1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-05 15:16:34 +02:00
git/refs/refs-internal.h

739 lines
26 KiB
C
Raw Normal View History

#ifndef REFS_REFS_INTERNAL_H
#define REFS_REFS_INTERNAL_H
#include "refs.h"
#include "iterator.h"
struct ref_transaction;
/*
* Data structures and functions for the internal use of the refs
* module. Code outside of the refs module should use only the public
* functions defined in "refs.h", and should *not* include this file.
*/
/*
* The following flags can appear in `ref_update::flags`. Their
* numerical values must not conflict with those of REF_NO_DEREF and
* REF_FORCE_CREATE_REFLOG, which are also stored in
* `ref_update::flags`.
*/
/*
* The reference should be updated to new_oid.
*/
#define REF_HAVE_NEW (1 << 2)
/*
* The current reference's value should be checked to make sure that
* it agrees with old_oid.
*/
#define REF_HAVE_OLD (1 << 3)
/*
* Used as a flag in ref_update::flags when we want to log a ref
* update but not actually perform it. This is used when a symbolic
* ref update is split up.
*/
#define REF_LOG_ONLY (1 << 7)
/*
* Return the length of time to retry acquiring a loose reference lock
* before giving up, in milliseconds:
*/
long get_files_ref_lock_timeout_ms(void);
/*
* Return true iff refname is minimally safe. "Safe" here means that
* deleting a loose reference by this name will not do any damage, for
* example by causing a file that is not a reference to be deleted.
* This function does not check that the reference name is legal; for
* that, use check_refname_format().
*
* A refname that starts with "refs/" is considered safe iff it
* doesn't contain any "." or ".." components or consecutive '/'
* characters, end with '/', or (on Windows) contain any '\'
* characters. Names that do not start with "refs/" are considered
* safe iff they consist entirely of upper case characters and '_'
* (like "HEAD" and "MERGE_HEAD" but not "config" or "FOO/BAR").
*/
int refname_is_safe(const char *refname);
/*
* Helper function: return true if refname, which has the specified
* oid and flags, can be resolved to an object in the database. If the
* referred-to object does not exist, emit a warning and return false.
*/
int ref_resolves_to_object(const char *refname,
struct repository *repo,
const struct object_id *oid,
unsigned int flags);
enum peel_status {
/* object was peeled successfully: */
PEEL_PEELED = 0,
/*
* object cannot be peeled because the named object (or an
* object referred to by a tag in the peel chain), does not
* exist.
*/
PEEL_INVALID = -1,
/* object cannot be peeled because it is not a tag: */
PEEL_NON_TAG = -2,
/* ref_entry contains no peeled value because it is a symref: */
PEEL_IS_SYMREF = -3,
/*
* ref_entry cannot be peeled because it is broken (i.e., the
* symbolic reference cannot even be resolved to an object
* name):
*/
PEEL_BROKEN = -4
};
/*
* Peel the named object; i.e., if the object is a tag, resolve the
* tag recursively until a non-tag is found. If successful, store the
* result to oid and return PEEL_PEELED. If the object is not a tag
* or is not valid, return PEEL_NON_TAG or PEEL_INVALID, respectively,
* and leave oid unchanged.
*/
enum peel_status peel_object(const struct object_id *name, struct object_id *oid);
/**
* Information needed for a single ref update. Set new_oid to the new
* value or to null_oid to delete the ref. To check the old value
* while the ref is locked, set (flags & REF_HAVE_OLD) and set old_oid
* to the old value, or to null_oid to ensure the ref does not exist
* before update.
*/
struct ref_update {
/*
* If (flags & REF_HAVE_NEW), set the reference to this value
* (or delete it, if `new_oid` is `null_oid`).
*/
struct object_id new_oid;
/*
* If (flags & REF_HAVE_OLD), check that the reference
* previously had this value (or didn't previously exist, if
* `old_oid` is `null_oid`).
*/
struct object_id old_oid;
/*
* One or more of REF_NO_DEREF, REF_FORCE_CREATE_REFLOG,
* REF_HAVE_NEW, REF_HAVE_OLD, or backend-specific flags.
*/
unsigned int flags;
void *backend_data;
unsigned int type;
char *msg;
/*
* If this ref_update was split off of a symref update via
* split_symref_update(), then this member points at that
* update. This is used for two purposes:
* 1. When reporting errors, we report the refname under which
* the update was originally requested.
* 2. When we read the old value of this reference, we
* propagate it back to its parent update for recording in
* the latter's reflog.
*/
struct ref_update *parent_update;
const char refname[FLEX_ARRAY];
};
int refs_read_raw_ref(struct ref_store *ref_store, const char *refname,
struct object_id *oid, struct strbuf *referent,
unsigned int *type, int *failure_errno);
/*
* Write an error to `err` and return a nonzero value iff the same
* refname appears multiple times in `refnames`. `refnames` must be
* sorted on entry to this function.
*/
int ref_update_reject_duplicates(struct string_list *refnames,
struct strbuf *err);
/*
* Add a ref_update with the specified properties to transaction, and
* return a pointer to the new object. This function does not verify
* that refname is well-formed. new_oid and old_oid are only
* dereferenced if the REF_HAVE_NEW and REF_HAVE_OLD bits,
* respectively, are set in flags.
*/
struct ref_update *ref_transaction_add_update(
struct ref_transaction *transaction,
const char *refname, unsigned int flags,
const struct object_id *new_oid,
const struct object_id *old_oid,
const char *msg);
/*
* Transaction states.
*
* OPEN: The transaction is initialized and new updates can still be
* added to it. An OPEN transaction can be prepared,
* committed, freed, or aborted (freeing and aborting an open
* transaction are equivalent).
*
* PREPARED: ref_transaction_prepare(), which locks all of the
* references involved in the update and checks that the
* update has no errors, has been called successfully for the
* transaction. A PREPARED transaction can be committed or
* aborted.
*
* CLOSED: The transaction is no longer active. A transaction becomes
* CLOSED if there is a failure while building the transaction
* or if a transaction is committed or aborted. A CLOSED
* transaction can only be freed.
*/
enum ref_transaction_state {
REF_TRANSACTION_OPEN = 0,
REF_TRANSACTION_PREPARED = 1,
REF_TRANSACTION_CLOSED = 2
};
/*
* Data structure for holding a reference transaction, which can
* consist of checks and updates to multiple references, carried out
* as atomically as possible. This structure is opaque to callers.
