| 1 | #ifndef ODB_SOURCE_H |
| 2 | #define ODB_SOURCE_H |
| 3 | |
| 4 | #include "object.h" |
| 5 | #include "odb.h" |
| 6 | #include "odb/transaction.h" |
| 7 | |
| 8 | enum odb_source_type { |
| 9 | /* |
| 10 | * The "unknown" type, which should never be in use. This type mostly |
| 11 | * exists to catch cases where the type field remains zeroed out. |
| 12 | */ |
| 13 | ODB_SOURCE_UNKNOWN, |
| 14 | |
| 15 | /* The "files" backend that uses loose objects and packfiles. */ |
| 16 | ODB_SOURCE_FILES, |
| 17 | |
| 18 | /* The "loose" backend that uses loose objects, only. */ |
| 19 | ODB_SOURCE_LOOSE, |
| 20 | |
| 21 | /* The "packed" backend that uses packfiles. */ |
| 22 | ODB_SOURCE_PACKED, |
| 23 | |
| 24 | /* The "in-memory" backend that stores objects in memory. */ |
| 25 | ODB_SOURCE_INMEMORY, |
| 26 | }; |
| 27 | |
| 28 | struct object_id; |
| 29 | struct odb_read_stream; |
| 30 | struct strvec; |
| 31 | |
| 32 | /* |
| 33 | * The source is the part of the object database that stores the actual |
| 34 | * objects. It thus encapsulates the logic to read and write the specific |
| 35 | * on-disk format. An object database can have multiple sources: |
| 36 | * |
| 37 | * - The primary source, which is typically located in "$GIT_DIR/objects". |
| 38 | * This is where new objects are usually written to. |
| 39 | * |
| 40 | * - Alternate sources, which are configured via "objects/info/alternates" or |
| 41 | * via the GIT_ALTERNATE_OBJECT_DIRECTORIES environment variable. These |
| 42 | * alternate sources are only used to read objects. |
| 43 | */ |
| 44 | struct odb_source { |
| 45 | struct odb_source *next; |
| 46 | |
| 47 | /* Object database that owns this object source. */ |
| 48 | struct object_database *odb; |
| 49 | |
| 50 | /* The type used by this source. */ |
| 51 | enum odb_source_type type; |
| 52 | |
| 53 | /* |
| 54 | * Figure out whether this is the local source of the owning |
| 55 | * repository, which would typically be its ".git/objects" directory. |
| 56 | * This local object directory is usually where objects would be |
| 57 | * written to. |
| 58 | */ |
| 59 | bool local; |
| 60 | |
| 61 | /* |
| 62 | * This object store is ephemeral, so there is no need to fsync. |
| 63 | */ |
| 64 | int will_destroy; |
| 65 | |
| 66 | /* |
| 67 | * Path to the source. If this is a relative path, it is relative to |
| 68 | * the current working directory. |
| 69 | */ |
| 70 | char *path; |
| 71 | |
| 72 | /* |
| 73 | * This callback is expected to free the underlying object database source and |
| 74 | * all associated resources. The function will never be called with a NULL pointer. |
| 75 | */ |
| 76 | void (*free)(struct odb_source *source); |
| 77 | |
| 78 | /* |
| 79 | * This callback is expected to close any open resources, like for |
| 80 | * example file descriptors or connections. The source is expected to |
| 81 | * still be usable after it has been closed. Closed resources may need |
| 82 | * to be reopened in that case. |
| 83 | */ |
| 84 | void (*close)(struct odb_source *source); |
| 85 | |
| 86 | /* |
| 87 | * This callback is expected to prepare the source so that it becomes |
| 88 | * ready for use. It optionally clears underlying caches of the object |
| 89 | * database source. |
| 90 | */ |
| 91 | void (*prepare)(struct odb_source *source, |
| 92 | enum odb_prepare_flags flags); |
| 93 | |
| 94 | /* |
| 95 | * This callback is expected to read object information from the object |
| 96 | * database source. The object info will be partially populated with |
| 97 | * pointers for each bit of information that was requested by the |
| 98 | * caller. |
| 99 | * |
| 100 | * The flags field is a combination of `OBJECT_INFO` flags. Only the |
| 101 | * following fields need to be handled by the backend: |
| 102 | * |
| 103 | * - `OBJECT_INFO_QUICK` indicates it is fine to use caches without |
| 104 | * re-verifying the data. |
| 105 | * |
| 106 | * - `OBJECT_INFO_SECOND_READ` indicates that the initial object |
| 107 | * lookup has failed and that the object sources should check |
