From 709dfa69908c9448db91a9bcc96941549be6421e Mon Sep 17 00:00:00 2001 From: Jeff King Date: Mon, 1 Jul 2019 09:17:40 -0400 Subject: [PATCH 1/2] object-store.h: move for_each_alternate_ref() from transport.h There's nothing inherently transport-related about enumerating the alternate ref tips. The code has lived in transport.[ch] because the only use so far had been advertising available tips during transport. But it could be used for more, and a future patch will teach rev-list to access these refs. Let's move it alongside the other alt-odb code, declaring it in object-store.h with the implementation in sha1-file.c. This lets us drop the inclusion of transport.h from receive-pack, which perhaps shows how it was misplaced (though receive-pack is about transporting objects, transport.h is mostly about the client side). Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/receive-pack.c | 1 - object-store.h | 2 + sha1-file.c | 97 ++++++++++++++++++++++++++++++++++++++++++ transport.c | 97 ------------------------------------------ transport.h | 2 - 5 files changed, 99 insertions(+), 100 deletions(-) diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 29f165d8bd..4ab6dc1037 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -12,7 +12,6 @@ #include "object.h" #include "remote.h" #include "connect.h" -#include "transport.h" #include "string-list.h" #include "sha1-array.h" #include "connected.h" diff --git a/object-store.h b/object-store.h index 272e01e452..74d6860a9f 100644 --- a/object-store.h +++ b/object-store.h @@ -33,6 +33,8 @@ void prepare_alt_odb(struct repository *r); char *compute_alternate_path(const char *path, struct strbuf *err); typedef int alt_odb_fn(struct object_directory *, void *); int foreach_alt_odb(alt_odb_fn, void*); +typedef void alternate_ref_fn(const struct object_id *oid, void *); +void for_each_alternate_ref(alternate_ref_fn, void *); /* * Add the directory to the on-disk alternates file; the new entry will also diff --git a/sha1-file.c b/sha1-file.c index ed5c50dac4..ccd5bf30bd 100644 --- a/sha1-file.c +++ b/sha1-file.c @@ -743,6 +743,103 @@ out: return ref_git; } +static void fill_alternate_refs_command(struct child_process *cmd, + const char *repo_path) +{ + const char *value; + + if (!git_config_get_value("core.alternateRefsCommand", &value)) { + cmd->use_shell = 1; + + argv_array_push(&cmd->args, value); + argv_array_push(&cmd->args, repo_path); + } else { + cmd->git_cmd = 1; + + argv_array_pushf(&cmd->args, "--git-dir=%s", repo_path); + argv_array_push(&cmd->args, "for-each-ref"); + argv_array_push(&cmd->args, "--format=%(objectname)"); + + if (!git_config_get_value("core.alternateRefsPrefixes", &value)) { + argv_array_push(&cmd->args, "--"); + argv_array_split(&cmd->args, value); + } + } + + cmd->env = local_repo_env; + cmd->out = -1; +} + +static void read_alternate_refs(const char *path, + alternate_ref_fn *cb, + void *data) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct strbuf line = STRBUF_INIT; + FILE *fh; + + fill_alternate_refs_command(&cmd, path); + + if (start_command(&cmd)) + return; + + fh = xfdopen(cmd.out, "r"); + while (strbuf_getline_lf(&line, fh) != EOF) { + struct object_id oid; + const char *p; + + if (parse_oid_hex(line.buf, &oid, &p) || *p) { + warning(_("invalid line while parsing alternate refs: %s"), + line.buf); + break; + } + + cb(&oid, data); + } + + fclose(fh); + finish_command(&cmd); +} + +struct alternate_refs_data { + alternate_ref_fn *fn; + void *data; +}; + +static int refs_from_alternate_cb(struct object_directory *e, + void *data) +{ + struct strbuf path = STRBUF_INIT; + size_t base_len; + struct alternate_refs_data *cb = data; + + if (!strbuf_realpath(&path, e->path, 0)) + goto out; + if (!strbuf_strip_suffix(&path, "/objects")) + goto out; + base_len = path.len; + + /* Is this a git repository with refs? */ + strbuf_addstr(&path, "/refs"); + if (!is_directory(path.buf)) + goto out; + strbuf_setlen(&path, base_len); + + read_alternate_refs(path.buf, cb->fn, cb->data); + +out: + strbuf_release(&path); + return 0; +} + +void for_each_alternate_ref(alternate_ref_fn fn, void *data) +{ + struct alternate_refs_data cb; + cb.fn = fn; + cb.data = data; + foreach_alt_odb(refs_from_alternate_cb, &cb); +} + int foreach_alt_odb(alt_odb_fn fn, void *cb) { struct object_directory *ent; diff --git a/transport.c b/transport.c index f1fcd2c4b0..2def5a0c35 100644 --- a/transport.c +++ b/transport.c @@ -1380,100 +1380,3 @@ char *transport_anonymize_url(const char *url) literal_copy: return xstrdup(url); } - -static void fill_alternate_refs_command(struct child_process *cmd, - const char *repo_path) -{ - const char *value; - - if (!git_config_get_value("core.alternateRefsCommand", &value)) { - cmd->use_shell = 1; - - argv_array_push(&cmd->args, value); - argv_array_push(&cmd->args, repo_path); - } else { - cmd->git_cmd = 1; - - argv_array_pushf(&cmd->args, "--git-dir=%s", repo_path); - argv_array_push(&cmd->args, "for-each-ref"); - argv_array_push(&cmd->args, "--format=%(objectname)"); - - if (!git_config_get_value("core.alternateRefsPrefixes", &value)) { - argv_array_push(&cmd->args, "--"); - argv_array_split(&cmd->args, value); - } - } - - cmd->env = local_repo_env; - cmd->out = -1; -} - -static void read_alternate_refs(const char *path, - alternate_ref_fn *cb, - void *data) -{ - struct child_process cmd = CHILD_PROCESS_INIT; - struct strbuf line = STRBUF_INIT; - FILE *fh; - - fill_alternate_refs_command(&cmd, path); - - if (start_command(&cmd)) - return; - - fh = xfdopen(cmd.out, "r"); - while (strbuf_getline_lf(&line, fh) != EOF) { - struct object_id oid; - const char *p; - - if (parse_oid_hex(line.buf, &oid, &p) || *p) { - warning(_("invalid line while parsing alternate refs: %s"), - line.buf); - break; - } - - cb(&oid, data); - } - - fclose(fh); - finish_command(&cmd); -} - -struct alternate_refs_data { - alternate_ref_fn *fn; - void *data; -}; - -static int refs_from_alternate_cb(struct object_directory *e, - void *data) -{ - struct strbuf path = STRBUF_INIT; - size_t base_len; - struct alternate_refs_data *cb = data; - - if (!strbuf_realpath(&path, e->path, 0)) - goto out; - if (!strbuf_strip_suffix(&path, "/objects")) - goto out; - base_len = path.len; - - /* Is this a git repository with refs? */ - strbuf_addstr(&path, "/refs"); - if (!is_directory(path.buf)) - goto out; - strbuf_setlen(&path, base_len); - - read_alternate_refs(path.buf, cb->fn, cb->data); - -out: - strbuf_release(&path); - return 0; -} - -void for_each_alternate_ref(alternate_ref_fn fn, void *data) -{ - struct alternate_refs_data cb; - cb.fn = fn; - cb.data = data; - foreach_alt_odb(refs_from_alternate_cb, &cb); -} diff --git a/transport.h b/transport.h index 06e06d3d89..0b5f7806f6 100644 --- a/transport.h +++ b/transport.h @@ -262,6 +262,4 @@ int transport_refs_pushed(struct ref *ref); void transport_print_push_status(const char *dest, struct ref *refs, int verbose, int porcelain, unsigned int *reject_reasons); -typedef void alternate_ref_fn(const struct object_id *oid, void *); -void for_each_alternate_ref(alternate_ref_fn, void *); #endif From 39b44ba771a315602fd1fdca2e12dfc31ef9c613 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Mon, 1 Jul 2019 09:18:15 -0400 Subject: [PATCH 2/2] check_everything_connected: assume alternate ref tips are valid When we receive a