*/
struct ref_transaction {
struct ref_store *ref_store;
struct ref_update **updates;
size_t alloc;
size_t nr;
enum ref_transaction_state state;
void *backend_data;
};
/*
* Check for entries in extras that are within the specified
* directory, where dirname is a reference directory name including
* the trailing slash (e.g., "refs/heads/foo/"). Ignore any
* conflicting references that are found in skip. If there is a
* conflicting reference, return its name.
*
* extras and skip must be sorted lists of reference names. Either one
* can be NULL, signifying the empty list.
*/
const char *find_descendant_ref(const char *dirname,
const struct string_list *extras,
const struct string_list *skip);
/* We allow "recursive" symbolic refs. Only within reason, though */
#define SYMREF_MAXDEPTH 5
/*
* These flags are passed to refs_ref_iterator_begin() (and do_for_each_ref(),
* which feeds it).
*/
enum do_for_each_ref_flags {
/*
* Include broken references in a do_for_each_ref*() iteration, which
* would normally be omitted. This includes both refs that point to
* missing objects (a true repository corruption), ones with illegal
* names (which we prefer not to expose to callers), as well as
* dangling symbolic refs (i.e., those that point to a non-existent
* ref; this is not a corruption, but as they have no valid oid, we
* omit them from normal iteration results).
*/
DO_FOR_EACH_INCLUDE_BROKEN = (1 << 0),
/*
* Only include per-worktree refs in a do_for_each_ref*() iteration.
* Normally this will be used with a files ref_store, since that's
* where all reference backends will presumably store their
* per-worktree refs.
*/
DO_FOR_EACH_PER_WORKTREE_ONLY = (1 << 1),
refs: add DO_FOR_EACH_OMIT_DANGLING_SYMREFS flag When the DO_FOR_EACH_INCLUDE_BROKEN flag is used, we include both actual corrupt refs (illegal names, missing objects), but also symrefs that point to nothing. This latter is not really a corruption, but just something that may happen normally. For example, the symref at refs/remotes/origin/HEAD may point to a tracking branch which is later deleted. (The local HEAD may also be unborn, of course, but we do not access it through ref iteration). Most callers of for_each_ref() etc, do not care. They don't pass INCLUDE_BROKEN, so don't see it at all. But for those which do pass it, this somewhat-normal state causes extra warnings (e.g., from for-each-ref) or even aborts operations (destructive repacks with GIT_REF_PARANOIA set). This patch just introduces the flag and the mechanism; there are no callers yet (and hence no tests). Two things to note on the implementation: - we actually skip any symref that does not resolve to a ref. This includes ones which point to an invalidly-named ref. You could argue this is a more serious breakage than simple dangling. But the overall effect is the same (we could not follow the symref), as well as the impact on things like REF_PARANOIA (either way, a symref we can't follow won't impact reachability, because we'll see the ref itself during iteration). The underlying resolution function doesn't distinguish these two cases (they both get REF_ISBROKEN). - we change the iterator in refs/files-backend.c where we check INCLUDE_BROKEN. There's a matching spot in refs/packed-backend.c, but we don't know need to do anything there. The packed backend does not support symrefs at all. The resulting set of flags might be a bit easier to follow if we broke this down into "INCLUDE_CORRUPT_REFS" and "INCLUDE_DANGLING_SYMREFS". But there are a few reasons not do so: - adding a new OMIT_DANGLING_SYMREFS flag lets us leave existing callers intact, without changing their behavior (and some of them really do want to see the dangling symrefs; e.g., t5505 has a test which expects us to report when a symref becomes dangling) - they're not actually independent. You cannot say "include dangling symrefs" without also including refs whose objects are not reachable, because dangling symrefs by definition do not have an object. We could tweak the implementation to distinguish this, but in practice nobody wants to ask for that. Adding the OMIT flag keeps the implementation simple and makes sure we don't regress the current behavior. Signed-off-by: Jeff King <peff@peff.net> Reviewed-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-09-24 20:41:32 +02:00
/*
* Omit dangling symrefs from output; this only has an effect with
* INCLUDE_BROKEN, since they are otherwise not included at all.
*/
DO_FOR_EACH_OMIT_DANGLING_SYMREFS = (1 << 2),
/*
* Include root refs i.e. HEAD and pseudorefs along with the regular
* refs.
*/
DO_FOR_EACH_INCLUDE_ROOT_REFS = (1 << 3),
};
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
/*
* Reference iterators
*
* A reference iterator encapsulates the state of an in-progress
* iteration over references. Create an instance of `struct
* ref_iterator` via one of the functions in this module.
*
* A freshly-created ref_iterator doesn't yet point at a reference. To
* advance the iterator, call ref_iterator_advance(). If successful,
* this sets the iterator's refname, oid, and flags fields to describe
* the next reference and returns ITER_OK. The data pointed at by
* refname and oid belong to the iterator; if you want to retain them
* after calling ref_iterator_advance() again or calling
* ref_iterator_abort(), you must make a copy. When the iteration has
* been exhausted, ref_iterator_advance() releases any resources
* associated with the iteration, frees the ref_iterator object, and
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
* returns ITER_DONE. If you want to abort the iteration early, call
* ref_iterator_abort(), which also frees the ref_iterator object and
* any associated resources. If there was an internal error advancing
* to the next entry, ref_iterator_advance() aborts the iteration,
* frees the ref_iterator, and returns ITER_ERROR.
*
* The reference currently being looked at can be peeled by calling
* ref_iterator_peel(). This function is often faster than peel_ref(),
* so it should be preferred when iterating over references.
*
* Putting it all together, a typical iteration looks like this:
*
* int ok;
* struct ref_iterator *iter = ...;
*
* while ((ok = ref_iterator_advance(iter)) == ITER_OK) {
* if (want_to_stop_iteration()) {
* ok = ref_iterator_abort(iter);
* break;
* }
*
* // Access information about the current reference:
* if (!(iter->flags & REF_ISSYMREF))
* printf("%s is %s\n", iter->refname, oid_to_hex(iter->oid));
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
*
* // If you need to peel the reference:
* ref_iterator_peel(iter, &oid);
* }
*
* if (ok != ITER_DONE)
* handle_error();
*/
struct ref_iterator {
struct ref_iterator_vtable *vtable;
const char *refname;
const struct object_id *oid;
unsigned int flags;
};
/*
* Advance the iterator to the first or next item and return ITER_OK.
