0CompactionConcurrency)
1730 1 : }
1731 1 : if o.L0StopWritesThreshold < o.L0CompactionThreshold {
1732 1 : fmt.Fprintf(&buf, "L0StopWritesThreshold (%d) must be >= L0CompactionThreshold (%d)\n",
1733 1 : o.L0StopWritesThreshold, o.L0CompactionThreshold)
1734 1 : }
1735 1 : if uint64(o.MemTableSize) >= maxMemTableSize {
1736 1 : fmt.Fprintf(&buf, "MemTableSize (%s) must be < %s\n",
1737 1 : humanize.Bytes.Uint64(uint64(o.MemTableSize)), humanize.Bytes.Uint64(maxMemTableSize))
1738 1 : }
1739 1 : if o.MemTableStopWritesThreshold < 2 {
1740 1 : fmt.Fprintf(&buf, "MemTableStopWritesThreshold (%d) must be >= 2\n",
1741 1 : o.MemTableStopWritesThreshold)
1742 1 : }
1743 1 : if o.FormatMajorVersion < FormatMinSupported || o.FormatMajorVersion > internalFormatNewest {
1744 0 : fmt.Fprintf(&buf, "FormatMajorVersion (%d) must be between %d and %d\n",
1745 0 : o.FormatMajorVersion, FormatMinSupported, internalFormatNewest)
1746 0 : }
1747 1 : if o.TableCache != nil && o.Cache != o.TableCache.cache {
1748 1 : fmt.Fprintf(&buf, "underlying cache in the TableCache and the Cache dont match\n")
1749 1 : }
1750 1 : if buf.Len() == 0 {
1751 1 : return nil
1752 1 : }
1753 1 : return errors.New(buf.String())
1754 : }
1755 :
1756 : // MakeReaderOptions constructs sstable.ReaderOptions from the corresponding
1757 : // options in the receiver.
1758 1 : func (o *Options) MakeReaderOptions() sstable.ReaderOptions {
1759 1 : var readerOpts sstable.ReaderOptions
1760 1 : if o != nil {
1761 1 : readerOpts.Cache = o.Cache
1762 1 : readerOpts.Comparer = o.Comparer
1763 1 : readerOpts.Filters = o.Filters
1764 1 : if o.Merger != nil {
1765 1 : readerOpts.Merge = o.Merger.Merge
1766 1 : readerOpts.MergerName = o.Merger.Name
1767 1 : }
1768 1 : readerOpts.LoggerAndTracer = o.LoggerAndTracer
1769 : }
1770 1 : return readerOpts
1771 : }
1772 :
1773 : // MakeWriterOptions constructs sstable.WriterOptions for the specified level
1774 : // from the corresponding options in the receiver.
1775 1 : func (o *Options) MakeWriterOptions(level int, format sstable.TableFormat) sstable.WriterOptions {
1776 1 : var writerOpts sstable.WriterOptions
1777 1 : writerOpts.TableFormat = format
1778 1 : if o != nil {
1779 1 : writerOpts.Cache = o.Cache
1780 1 : writerOpts.Comparer = o.Comparer
1781 1 : if o.Merger != nil {
1782 1 : writerOpts.MergerName = o.Merger.Name
1783 1 : }
1784 1 : writerOpts.TablePropertyCollectors = o.TablePropertyCollectors
1785 1 : writerOpts.BlockPropertyCollectors = o.BlockPropertyCollectors
1786 : }
1787 1 : if format >= sstable.TableFormatPebblev3 {
1788 1 : writerOpts.ShortAttributeExtractor = o.Experimental.ShortAttributeExtractor
1789 1 : writerOpts.RequiredInPlaceValueBound = o.Experimental.RequiredInPlaceValueBound
1790 1 : if format >= sstable.TableFormatPebblev4 && level == numLevels-1 {
1791 1 : writerOpts.WritingToLowestLevel = true
1792 1 : }
1793 : }
1794 1 : levelOpts := o.Level(level)
1795 1 : writerOpts.BlockRestartInterval = levelOpts.BlockRestartInterval
1796 1 : writerOpts.BlockSize = levelOpts.BlockSize
1797 1 : writerOpts.BlockSizeThreshold = levelOpts.BlockSizeThreshold
1798 1 : writerOpts.Compression = levelOpts.Compression
1799 1 : writerOpts.FilterPolicy = levelOpts.FilterPolicy
1800 1 : writerOpts.FilterType = levelOpts.FilterType
1801 1 : writerOpts.IndexBlockSize = levelOpts.IndexBlockSize
1802 1 : return writerOpts
1803 : }
|