| 108 | * whether any of its on-disk state has changed that may have |
| 109 | * caused the object to appear. Sources are free to ignore the |
| 110 | * second read in case they know that the first read would have |
| 111 | * already surfaced the object without reloading any on-disk state. |
| 112 | * |
| 113 | * The callback is expected to return a negative error code in case |
| 114 | * reading the object has failed, 0 otherwise. |
| 115 | */ |
| 116 | int (*read_object_info)(struct odb_source *source, |
| 117 | const struct object_id *oid, |
| 118 | struct object_info *oi, |
| 119 | enum object_info_flags flags); |
| 120 | |
| 121 | /* |
| 122 | * This callback is expected to create a new read stream that can be |
| 123 | * used to stream the object identified by the given ID. |
| 124 | * |
| 125 | * The callback is expected to return a negative error code in case |
| 126 | * creating the object stream has failed, 0 otherwise. |
| 127 | */ |
| 128 | int (*read_object_stream)(struct odb_read_stream **out, |
| 129 | struct odb_source *source, |
| 130 | const struct object_id *oid); |
| 131 | |
| 132 | /* |
| 133 | * This callback is expected to iterate over all objects stored in this |
| 134 | * source and invoke the callback function for each of them. It is |
| 135 | * valid to yield the same object multiple time. A non-zero exit code |
| 136 | * from the object callback shall abort iteration. |
| 137 | * |
| 138 | * The optional `request` structure should serve as a template for |
| 139 | * looking up object info for every individual iterated object. It |
| 140 | * should not be modified directly and should instead be copied into a |
| 141 | * separate `struct object_info` that gets passed to the callback. If |
| 142 | * the caller passes a `NULL` pointer then the object itself shall not |
| 143 | * be read. |
| 144 | * |
| 145 | * The callback is expected to return a negative error code in case the |
| 146 | * iteration has failed to read all objects, 0 otherwise. When the |
| 147 | * callback function returns a non-zero error code then that error code |
| 148 | * should be returned. |
| 149 | */ |
| 150 | int (*for_each_object)(struct odb_source *source, |
| 151 | const struct object_info *request, |
| 152 | odb_for_each_object_cb cb, |
| 153 | void *cb_data, |
| 154 | const struct odb_for_each_object_options *opts); |
| 155 | |
| 156 | /* |
| 157 | * This callback is expected to count objects in the given object |
| 158 | * database source. The callback function does not have to guarantee |
| 159 | * that only unique objects are counted. The result shall be assigned |
| 160 | * to the `out` pointer. |
| 161 | * |
| 162 | * Accepts `enum odb_count_objects_flag` flags to alter the behaviour. |
| 163 | * |
| 164 | * The callback is expected to return 0 on success, or a negative error |
| 165 | * code otherwise. |
| 166 | */ |
| 167 | int (*count_objects)(struct odb_source *source, |
| 168 | enum odb_count_objects_flags flags, |
| 169 | unsigned long *out); |
| 170 | |
| 171 | /* |
| 172 | * This callback is expected to find the minimum required length to |
| 173 | * make the given object ID unique. |
| 174 | * |
| 175 | * The callback is expected to return a negative error code in case it |
| 176 | * failed, 0 otherwise. |
| 177 | */ |
| 178 | int (*find_abbrev_len)(struct odb_source *source, |
| 179 | const struct object_id *oid, |
| 180 | unsigned min_length, |
| 181 | unsigned *out); |
| 182 | |
| 183 | /* |
| 184 | * This callback is expected to freshen the given object so that its |
| 185 | * last access time is set to the current time. This is used to ensure |
| 186 | * that objects that are recent will not get garbage collected even if |
| 187 | * they were unreachable. |
| 188 | * |
| 189 | * Returns 0 in case the object does not exist, 1 in case the object |
| 190 | * has been freshened. |
| 191 | */ |
| 192 | int (*freshen_object)(struct odb_source *source, |
| 193 | const struct object_id *oid, |
| 194 | const time_t *mtime); |
| 195 | |
| 196 | /* |
| 197 | * This callback is expected to persist the given object into the |