* If the iteration is exhausted, free the resources associated with
* the ref_iterator and return ITER_DONE. On errors, free the iterator
* resources and return ITER_ERROR. It is a bug to use ref_iterator or
* call this function again after it has returned ITER_DONE or
* ITER_ERROR.
*/
int ref_iterator_advance(struct ref_iterator *ref_iterator);
/*
* If possible, peel the reference currently being viewed by the
* iterator. Return 0 on success.
*/
int ref_iterator_peel(struct ref_iterator *ref_iterator,
struct object_id *peeled);
/*
* End the iteration before it has been exhausted, freeing the
* reference iterator and any associated resources and returning
* ITER_DONE. If the abort itself failed, return ITER_ERROR.
*/
int ref_iterator_abort(struct ref_iterator *ref_iterator);
/*
* An iterator over nothing (its first ref_iterator_advance() call
* returns ITER_DONE).
*/
struct ref_iterator *empty_ref_iterator_begin(void);
/*
* Return true iff ref_iterator is an empty_ref_iterator.
*/
int is_empty_ref_iterator(struct ref_iterator *ref_iterator);
/*
* Return an iterator that goes over each reference in `refs` for
* which the refname begins with prefix. If trim is non-zero, then
* trim that many characters off the beginning of each refname.
* The output is ordered by refname.
*/
struct ref_iterator *refs_ref_iterator_begin(
struct ref_store *refs,
const char *prefix, const char **exclude_patterns,
int trim, enum do_for_each_ref_flags flags);
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
/*
* A callback function used to instruct merge_ref_iterator how to
* interleave the entries from iter0 and iter1. The function should
* return one of the constants defined in enum iterator_selection. It
* must not advance either of the iterators itself.
*
* The function must be prepared to handle the case that iter0 and/or
* iter1 is NULL, which indicates that the corresponding sub-iterator
* has been exhausted. Its return value must be consistent with the
* current states of the iterators; e.g., it must not return
* ITER_SKIP_1 if iter1 has already been exhausted.
*/
typedef enum iterator_selection ref_iterator_select_fn(
struct ref_iterator *iter0, struct ref_iterator *iter1,
void *cb_data);
/*
* An implementation of ref_iterator_select_fn that merges worktree and common
* refs. Per-worktree refs from the common iterator are ignored, worktree refs
* override common refs. Refs are selected lexicographically.
*/
enum iterator_selection ref_iterator_select(struct ref_iterator *iter_worktree,
struct ref_iterator *iter_common,
void *cb_data);
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
/*
* Iterate over the entries from iter0 and iter1, with the values
* interleaved as directed by the select function. The iterator takes
* ownership of iter0 and iter1 and frees them when the iteration is
* over.
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
*/
struct ref_iterator *merge_ref_iterator_begin(
struct ref_iterator *iter0, struct ref_iterator *iter1,
ref_iterator_select_fn *select, void *cb_data);
/*
* An iterator consisting of the union of the entries from front and
* back. If there are entries common to the two sub-iterators, use the
* one from front. Each iterator must iterate over its entries in
* strcmp() order by refname for this to work.
*
* The new iterator takes ownership of its arguments and frees them
* when the iteration is over. As a convenience to callers, if front
* or back is an empty_ref_iterator, then abort that one immediately
* and return the other iterator directly, without wrapping it.
*/
struct ref_iterator *overlay_ref_iterator_begin(
struct ref_iterator *front, struct ref_iterator *back);
/*
* Wrap iter0, only letting through the references whose names start
* with prefix. If trim is set, set iter->refname to the name of the
* reference with that many characters trimmed off the front;
* otherwise set it to the full refname. The new iterator takes over
* ownership of iter0 and frees it when iteration is over. It makes
* its own copy of prefix.
*
* As an convenience to callers, if prefix is the empty string and
* trim is zero, this function returns iter0 directly, without
* wrapping it.
*/
struct ref_iterator *prefix_ref_iterator_begin(struct ref_iterator *iter0,
const char *prefix,
int trim);
/* Internal implementation of reference iteration: */
/*
* Base class constructor for ref_iterators. Initialize the
* ref_iterator part of iter, setting its vtable pointer as specified.
* This is meant to be called only by the initializers of derived
* classes.
*/
void base_ref_iterator_init(struct ref_iterator *iter,
struct ref_iterator_vtable *vtable);
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
/*
* Base class destructor for ref_iterators. Destroy the ref_iterator
* part of iter and shallow-free the object. This is meant to be
* called only by the destructors of derived classes.
*/
void base_ref_iterator_free(struct ref_iterator *iter);
/* Virtual function declarations for ref_iterators: */
/*
* backend-specific implementation of ref_iterator_advance. For symrefs, the
* function should set REF_ISSYMREF, and it should also dereference the symref
* to provide the OID referent. It should respect do_for_each_ref_flags
* that were passed to refs_ref_iterator_begin().
*/
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
typedef int ref_iterator_advance_fn(struct ref_iterator *ref_iterator);
/*
* Peels the current ref, returning 0 for success or -1 for failure.