remote ref update to sha1 "X", we want to check that we have all of the objects needed by "X". We can assume that our repository is not currently corrupted, and therefore if we have a ref pointing at "Y", we have all of its objects. So we can stop our traversal from "X" as soon as we hit "Y". If we make the same non-corruption assumption about any repositories we use to store alternates, then we can also use their ref tips to shorten the traversal. This is especially useful when cloning with "--reference", as we otherwise do not have any local refs to check against, and have to traverse the whole history, even though the other side may have sent us few or no objects. Here are results for the included perf test (which shows off more or less the maximal savings, getting one new commit and sharing the whole history): Test HEAD^ HEAD -------------------------------------------------------------------- [on git.git] 5600.3: clone --reference 2.94(2.86+0.08) 0.09(0.08+0.01) -96.9% [on linux.git] 5600.3: clone --reference 45.74(45.34+0.41) 0.36(0.30+0.08) -99.2% Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- Documentation/rev-list-options.txt | 8 ++++ connected.c | 1 + revision.c | 29 +++++++++++++++ t/perf/p5600-clone-reference.sh | 27 ++++++++++++++ t/t5618-alternate-refs.sh | 60 ++++++++++++++++++++++++++++++ 5 files changed, 125 insertions(+) create mode 100755 t/perf/p5600-clone-reference.sh create mode 100755 t/t5618-alternate-refs.sh diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt index 71a1fcc093..90a2c027ea 100644 --- a/Documentation/rev-list-options.txt +++ b/Documentation/rev-list-options.txt @@ -182,6 +182,14 @@ explicitly. Pretend as if all objects mentioned by reflogs are listed on the command line as ``. +--alternate-refs:: + Pretend as if all objects mentioned as ref tips of alternate + repositories were listed on the command line. An alternate + repository is any repository whose object directory is specified + in `objects/info/alternates`. The set of included objects may + be modified by `core.alternateRefsCommand`, etc. See + linkgit:git-config[1]. + --single-worktree:: By default, all working trees will be examined by the following options when there are more than one (see diff --git a/connected.c b/connected.c index 1ab481fed6..cd9b324afa 100644 --- a/connected.c +++ b/connected.c @@ -80,6 +80,7 @@ int check_connected(oid_iterate_fn fn, void *cb_data, argv_array_push(&rev_list.args, "--all"); } argv_array_push(&rev_list.args, "--quiet"); + argv_array_push(&rev_list.args, "--alternate-refs"); if (opt->progress) argv_array_pushf(&rev_list.args, "--progress=%s", _("Checking connectivity")); diff --git a/revision.c b/revision.c index d4aaf0ef25..0d1a30a7d7 100644 --- a/revision.c +++ b/revision.c @@ -1552,6 +1552,32 @@ void add_index_objects_to_pending(struct rev_info *revs, unsigned int flags) free_worktrees(worktrees); } +struct add_alternate_refs_data { + struct rev_info *revs; + unsigned int flags; +}; + +static void add_one_alternate_ref(const struct object_id *oid, + void *vdata) +{ + const char *name = ".alternate"; + struct add_alternate_refs_data *data = vdata; + struct object *obj; + + obj = get_reference(data->revs, name, oid, data->flags); + add_rev_cmdline(data->revs, obj, name, REV_CMD_REV, data->flags); + add_pending_object(data->revs, obj, name); +} + +static void add_alternate_refs_to_pending(struct rev_info *revs, + unsigned int flags) +{ + struct add_alternate_refs_data data; + data.revs = revs; + data.flags = flags; + for_each_alternate_ref(add_one_alternate_ref, &data); +} + static int add_parents_only(struct rev_info *revs, const char *arg_, int flags, int