| 198 | * object source. In case the object already exists it shall be |
| 199 | * freshened. |
| 200 | * |
| 201 | * The flags field is a combination of `WRITE_OBJECT` flags. |
| 202 | * |
| 203 | * The resulting object ID (and optionally the compatibility object ID) |
| 204 | * shall be written into the out pointers. The callback is expected to |
| 205 | * return 0 on success, a negative error code otherwise. |
| 206 | */ |
| 207 | int (*write_object)(struct odb_source *source, |
| 208 | const void *buf, size_t len, |
| 209 | enum object_type type, |
| 210 | const struct object_id *oid, |
| 211 | const struct object_id *compat_oid, |
| 212 | const time_t *mtime, |
| 213 | enum odb_write_object_flags flags); |
| 214 | |
| 215 | /* |
| 216 | * This callback is expected to persist the given object stream into |
| 217 | * the object source. |
| 218 | * |
| 219 | * The resulting object ID shall be written into the out pointer. The |
| 220 | * callback is expected to return 0 on success, a negative error code |
| 221 | * otherwise. |
| 222 | */ |
| 223 | int (*write_object_stream)(struct odb_source *source, |
| 224 | struct odb_write_stream *stream, size_t len, |
| 225 | struct object_id *oid); |
| 226 | |
| 227 | /* |
| 228 | * This callback is expected to create a new transaction that can be |
| 229 | * used to write objects to. The objects shall only be persisted into |
| 230 | * the object database when the transcation's commit function is |
| 231 | * called. Otherwise, the objects shall be discarded. |
| 232 | * |
| 233 | * Returns 0 on success, in which case the `*out` pointer will have |
| 234 | * been populated with the object database transaction. Returns a |
| 235 | * negative error code otherwise. |
| 236 | */ |
| 237 | int (*begin_transaction)(struct odb_source *source, |
| 238 | struct odb_transaction **out, |
| 239 | enum odb_transaction_flags flags); |
| 240 | |
| 241 | /* |
| 242 | * This callback is expected to read the list of alternate object |
| 243 | * database sources connected to it and write them into the `strvec`. |
| 244 | * |
| 245 | * The result is expected to be paths to the alternates. All paths must |
| 246 | * be resolved to absolute paths. |
| 247 | * |
| 248 | * The callback is expected to return 0 on success, a negative error |
| 249 | * code otherwise. |
| 250 | */ |
| 251 | int (*read_alternates)(struct odb_source *source, |
| 252 | struct strvec *out); |
| 253 | |
| 254 | /* |
| 255 | * This callback is expected to persist the singular alternate passed |
| 256 | * to it into its list of alternates. Any pre-existing alternates are |
| 257 | * expected to remain active. Subsequent calls to `read_alternates` are |
| 258 | * thus expected to yield the pre-existing list of alternates plus the |
| 259 | * newly added alternate appended to its end. |
| 260 | * |
| 261 | * The callback is expected to return 0 on success, a negative error |
| 262 | * code otherwise. |
| 263 | */ |
| 264 | int (*write_alternate)(struct odb_source *source, |
| 265 | const char *alternate); |
| 266 | }; |
| 267 | |
| 268 | /* |
| 269 | * Allocate and initialize a new source for the given object database located |
| 270 | * at `path`. `local` indicates whether or not the source is the local and thus |
| 271 | * primary object source of the object database. |
| 272 | */ |
| 273 | struct odb_source *odb_source_new(struct object_database *odb, |
| 274 | const char *path, |
| 275 | bool local); |
| 276 | |
| 277 | /* |
| 278 | * Initialize the source for the given object database located at `path`. |
| 279 | * `local` indicates whether or not the source is the local and thus primary |
| 280 | * object source of the object database. |
| 281 | * |
| 282 | * This function is only supposed to be called by specific object source |
| 283 | * implementations. |
| 284 | */ |
| 285 | void odb_source_init(struct odb_source *source, |
| 286 | struct object_database *odb, |
| 287 | enum odb_source_type type, |
| 288 | const char *path, |
| 289 | bool local); |
| 290 | |
| 291 | /* |