*/
refs: introduce an iterator interface Currently, the API for iterating over references is via a family of for_each_ref()-type functions that invoke a callback function for each selected reference. All of these eventually call do_for_each_ref(), which knows how to do one thing: iterate in parallel through two ref_caches, one for loose and one for packed refs, giving loose references precedence over packed refs. This is rather complicated code, and is quite specialized to the files backend. It also requires callers to encapsulate their work into a callback function, which often means that they have to define and use a "cb_data" struct to manage their context. The current design is already bursting at the seams, and will become even more awkward in the upcoming world of multiple reference storage backends: * Per-worktree vs. shared references are currently handled via a kludge in git_path() rather than iterating over each part of the reference namespace separately and merging the results. This kludge will cease to work when we have multiple reference storage backends. * The current scheme is inflexible. What if we sometimes want to bypass the ref_cache, or use it only for packed or only for loose refs? What if we want to store symbolic refs in one type of storage backend and non-symbolic ones in another? In the future, each reference backend will need to define its own way of iterating over references. The crux of the problem with the current design is that it is impossible to compose for_each_ref()-style iterations, because the flow of control is owned by the for_each_ref() function. There is nothing that a caller can do but iterate through all references in a single burst, so there is no way for it to interleave references from multiple backends and present the result to the rest of the world as a single compound backend. This commit introduces a new iteration primitive for references: a ref_iterator. A ref_iterator is a polymorphic object that a reference storage backend can be asked to instantiate. There are three functions that can be applied to a ref_iterator: * ref_iterator_advance(): move to the next reference in the iteration * ref_iterator_abort(): end the iteration before it is exhausted * ref_iterator_peel(): peel the reference currently being looked at Iterating using a ref_iterator leaves the flow of control in the hands of the caller, which means that ref_iterators from multiple sources (e.g., loose and packed refs) can be composed and presented to the world as a single compound ref_iterator. It also means that the backend code for implementing reference iteration will sometimes be more complicated. For example, the cache_ref_iterator (which iterates over a ref_cache) can't use the C stack to recurse; instead, it must manage its own stack internally as explicit data structures. There is also a lot of boilerplate connected with object-oriented programming in C. Eventually, end-user callers will be able to be written in a more natural way—managing their own flow of control rather than having to work via callbacks. Since there will only be a few reference backends but there are many consumers of this API, this is a good tradeoff. More importantly, we gain composability, and especially the possibility of writing interchangeable parts that can work with any ref_iterator. For example, merge_ref_iterator implements a generic way of merging the contents of any two ref_iterators. It is used to merge loose + packed refs as part of the implementation of the files_ref_iterator. But it will also be possible to use it to merge other pairs of reference sources (e.g., per-worktree vs. shared refs). Another example is prefix_ref_iterator, which can be used to trim a prefix off the front of reference names before presenting them to the caller (e.g., "refs/heads/master" -> "master"). In this patch, we introduce the iterator abstraction and many utilities, and implement a reference iterator for the files ref storage backend. (I've written several other obvious utilities, for example a generic way to filter references being iterated over. These will probably be useful in the future. But they are not needed for this patch series, so I am not including them at this time.) In a moment we will rewrite do_for_each_ref() to work via reference iterators (allowing some special-purpose code to be discarded), and do something similar for reflogs. In future patch series, we will expose the ref_iterator abstraction in the public refs API so that callers can use it directly. Implementation note: I tried abstracting this a layer further to allow generic iterators (over arbitrary types of objects) and generic utilities like a generic merge_iterator. But the implementation in C was very cumbersome, involving (in my opinion) too much boilerplate and too much unsafe casting, some of which would have had to be done on the caller side. However, I did put a few iterator-related constants in a top-level header file, iterator.h, as they will be useful in a moment to implement iteration over directory trees and possibly other types of iterators in the future. Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:15 +02:00
typedef int ref_iterator_peel_fn(struct ref_iterator *ref_iterator,
struct object_id *peeled);
/*
* Implementations of this function should free any resources specific
* to the derived class, then call base_ref_iterator_free() to clean
* up and free the ref_iterator object.
*/
typedef int ref_iterator_abort_fn(struct ref_iterator *ref_iterator);
struct ref_iterator_vtable {
ref_iterator_advance_fn *advance;
ref_iterator_peel_fn *peel;
ref_iterator_abort_fn *abort;
};
/*
do_for_each_ref(): reimplement using reference iteration Use the reference iterator interface to implement do_for_each_ref(). Delete a bunch of code supporting the old for_each_ref() implementation. And now that do_for_each_ref() is generic code (it is no longer tied to the files backend), move it to refs.c. The implementation is via a new function, do_for_each_ref_iterator(), which takes a reference iterator as argument and calls a callback function for each of the references in the iterator. This change requires the current_ref performance hack for peel_ref() to be implemented via ref_iterator_peel() rather than peel_entry() because we don't have a ref_entry handy (it is hidden under three layers: file_ref_iterator, merge_ref_iterator, and cache_ref_iterator). So: * do_for_each_ref_iterator() records the active iterator in current_ref_iter while it is running. * peel_ref() checks whether current_ref_iter is pointing at the requested reference. If so, it asks the iterator to peel the reference (which it can do efficiently via its "peel" virtual function). For extra safety, we do the optimization only if the refname *addresses* are the same, not only if the refname *strings* are the same, to forestall possible mixups between refnames that come from different ref_iterators. Please note that this optimization of peel_ref() is only available when iterating via do_for_each_ref_iterator() (including all of the for_each_ref() functions, which call it indirectly). It would be complicated to implement a similar optimization when iterating directly using a reference iterator, because multiple reference iterators can be in use at the same time, with interleaved calls to ref_iterator_advance(). (In fact we do exactly that in merge_ref_iterator.) But that is not necessary. peel_ref() is only called while iterating over references. Callers who iterate using the for_each_ref() functions benefit from the optimization described above. Callers who iterate using reference iterators directly have access to the ref_iterator, so they can call ref_iterator_peel() themselves to get an analogous optimization in a more straightforward manner. If we rewrite all callers to use the reference iteration API, then we can remove the current_ref_iter hack permanently. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-18 06:15:16 +02:00
* current_ref_iter is a performance hack: when iterating over
* references using the for_each_ref*() functions, current_ref_iter is
* set to the reference iterator before calling the callback function.
* If the callback function calls peel_ref(), then peel_ref() first
* checks whether the reference to be peeled is the one referred to by
* the iterator (it usually is) and if so, asks the iterator for the
* peeled version of the reference if it is available. This avoids a
* refname lookup in a common case. current_ref_iter is set to NULL
* when the iteration is over.
*/
extern struct ref_iterator *current_ref_iter;
/*
* The common backend for the for_each_*ref* functions. Call fn for
* each reference in iter. If the iterator itself ever returns
* ITER_ERROR, return -1. If fn ever returns a non-zero value, stop
* the iteration and return that value. Otherwise, return 0. In any
* case, free the iterator when done. This function is basically an
* adapter between the callback style of reference iteration and the
* iterator style.
*/
int do_for_each_repo_ref_iterator(struct repository *r,
struct ref_iterator *iter,
each_repo_ref_fn fn, void *cb_data);
struct ref_store;
/* refs backends */
/* ref_store_init flags */
#define REF_STORE_READ (1 << 0)
#define REF_STORE_WRITE (1 << 1) /* can perform update operations */
#define REF_STORE_ODB (1 << 2) /* has access to object database */
#define REF_STORE_MAIN (1 << 3)
#define REF_STORE_ALL_CAPS (REF_STORE_READ | \
REF_STORE_WRITE | \
REF_STORE_ODB | \
REF_STORE_MAIN)
/*
* Initialize the ref_store for the specified gitdir. These functions
* should call base_ref_store_init() to initialize the shared part of
* the ref_store and to record the ref_store for later lookup.