exclude_parent) { @@ -1954,6 +1980,7 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg !strcmp(arg, "--no-walk") || !strcmp(arg, "--do-walk") || !strcmp(arg, "--bisect") || starts_with(arg, "--glob=") || !strcmp(arg, "--indexed-objects") || + !strcmp(arg, "--alternate-refs") || starts_with(arg, "--exclude=") || starts_with(arg, "--branches=") || starts_with(arg, "--tags=") || starts_with(arg, "--remotes=") || starts_with(arg, "--no-walk=")) @@ -2440,6 +2467,8 @@ static int handle_revision_pseudo_opt(const char *submodule, add_reflogs_to_pending(revs, *flags); } else if (!strcmp(arg, "--indexed-objects")) { add_index_objects_to_pending(revs, *flags); + } else if (!strcmp(arg, "--alternate-refs")) { + add_alternate_refs_to_pending(revs, *flags); } else if (!strcmp(arg, "--not")) { *flags ^= UNINTERESTING | BOTTOM; } else if (!strcmp(arg, "--no-walk")) { diff --git a/t/perf/p5600-clone-reference.sh b/t/perf/p5600-clone-reference.sh new file mode 100755 index 0000000000..68fed66347 --- /dev/null +++ b/t/perf/p5600-clone-reference.sh @@ -0,0 +1,27 @@ +#!/bin/sh + +test_description='speed of clone --reference' +. ./perf-lib.sh + +test_perf_default_repo + +test_expect_success 'create shareable repository' ' + git clone --bare . shared.git +' + +test_expect_success 'advance base repository' ' + # Do not use test_commit here; its test_tick will + # use some ancient hard-coded date. The resulting clock + # skew will cause pack-objects to traverse in a very + # sub-optimal order, skewing the results. + echo content >new-file-that-does-not-exist && + git add new-file-that-does-not-exist && + git commit -m "new commit" +' + +test_perf 'clone --reference' ' + rm -rf dst.git && + git clone --no-local --bare --reference shared.git . dst.git +' + +test_done diff --git a/t/t5618-alternate-refs.sh b/t/t5618-alternate-refs.sh new file mode 100755 index 0000000000..3353216f09 --- /dev/null +++ b/t/t5618-alternate-refs.sh @@ -0,0 +1,60 @@ +#!/bin/sh + +test_description='test handling of --alternate-refs traversal' +. ./test-lib.sh + +# Avoid test_commit because we want a specific and known set of refs: +# +# base -- one +# \ \ +# two -- merged +# +# where "one" and "two" are on separate refs, and "merged" is available only in +# the dependent child repository. +test_expect_success 'set up local refs' ' + git checkout -b one && + test_tick && + git commit --allow-empty -m base && + test_tick && + git commit --allow-empty -m one && + git checkout -b two HEAD^ && + test_tick && + git commit --allow-empty -m two +' + +# We'll enter the child repository after it's set up since that's where +# all of the subsequent tests will want to run (and it's easy to forget a +# "-C child" and get nonsense results). +test_expect_success 'set up shared clone' ' + git clone -s . child && + cd child && + git merge origin/one +' + +test_expect_success 'rev-list --alternate-refs' ' + git rev-list --remotes=origin >expect && + git rev-list --alternate-refs >actual && + test_cmp expect actual +' + +test_expect_success 'rev-list --not --alternate-refs' ' + git rev-parse HEAD >expect && + git rev-list HEAD --not --alternate-refs >actual && + test_cmp expect actual +' + +test_expect_success 'limiting with alternateRefsPrefixes' ' + test_config core.alternateRefsPrefixes refs/heads/one && + git rev-list origin/one >expect && + git rev-list --alternate-refs >actual && + test_cmp expect actual +' + +test_expect_success 'log --source shows .alternate marker' ' + git log --oneline --source --remotes=origin >expect.orig && + sed "s/origin.* /.alternate /" expect && + git log --oneline --source --alternate-refs >actual && + test_cmp expect actual +' + +test_done