| 292 | * Free the object database source, releasing all associated resources and |
| 293 | * freeing the structure itself. |
| 294 | */ |
| 295 | void odb_source_free(struct odb_source *source); |
| 296 | |
| 297 | /* |
| 298 | * Release the object database source, releasing all associated resources. |
| 299 | * |
| 300 | * This function is only supposed to be called by specific object source |
| 301 | * implementations. |
| 302 | */ |
| 303 | void odb_source_release(struct odb_source *source); |
| 304 | |
| 305 | /* |
| 306 | * Close the object database source without releasing he underlying data. The |
| 307 | * source can still be used going forward, but it first needs to be reopened. |
| 308 | * This can be useful to reduce resource usage. |
| 309 | */ |
| 310 | static inline void odb_source_close(struct odb_source *source) |
| 311 | { |
| 312 | source->close(source); |
| 313 | } |
| 314 | |
| 315 | /* |
| 316 | * Prepare the object database source and clear any caches. Depending on the |
| 317 | * backend used this may have the effect that concurrently-written objects |
| 318 | * become visible. |
| 319 | */ |
| 320 | static inline void odb_source_prepare(struct odb_source *source, |
| 321 | enum odb_prepare_flags flags) |
| 322 | { |
| 323 | source->prepare(source, flags); |
| 324 | } |
| 325 | |
| 326 | /* |
| 327 | * Read an object from the object database source identified by its object ID. |
| 328 | * Returns 0 on success, a negative error code otherwise. |
| 329 | */ |
| 330 | static inline int odb_source_read_object_info(struct odb_source *source, |
| 331 | const struct object_id *oid, |
| 332 | struct object_info *oi, |
| 333 | enum object_info_flags flags) |
| 334 | { |
| 335 | return source->read_object_info(source, oid, oi, flags); |
| 336 | } |
| 337 | |
| 338 | /* |
| 339 | * Create a new read stream for the given object ID. Returns 0 on success, a |
| 340 | * negative error code otherwise. |
| 341 | */ |
| 342 | static inline int odb_source_read_object_stream(struct odb_read_stream **out, |
| 343 | struct odb_source *source, |
| 344 | const struct object_id *oid) |
| 345 | { |
| 346 | return source->read_object_stream(out, source, oid); |
| 347 | } |
| 348 | |
| 349 | /* |
| 350 | * Iterate through all objects contained in the given source and invoke the |
| 351 | * callback function for each of them. Returning a non-zero code from the |
| 352 | * callback function aborts iteration. There is no guarantee that objects |
| 353 | * are only iterated over once. |
| 354 | * |
| 355 | * The optional `request` structure serves as a template for retrieving the |
| 356 | * object info for each individual iterated object and will be populated as if |
| 357 | * `odb_source_read_object_info()` was called on the object. It will not be |
| 358 | * modified, the callback will instead be invoked with a separate `struct |
| 359 | * object_info` for every object. Object info will not be read when passing a |
| 360 | * `NULL` pointer. |
| 361 | * |
| 362 | * The flags is a bitfield of `ODB_FOR_EACH_OBJECT_*` flags. Not all flags may |
| 363 | * apply to a specific backend, so whether or not they are honored is defined |
| 364 | * by the implementation. |
| 365 | * |
| 366 | * Returns 0 when all objects have been iterated over, a negative error code in |
| 367 | * case iteration has failed, or a non-zero value returned from the callback. |
| 368 | */ |
| 369 | static inline int odb_source_for_each_object(struct odb_source *source, |
| 370 | const struct object_info *request, |
| 371 | odb_for_each_object_cb cb, |
| 372 | void *cb_data, |
| 373 | const struct odb_for_each_object_options *opts) |
| 374 | { |
| 375 | return source->for_each_object(source, request, cb, cb_data, opts); |
| 376 | } |
| 377 | |
| 378 | /* |
| 379 | * Count the number of objects in the given object database source. |
| 380 | * |
| 381 | * Returns 0 on success, a negative error code otherwise. |
| 382 | */ |
| 383 | static inline int odb_source_count_objects(struct odb_source *source, |
| 384 | enum odb_count_objects_flags flags, |
| 385 | unsigned long *out) |
| 386 | { |