*/
typedef struct ref_store *ref_store_init_fn(struct repository *repo,
const char *gitdir,
unsigned int flags);
typedef int ref_init_db_fn(struct ref_store *refs,
int flags,
struct strbuf *err);
typedef int ref_transaction_prepare_fn(struct ref_store *refs,
struct ref_transaction *transaction,
struct strbuf *err);
typedef int ref_transaction_finish_fn(struct ref_store *refs,
struct ref_transaction *transaction,
struct strbuf *err);
typedef int ref_transaction_abort_fn(struct ref_store *refs,
struct ref_transaction *transaction,
struct strbuf *err);
typedef int ref_transaction_commit_fn(struct ref_store *refs,
struct ref_transaction *transaction,
struct strbuf *err);
typedef int pack_refs_fn(struct ref_store *ref_store,
struct pack_refs_opts *opts);
typedef int create_symref_fn(struct ref_store *ref_store,
const char *ref_target,
const char *refs_heads_master,
const char *logmsg);
typedef int rename_ref_fn(struct ref_store *ref_store,
const char *oldref, const char *newref,
const char *logmsg);
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 23:19:16 +02:00
typedef int copy_ref_fn(struct ref_store *ref_store,
const char *oldref, const char *newref,
const char *logmsg);
/*
* Iterate over the references in `ref_store` whose names start with
* `prefix`. `prefix` is matched as a literal string, without regard
* for path separators. If prefix is NULL or the empty string, iterate
* over all references in `ref_store`. The output is ordered by
* refname.
*/
typedef struct ref_iterator *ref_iterator_begin_fn(
struct ref_store *ref_store,
const char *prefix, const char **exclude_patterns,
unsigned int flags);
/* reflog functions */
/*
* Iterate over the references in the specified ref_store that have a
* reflog. The refs are iterated over in arbitrary order.
*/
typedef struct ref_iterator *reflog_iterator_begin_fn(
struct ref_store *ref_store);
typedef int for_each_reflog_ent_fn(struct ref_store *ref_store,
const char *refname,
each_reflog_ent_fn fn,
void *cb_data);
typedef int for_each_reflog_ent_reverse_fn(struct ref_store *ref_store,
const char *refname,
each_reflog_ent_fn fn,
void *cb_data);
typedef int reflog_exists_fn(struct ref_store *ref_store, const char *refname);
typedef int create_reflog_fn(struct ref_store *ref_store, const char *refname,
struct strbuf *err);
typedef int delete_reflog_fn(struct ref_store *ref_store, const char *refname);
typedef int reflog_expire_fn(struct ref_store *ref_store,
const char *refname,
unsigned int flags,
reflog_expiry_prepare_fn prepare_fn,
reflog_expiry_should_prune_fn should_prune_fn,
reflog_expiry_cleanup_fn cleanup_fn,
void *policy_cb_data);
/*
* Read a reference from the specified reference store, non-recursively.
* Set type to describe the reference, and:
*
* - If refname is the name of a normal reference, fill in oid
* (leaving referent unchanged).
*
* - If refname is the name of a symbolic reference, write the full
* name of the reference to which it refers (e.g.
* "refs/heads/master") to referent and set the REF_ISSYMREF bit in
* type (leaving oid unchanged). The caller is responsible for
* validating that referent is a valid reference name.
*
* WARNING: refname might be used as part of a filename, so it is
* important from a security standpoint that it be safe in the sense
* of refname_is_safe(). Moreover, for symrefs this function sets
* referent to whatever the repository says, which might not be a
* properly-formatted or even safe reference name. NEITHER INPUT NOR
* OUTPUT REFERENCE NAMES ARE VALIDATED WITHIN THIS FUNCTION.
*
* Return 0 on success, or -1 on failure. If the ref exists but is neither a
* symbolic ref nor an object ID, it is broken. In this case set REF_ISBROKEN in
* type, and return -1 (failure_errno should not be ENOENT)
*
* failure_errno provides errno codes that are interpreted beyond error
* reporting. The following error codes have special meaning:
* * ENOENT: the ref doesn't exist
* * EISDIR: ref name is a directory
* * ENOTDIR: ref prefix is not a directory
*
* Backend-specific flags might be set in type as well, regardless of
* outcome.
*
* It is OK for refname to point into referent. If so:
*
* - if the function succeeds with REF_ISSYMREF, referent will be
* overwritten and the memory formerly pointed to by it might be
* changed or even freed.
*
* - in all other cases, referent will be untouched, and therefore
* refname will still be valid and unchanged.
*/
typedef int read_raw_ref_fn(struct ref_store *ref_store, const char *refname,
struct object_id *oid, struct strbuf *referent,
unsigned int *type, int *failure_errno);
refs: add ability for backends to special-case reading of symbolic refs Reading of symbolic and non-symbolic references is currently treated the same in reference backends: we always call `refs_read_raw_ref()` and then decide based on the returned flags what type it is. This has one downside though: symbolic references may be treated different from normal references in a backend from normal references. The packed-refs backend for example doesn't even know about symbolic references, and as a result it is pointless to even ask it for one. There are cases where we really only care about whether a reference is symbolic or not, but don't care about whether it exists at all or may be a non-symbolic reference. But it is not possible to optimize for this case right now, and as a consequence we will always first check for a loose reference to exist, and if it doesn't, we'll query the packed-refs backend for a known-to-not-be-symbolic reference. This is inefficient and requires us to search all packed references even though we know to not care for the result at all. Introduce a new function `refs_read_symbolic_ref()` which allows us to fix this case. This function will only ever return symbolic references and can thus optimize for the scenario layed out above. By default, if the backend doesn't provide an implementation for it, we just use the old code path and fall back to `read_raw_ref()`. But in case the backend provides its own, more efficient implementation, we will use that one instead. Note that this function is explicitly designed to not distinguish between missing references and non-symbolic references. If it did, we'd be forced to always search the packed-refs backend to see whether the symbolic reference the user asked for really doesn't exist, or if it exists as a non-symbolic reference. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-03-01 10:33:46 +01:00
/*
* Read a symbolic reference from the specified reference store. This function
* is optional: if not implemented by a backend, then `read_raw_ref_fn` is used
* to read the symbolcic reference instead. It is intended to be implemented
* only in case the backend can optimize the reading of symbolic references.
