On Thu, Mar 06, 2025 at 04:08:35PM +0100, Patrick Steinhardt wrote:
> The `refs_verify_refname_available()` functions checks whether a
> reference update can be committed or whether it would conflict with
> either a prefix or suffix thereof. This function needs to be called once
> per reference that one wants to check, which requires us to redo a
> couple of checks every time the function is called.
>
> Introduce a new function `refs_verify_refnames_available()` that does
> the same, but for a list of references. For now, the new function uses
> the exact same implementation, except that we loop through all refnames
> provided by the caller. This will be tuned in subsequent commits.
>
After reading this patch, I think we may could add more motivation here.
What's the advantage of checking batch refname? From my understanding,
we want to check the group of refnames and if we find one which is not
good we will just return and we don't need to check further more thus
avoiding unnecessary checks which improves speed.
When I read the commit message, I wonder if we will loop through all
refnames, we still need to handle the same number of refnames. So how do
we avoid this?
I think we should make this clear.
> The existing `refs_verify_refname_available()` function is reimplemented
> on top of the new function. As such, the diff is best viewed with the
> `--ignore-space-change option`.
>
> Signed-off-by: Patrick Steinhardt <ps@xxxxxx>
> ---
> refs.c | 169 +++++++++++++++++++++++++++++++++++++----------------------------
> refs.h | 12 +++++
> 2 files changed, 109 insertions(+), 72 deletions(-)
>
> diff --git a/refs.c b/refs.c
> index f4094a326a9..5a9b0f2fa1e 100644
> --- a/refs.c
> +++ b/refs.c
> @@ -2467,19 +2467,15 @@ int ref_transaction_commit(struct ref_transaction *transaction,
> return ret;
> }
>
> -int refs_verify_refname_available(struct ref_store *refs,
> - const char *refname,
> - const struct string_list *extras,
> - const struct string_list *skip,
> - unsigned int initial_transaction,
> - struct strbuf *err)
> +int refs_verify_refnames_available(struct ref_store *refs,
> + const struct string_list *refnames,
> + const struct string_list *extras,
> + const struct string_list *skip,
> + unsigned int initial_transaction,
> + struct strbuf *err)
> {
> - const char *slash;
> - const char *extra_refname;
> struct strbuf dirname = STRBUF_INIT;
> struct strbuf referent = STRBUF_INIT;
> - struct object_id oid;
> - unsigned int type;
> int ret = -1;
>
> /*
> @@ -2489,79 +2485,91 @@ int refs_verify_refname_available(struct ref_store *refs,
>
> assert(err);
>
> - strbuf_grow(&dirname, strlen(refname) + 1);
> - for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) {
> - /*
> - * Just saying "Is a directory" when we e.g. can't
> - * lock some multi-level ref isn't very informative,
> - * the user won't be told *what* is a directory, so
> - * let's not use strerror() below.
> - */
> - int ignore_errno;
> - /* Expand dirname to the new prefix, not including the trailing slash: */
> - strbuf_add(&dirname, refname + dirname.len, slash - refname - dirname.len);
> + for (size_t i = 0; i < refnames->nr; i++) {
Nit: we may just use `for_each_string_list_item` instead of use the raw
"for" loop.
> + const char *refname = refnames->items[i].string;
> + const char *extra_refname;
> + struct object_id oid;
> + unsigned int type;
> + const char *slash;
> +
> + strbuf_reset(&dirname);
> +
> + for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) {
> + /*
> + * Just saying "Is a directory" when we e.g. can't
> + * lock some multi-level ref isn't very informative,
> + * the user won't be told *what* is a directory, so
> + * let's not use strerror() below.
> + */
> + int ignore_errno;
> +
> + /* Expand dirname to the new prefix, not including the trailing slash: */
> + strbuf_add(&dirname, refname + dirname.len, slash - refname - dirname.len);
> +
> + /*
> + * We are still at a leading dir of the refname (e.g.,
> + * "refs/foo"; if there is a reference with that name,
> + * it is a conflict, *unless* it is in skip.
> + */
> + if (skip && string_list_has_string(skip, dirname.buf))
> + continue;
> +
> + if (!initial_transaction &&
> + !refs_read_raw_ref(refs, dirname.buf, &oid, &referent,
> + &type, &ignore_errno)) {
> + strbuf_addf(err, _("'%s' exists; cannot create '%s'"),
> + dirname.buf, refname);
> + goto cleanup;
> + }
> +
> + if (extras && string_list_has_string(extras, dirname.buf)) {
> + strbuf_addf(err, _("cannot process '%s' and '%s' at the same time"),
> + refname, dirname.buf);
> + goto cleanup;
> + }
> + }
>
> /*
> - * We are still at a leading dir of the refname (e.g.,
> - * "refs/foo"; if there is a reference with that name,
> - * it is a conflict, *unless* it is in skip.
> + * We are at the leaf of our refname (e.g., "refs/foo/bar").