| 387 | return source->count_objects(source, flags, out); |
| 388 | } |
| 389 | |
| 390 | /* |
| 391 | * Determine the minimum required length to make the given object ID unique in |
| 392 | * the given source. Returns 0 on success, a negative error code otherwise. |
| 393 | */ |
| 394 | static inline int odb_source_find_abbrev_len(struct odb_source *source, |
| 395 | const struct object_id *oid, |
| 396 | unsigned min_len, |
| 397 | unsigned *out) |
| 398 | { |
| 399 | return source->find_abbrev_len(source, oid, min_len, out); |
| 400 | } |
| 401 | |
| 402 | /* |
| 403 | * Freshen an object in the object database by updating its timestamp. |
| 404 | * Returns 1 in case the object has been freshened, 0 in case the object does |
| 405 | * not exist. |
| 406 | */ |
| 407 | static inline int odb_source_freshen_object(struct odb_source *source, |
| 408 | const struct object_id *oid, |
| 409 | const time_t *mtime) |
| 410 | { |
| 411 | return source->freshen_object(source, oid, mtime); |
| 412 | } |
| 413 | |
| 414 | /* |
| 415 | * Write an object into the object database source. Returns 0 on success, a |
| 416 | * negative error code otherwise. Populates the given out pointers for the |
| 417 | * object ID and the compatibility object ID, if non-NULL. |
| 418 | */ |
| 419 | static inline int odb_source_write_object(struct odb_source *source, |
| 420 | const void *buf, unsigned long len, |
| 421 | enum object_type type, |
| 422 | const struct object_id *oid, |
| 423 | const struct object_id *compat_oid, |
| 424 | const time_t *mtime, |
| 425 | enum odb_write_object_flags flags) |
| 426 | { |
| 427 | return source->write_object(source, buf, len, type, oid, |
| 428 | compat_oid, mtime, flags); |
| 429 | } |
| 430 | |
| 431 | /* |
| 432 | * Write an object into the object database source via a stream. The overall |
| 433 | * length of the object must be known in advance. |
| 434 | * |
| 435 | * Return 0 on success, a negative error code otherwise. Populates the given |
| 436 | * out pointer for the object ID. |
| 437 | */ |
| 438 | static inline int odb_source_write_object_stream(struct odb_source *source, |
| 439 | struct odb_write_stream *stream, |
| 440 | size_t len, |
| 441 | struct object_id *oid) |
| 442 | { |
| 443 | return source->write_object_stream(source, stream, len, oid); |
| 444 | } |
| 445 | |
| 446 | /* |
| 447 | * Read the list of alternative object database sources from the given backend |
| 448 | * and populate the `strvec` with them. The listing is not recursive -- that |
| 449 | * is, if any of the yielded alternate sources has alternates itself, those |
| 450 | * will not be yielded as part of this function call. |
| 451 | * |
| 452 | * Return 0 on success, a negative error code otherwise. |
| 453 | */ |
| 454 | static inline int odb_source_read_alternates(struct odb_source *source, |
| 455 | struct strvec *out) |
| 456 | { |
| 457 | return source->read_alternates(source, out); |
| 458 | } |
| 459 | |
| 460 | /* |
| 461 | * Write and persist a new alternate object database source for the given |
| 462 | * source. Any preexisting alternates are expected to stay valid, and the new |
| 463 | * alternate shall be appended to the end of the list. |
| 464 | * |
| 465 | * Returns 0 on success, a negative error code otherwise. |
| 466 | */ |
| 467 | static inline int odb_source_write_alternate(struct odb_source *source, |
| 468 | const char *alternate) |
| 469 | { |
| 470 | return source->write_alternate(source, alternate); |
| 471 | } |
| 472 | |
| 473 | /* |
| 474 | * Create a new transaction that can be used to write objects into a temporary |
| 475 | * staging area. The objects will only be persisted when the transaction is |
| 476 | * committed. |
| 477 | * |
| 478 | * Returns 0 on success, a negative error code otherwise. |
| 479 | */ |
| 480 | static inline int odb_source_begin_transaction(struct odb_source *source, |
| 481 | struct odb_transaction **out, |
| 482 | enum odb_transaction_flags flags) |
| 483 | { |
| 484 | return source->begin_transaction(source, out, flags); |
| 485 | } |
| 486 | |
| 487 | #endif |