*
* Return 0 on success, or -1 on failure. `referent` will be set to the target
* of the symbolic reference on success. This function explicitly does not
* distinguish between error cases and the reference not being a symbolic
* reference to allow backends to optimize this operation in case symbolic and
* non-symbolic references are treated differently.
*/
typedef int read_symbolic_ref_fn(struct ref_store *ref_store, const char *refname,
struct strbuf *referent);
struct ref_storage_be {
const char *name;
ref_store_init_fn *init;
ref_init_db_fn *init_db;
ref_transaction_prepare_fn *transaction_prepare;
ref_transaction_finish_fn *transaction_finish;
ref_transaction_abort_fn *transaction_abort;
ref_transaction_commit_fn *initial_transaction_commit;
pack_refs_fn *pack_refs;
create_symref_fn *create_symref;
rename_ref_fn *rename_ref;
branch: add a --copy (-c) option to go with --move (-m) Add the ability to --copy a branch and its reflog and configuration, this uses the same underlying machinery as the --move (-m) option except the reflog and configuration is copied instead of being moved. This is useful for e.g. copying a topic branch to a new version, e.g. work to work-2 after submitting the work topic to the list, while preserving all the tracking info and other configuration that goes with the branch, and unlike --move keeping the other already-submitted branch around for reference. Like --move, when the source branch is the currently checked out branch the HEAD is moved to the destination branch. In the case of --move we don't really have a choice (other than remaining on a detached HEAD) and in order to keep the functionality consistent, we are doing it in similar way for --copy too. The most common usage of this feature is expected to be moving to a new topic branch which is a copy of the current one, in that case moving to the target branch is what the user wants, and doesn't unexpectedly behave differently than --move would. One outstanding caveat of this implementation is that: git checkout maint && git checkout master && git branch -c topic && git checkout - Will check out 'maint' instead of 'master'. This is because the @{-N} feature (or its -1 shorthand "-") relies on HEAD reflogs created by the checkout command, so in this case we'll checkout maint instead of master, as the user might expect. What to do about that is left to a future change. Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Sahil Dua <sahildua2305@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-06-18 23:19:16 +02:00
copy_ref_fn *copy_ref;
ref_iterator_begin_fn *iterator_begin;
read_raw_ref_fn *read_raw_ref;
refs: add ability for backends to special-case reading of symbolic refs Reading of symbolic and non-symbolic references is currently treated the same in reference backends: we always call `refs_read_raw_ref()` and then decide based on the returned flags what type it is. This has one downside though: symbolic references may be treated different from normal references in a backend from normal references. The packed-refs backend for example doesn't even know about symbolic references, and as a result it is pointless to even ask it for one. There are cases where we really only care about whether a reference is symbolic or not, but don't care about whether it exists at all or may be a non-symbolic reference. But it is not possible to optimize for this case right now, and as a consequence we will always first check for a loose reference to exist, and if it doesn't, we'll query the packed-refs backend for a known-to-not-be-symbolic reference. This is inefficient and requires us to search all packed references even though we know to not care for the result at all. Introduce a new function `refs_read_symbolic_ref()` which allows us to fix this case. This function will only ever return symbolic references and can thus optimize for the scenario layed out above. By default, if the backend doesn't provide an implementation for it, we just use the old code path and fall back to `read_raw_ref()`. But in case the backend provides its own, more efficient implementation, we will use that one instead. Note that this function is explicitly designed to not distinguish between missing references and non-symbolic references. If it did, we'd be forced to always search the packed-refs backend to see whether the symbolic reference the user asked for really doesn't exist, or if it exists as a non-symbolic reference. Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-03-01 10:33:46 +01:00
read_symbolic_ref_fn *read_symbolic_ref;
reflog_iterator_begin_fn *reflog_iterator_begin;
for_each_reflog_ent_fn *for_each_reflog_ent;
for_each_reflog_ent_reverse_fn *for_each_reflog_ent_reverse;
reflog_exists_fn *reflog_exists;
create_reflog_fn *create_reflog;
delete_reflog_fn *delete_reflog;
reflog_expire_fn *reflog_expire;
};
extern struct ref_storage_be refs_be_files;
refs: introduce reftable backend Due to scalability issues, Shawn Pearce has originally proposed a new "reftable" format more than six years ago [1]. Initially, this new format was implemented in JGit with promising results. Around two years ago, we have then added the "reftable" library to the Git codebase via a4bbd13be3 (Merge branch 'hn/reftable', 2021-12-15). With this we have landed all the low-level code to read and write reftables. Notably missing though was the integration of this low-level code into the Git code base in the form of a new ref backend that ties all of this together. This gap is now finally closed by introducing a new "reftable" backend into the Git codebase. This new backend promises to bring some notable improvements to Git repositories: - It becomes possible to do truly atomic writes where either all refs are committed to disk or none are. This was not possible with the "files" backend because ref updates were split across multiple loose files. - The disk space required to store many refs is reduced, both compared to loose refs and packed-refs. This is enabled both by the reftable format being a binary format, which is more compact, and by prefix compression. - We can ignore filesystem-specific behaviour as ref names are not encoded via paths anymore. This means there is no need to handle case sensitivity on Windows systems or Unicode precomposition on macOS. - There is no need to rewrite the complete refdb anymore every time a ref is being deleted like it was the case for packed-refs. This means that ref deletions are