> + * There is no point in searching for a reference with that
> + * name, because a refname isn't considered to conflict with
> + * itself. But we still need to check for references whose
> + * names are in the "refs/foo/bar/" namespace, because they
> + * *do* conflict.
> */
> - if (skip && string_list_has_string(skip, dirname.buf))
> - continue;
> + strbuf_addstr(&dirname, refname + dirname.len);
> + strbuf_addch(&dirname, '/');
> +
> + if (!initial_transaction) {
> + struct ref_iterator *iter;
> + int ok;
> +
> + iter = refs_ref_iterator_begin(refs, dirname.buf, NULL, 0,
> + DO_FOR_EACH_INCLUDE_BROKEN);
> + while ((ok = ref_iterator_advance(iter)) == ITER_OK) {
> + if (skip &&
> + string_list_has_string(skip, iter->refname))
> + continue;
> +
> + strbuf_addf(err, _("'%s' exists; cannot create '%s'"),
> + iter->refname, refname);
> + ref_iterator_abort(iter);
> + goto cleanup;
> + }
>
> - if (!initial_transaction &&
> - !refs_read_raw_ref(refs, dirname.buf, &oid, &referent,
> - &type, &ignore_errno)) {
> - strbuf_addf(err, _("'%s' exists; cannot create '%s'"),
> - dirname.buf, refname);
> - goto cleanup;
> + if (ok != ITER_DONE)
> + BUG("error while iterating over references");
> }
>
> - if (extras && string_list_has_string(extras, dirname.buf)) {
> + extra_refname = find_descendant_ref(dirname.buf, extras, skip);
> + if (extra_refname) {
> strbuf_addf(err, _("cannot process '%s' and '%s' at the same time"),
> - refname, dirname.buf);
> + refname, extra_refname);
> goto cleanup;
> }
> }
>
> - /*
> - * We are at the leaf of our refname (e.g., "refs/foo/bar").
> - * There is no point in searching for a reference with that
> - * name, because a refname isn't considered to conflict with
> - * itself. But we still need to check for references whose
> - * names are in the "refs/foo/bar/" namespace, because they
> - * *do* conflict.
> - */
> - strbuf_addstr(&dirname, refname + dirname.len);
> - strbuf_addch(&dirname, '/');
> -
> - if (!initial_transaction) {
> - struct ref_iterator *iter;
> - int ok;
> -
> - iter = refs_ref_iterator_begin(refs, dirname.buf, NULL, 0,
> - DO_FOR_EACH_INCLUDE_BROKEN);
> - while ((ok = ref_iterator_advance(iter)) == ITER_OK) {
> - if (skip &&
> - string_list_has_string(skip, iter->refname))
> - continue;
> -
> - strbuf_addf(err, _("'%s' exists; cannot create '%s'"),
> - iter->refname, refname);
> - ref_iterator_abort(iter);
> - goto cleanup;
> - }
> -
> - if (ok != ITER_DONE)
> - BUG("error while iterating over references");
> - }
> -
> - extra_refname = find_descendant_ref(dirname.buf, extras, skip);
> - if (extra_refname)
> - strbuf_addf(err, _("cannot process '%s' and '%s' at the same time"),
> - refname, extra_refname);
> - else
> - ret = 0;
> + ret = 0;
>
> cleanup:
> strbuf_release(&referent);
> @@ -2569,6 +2577,23 @@ int refs_verify_refname_available(struct ref_store *refs,
> return ret;
> }
>
> +int refs_verify_refname_available(struct ref_store *refs,
> + const char *refname,
> + const struct string_list *extras,
> + const struct string_list *skip,
> + unsigned int initial_transaction,
> + struct strbuf *err)
> +{
> + struct string_list_item item = { .string = (char *) refname };
> + struct string_list refnames = {
> + .items = &item,
> + .nr = 1,
> + };
> +
> + return refs_verify_refnames_available(refs, &refnames, extras, skip,
> + initial_transaction, err);
> +}
> +
> struct do_for_each_reflog_help {
> each_reflog_fn *fn;
> void *cb_data;
> diff --git a/refs.h b/refs.h
> index a0cdd99250e..185aed5a461 100644
> --- a/refs.h
> +++ b/refs.h
> @@ -124,6 +124,18 @@ int refs_verify_refname_available(struct ref_store *refs,
> unsigned int initial_transaction,
> struct strbuf *err);
>
> +/*
> + * Same as `refs_verify_refname_available()`, but checking for a list of
> + * refnames instead of only a single item. This is more efficient in the case
> + * where one needs to check multiple refnames.
> + */
Should we talk about more about why this is more efficient?
> +int refs_verify_refnames_available(struct ref_store *refs,
> + const struct string_list *refnames,
> + const struct string_list *extras,
> + const struct string_list *skip,
> + unsigned int initial_transaction,
> + struct strbuf *err);
> +
> int refs_ref_exists(struct ref_store *refs, const char *refname);
>
> int should_autocreate_reflog(enum log_refs_config log_all_ref_updates,
>
> --
> 2.49.0.rc0.416.g627208d89d.dirty