now constant time instead of scaling linearly with the number of refs. - We can ignore file/directory conflicts so that it becomes possible to store both "refs/heads/foo" and "refs/heads/foo/bar". - Due to this property we can retain reflogs for deleted refs. We have previously been deleting reflogs together with their refs to avoid file/directory conflicts, which is not necessary anymore. - We can properly enumerate all refs. With the "files" backend it is not easily possible to distinguish between refs and non-refs because they may live side by side in the gitdir. Not all of these improvements are realized with the current "reftable" backend implementation. At this point, the new backend is supposed to be a drop-in replacement for the "files" backend that is used by basically all Git repositories nowadays. It strives for 1:1 compatibility, which means that a user can expect the same behaviour regardless of whether they use the "reftable" backend or the "files" backend for most of the part. Most notably, this means we artificially limit the capabilities of the "reftable" backend to match the limits of the "files" backend. It is not possible to create refs that would end up with file/directory conflicts, we do not retain reflogs, we perform stricter-than-necessary checks. This is done intentionally due to two main reasons: - It makes it significantly easier to land the "reftable" backend as tests behave the same. It would be tough to argue for each and every single test that doesn't pass with the "reftable" backend. - It ensures compatibility between repositories that use the "files" backend and repositories that use the "reftable" backend. Like this, hosters can migrate their repositories to use the "reftable" backend without causing issues for clients that use the "files" backend in their clones. It is expected that these artificial limitations may eventually go away in the long term. Performance-wise things very much depend on the actual workload. The following benchmarks compare the "files" and "reftable" backends in the current version: - Creating N refs in separate transactions shows that the "files" backend is ~50% faster. This is not surprising given that creating a ref only requires us to create a single loose ref. The "reftable" backend will also perform auto compaction on updates. In real-world workloads we would likely also want to perform pack loose refs, which would likely change the picture. Benchmark 1: update-ref: create refs sequentially (refformat = files, refcount = 1) Time (mean ± σ): 2.1 ms ± 0.3 ms [User: 0.6 ms, System: 1.7 ms] Range (min … max): 1.8 ms … 4.3 ms 133 runs Benchmark 2: update-ref: create refs sequentially (refformat = reftable, refcount = 1) Time (mean ± σ): 2.7 ms ± 0.1 ms [User: 0.6 ms, System: 2.2 ms] Range (min … max): 2.4 ms … 2.9 ms 132 runs Benchmark 3: update-ref: create refs sequentially (refformat = files, refcount = 1000) Time (mean ± σ): 1.975 s ± 0.006 s [User: 0.437 s, System: 1.535 s] Range (min … max): 1.969 s … 1.980 s 3 runs Benchmark 4: update-ref: create refs sequentially (refformat = reftable, refcount = 1000) Time (mean ± σ): 2.611 s ± 0.013 s [User: 0.782 s, System: 1.825 s] Range (min … max): 2.597 s … 2.622 s 3 runs Benchmark 5: update-ref: create refs sequentially (refformat = files, refcount = 100000) Time (mean ± σ): 198.442 s ± 0.241 s [User: 43.051 s, System: 155.250 s] Range (min … max): 198.189 s … 198.670 s 3 runs Benchmark 6: update-ref: create refs sequentially (refformat = reftable, refcount = 100000) Time (mean ± σ): 294.509 s ± 4.269 s [User: 104.046 s, System: 190.326 s] Range (min … max): 290.223 s … 298.761 s 3 runs - Creating N refs in a single transaction shows that the "files" backend is significantly slower once we start to write many refs. The "reftable" backend only needs to update two files, whereas the "files" backend needs to write one file per ref. Benchmark 1: update-ref: create many refs (refformat = files, refcount = 1) Time (mean ± σ): 1.9 ms ± 0.1 ms [User: 0.4 ms, System: 1.4 ms] Range (min … max): 1.8 ms … 2.6 ms 151 runs Benchmark 2: update-ref: create many refs (refformat = reftable, refcount = 1) Time (mean ± σ): 2.5 ms ± 0.1 ms [User: 0.7 ms, System: 1.7 ms] Range (min … max): 2.4 ms … 3.4 ms 148 runs Benchmark 3: update-ref: create many refs (refformat = files, refcount = 1000) Time (mean ± σ): 152.5 ms ± 5.2 ms [User: 19.1 ms, System: 133.1 ms] Range (min … max): 148.5 ms … 167.8 ms 15 runs Benchmark 4: update-ref: create many refs (refformat = reftable, refcount = 1000) Time (mean ± σ): 58.0 ms ± 2.5 ms [User: 28.4 ms, System: 29.4 ms] Range (min … max): 56.3 ms … 72.9 ms 40 runs Benchmark 5: update-ref: create many refs (refformat = files, refcount = 1000000) Time (mean ± σ): 152.752 s ± 0.710 s [User: 20.315 s, System: 131.310 s] Range (min … max): 152.165 s … 153.542 s 3 runs Benchmark 6: update-ref: create many refs (refformat = reftable, refcount = 1000000) Time (mean ± σ): 51.912 s ± 0.127 s [User: 26.483 s, System: 25.424 s] Range (min … max): 51.769 s … 52.012 s 3 runs - Deleting a ref in a fully-packed repository shows that the "files" backend scales with the number of refs. The "reftable" backend has constant-time deletions. Benchmark 1: update-ref: delete ref (refformat = files, refcount = 1) Time (mean ± σ): 1.7 ms ± 0.1 ms [User: 0.4 ms, System: 1.2 ms] Range (min … max): 1.6 ms … 2.1 ms 316 runs Benchmark 2: update-ref: delete ref (refformat = reftable, refcount = 1) Time (mean ± σ): 1.8 ms ± 0.1 ms [User: 0.4 ms, System: 1.3 ms] Range (min … max): 1.7 ms … 2.1 ms 294 runs Benchmark 3: update-ref: delete ref (refformat = files, refcount = 1000) Time (mean ± σ): 2.0 ms ± 0.1 ms [User: 0.5 ms, System: 1.4 ms] Range (min … max): 1.9 ms … 2.5 ms 287 runs Benchmark 4: update-ref: delete ref (refformat = reftable, refcount = 1000) Time (mean ± σ): 1.9 ms ± 0.1 ms [User: 0.5 ms, System: 1.3 ms] Range (min … max): 1.8 ms … 2.1 ms 217 runs Benchmark 5: update-ref: delete ref (refformat = files, refcount = 1000000) Time (mean ± σ): 229.8 ms ± 7.9 ms [User: 182.6 ms, System: 46.8 ms] Range (min … max): 224.6 ms … 245.2 ms 6 runs Benchmark 6: update-ref: delete ref (refformat = reftable, refcount = 1000000) Time (mean ± σ): 2.0 ms ± 0.0 ms [User: 0.6 ms, System: 1.3 ms] Range (min … max): 2.0 ms … 2.1 ms 3 runs - Listing all refs shows no significant advantage for either of the backends. The "files" backend is a bit faster, but not by a significant margin. When repositories are not packed the "reftable" backend outperforms the "files" backend because the "reftable" backend performs auto-compaction. Benchmark 1: show-ref: print all refs (refformat = files, refcount = 1, packed = true) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 2.0 ms 1729 runs Benchmark 2: show-ref: print all refs (refformat = reftable, refcount = 1, packed = true) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 1.8 ms 1816 runs Benchmark 3: show-ref: print all refs (refformat = files, refcount = 1000, packed = true) Time (mean ± σ): 4.3 ms ± 0.1 ms [User: 0.9 ms, System: 3.3 ms] Range (min … max): 4.1 ms … 4.6 ms 645 runs Benchmark 4: show-ref: print all refs (refformat = reftable, refcount = 1000, packed = true) Time (mean ± σ): 4.5 ms ± 0.2 ms [User: 1.0 ms, System: 3.3 ms] Range (min … max): 4.2 ms … 5.9 ms 643 runs Benchmark 5: show-ref: print all refs (refformat = files, refcount = 1000000, packed = true) Time (mean ± σ): 2.537 s ± 0.034 s [User: 0.488 s, System: 2.048 s] Range (min … max): 2.511 s … 2.627 s 10 runs Benchmark 6: show-ref: print all refs (refformat = reftable, refcount = 1000000, packed = true) Time (mean ± σ): 2.712 s ± 0.017 s [User: 0.653 s, System: 2.059 s] Range (min … max): 2.692 s … 2.752 s 10 runs Benchmark 7: show-ref: print all refs (refformat = files, refcount = 1, packed = false) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 1.9 ms 1834 runs Benchmark 8: show-ref: print all refs (refformat = reftable, refcount = 1, packed = false) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.4 ms … 2.0 ms 1840 runs Benchmark 9: show-ref: print all refs (refformat = files, refcount = 1000, packed = false) Time (mean ± σ): 13.8 ms ± 0.2 ms [User: 2.8 ms, System: 10.8 ms] Range (min … max): 13.3 ms … 14.5 ms 208 runs Benchmark 10: show-ref: print all refs (refformat = reftable, refcount = 1000, packed = false) Time (mean ± σ): 4.5 ms ± 0.2 ms [User: 1.2 ms, System: 3.3 ms] Range (min … max): 4.3 ms … 6.2 ms 624 runs Benchmark 11: show-ref: print all refs (refformat = files, refcount = 1000000, packed = false) Time (mean ± σ): 12.127 s ± 0.129 s [User: 2.675 s, System: 9.451 s] Range (min … max): 11.965 s … 12.370 s 10 runs Benchmark 12: show-ref: print all refs (refformat = reftable, refcount = 1000000, packed = false) Time (mean ± σ): 2.799 s ± 0.022 s [User: 0.735 s, System: 2.063 s] Range (min … max): 2.769 s … 2.836 s 10 runs - Printing a single ref shows no real difference between the "files" and "reftable" backends. Benchmark 1: show-ref: print single ref (refformat = files, refcount = 1) Time (mean ± σ): 1.5 ms ± 0.1 ms [User: 0.4 ms, System: 1.0 ms] Range (min … max): 1.4 ms … 1.8 ms 1779 runs Benchmark 2: show-ref: print single ref (refformat = reftable, refcount = 1) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.4 ms … 2.5 ms 1753 runs Benchmark 3: show-ref: print single ref (refformat = files, refcount = 1000) Time (mean ± σ): 1.5 ms ± 0.1 ms [User: 0.3 ms, System: 1.1 ms] Range (min … max): 1.4 ms … 1.9 ms 1840 runs Benchmark 4: show-ref: print single ref (refformat = reftable, refcount = 1000) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 2.0 ms 1831 runs Benchmark 5: show-ref: print single ref (refformat = files, refcount = 1000000) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 2.1 ms 1848 runs Benchmark 6: show-ref: print single ref (refformat = reftable, refcount = 1000000) Time (mean ± σ): 1.6 ms ± 0.1 ms [User: 0.4 ms, System: 1.1 ms] Range (min … max): 1.5 ms … 2.1 ms 1762 runs So overall, performance depends on the usecases. Except for many sequential writes the "reftable" backend is roughly on par or significantly faster than the "files" backend though. Given that the "files" backend has received 18 years of optimizations by now this can be seen as a win. Furthermore, we can expect that the "reftable" backend will grow faster over time when attention turns more towards optimizations. The complete test suite passes, except for those tests explicitly marked to require the REFFILES prerequisite. Some tests in t0610 are marked as failing because they depend on still-in-flight bug fixes. Tests can be run with the new backend by setting the GIT_TEST_DEFAULT_REF_FORMAT environment variable to "reftable". There is a single known conceptual incompatibility with the dumb HTTP transport. As "info/refs" SHOULD NOT contain the HEAD reference, and because the "HEAD" file is not valid anymore, it is impossible for the remote client to figure out the default branch without changing the protocol. This shortcoming needs to be handled in a subsequent patch series. As the reftable library has already been introduced a while ago, this commit message will not go into the details of how exactly the on-disk format works. Please refer to our preexisting technical documentation at Documentation/technical/reftable for this. [1]: https://public-inbox.org/git/CAJo=hJtyof=HRy=2sLP0ng0uZ4=S-DpZ5dR1aF+VHVETKG20OQ@mail.gmail.com/ Original-idea-by: Shawn Pearce <spearce@spearce.org> Based-on-patch-by: Han-Wen Nienhuys <hanwen@google.com> Signed-off-by: Patrick Steinhardt <ps@pks.im> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2024-02-07 08:20:31 +01:00
extern struct ref_storage_be refs_be_reftable;
extern struct ref_storage_be refs_be_packed;
/*
* A representation of the reference store for the main repository or
* a submodule. The ref_store instances for submodules are kept in a
* hash map; see get_submodule_ref_store() for more info.
*/
struct ref_store {
/* The backend describing this ref_store's storage scheme: */
const struct ref_storage_be *be;
struct repository *repo;
/*
* The gitdir that this ref_store applies to. Note that this is not
* necessarily repo->gitdir if the repo has multiple worktrees.
*/
char *gitdir;
};
/*
* Parse contents of a loose ref file. *failure_errno maybe be set to EINVAL for
* invalid contents.
*/
int parse_loose_ref_contents(const char *buf, struct object_id *oid,
struct strbuf *referent, unsigned int *type,
int *failure_errno);
/*
* Fill in the generic part of refs and add it to our collection of
* reference stores.
*/
void base_ref_store_init(struct ref_store *refs, struct repository *repo,
const char *path, const struct ref_storage_be *be);
/*
* Support GIT_TRACE_REFS by optionally wrapping the given ref_store instance.
*/
struct ref_store *maybe_debug_wrap_ref_store(const char *gitdir, struct ref_store *store);
#endif /* REFS_REFS_INTERNAL_H */