On Mon, Apr 05, 2021 at 01:04:15PM +0000, Derrick Stolee via GitGitGadget wrote:
> From: Derrick Stolee <dstolee@xxxxxxxxxxxxx>
>
> The prefetch task previously used the default refspec source plus a
> custom refspec destination to avoid colliding with remote refs:
>
> +refs/heads/*:refs/prefetch/<remote>/*
>
> However, some users customize their refspec to reduce how much data they
> download from specific remotes. This can involve restrictive patterns
> for fetching or negative patterns to avoid downloading some refs.
>
> Modify fetch_remote() to iterate over the remote's refspec list and
> translate that into the appropriate prefetch scenario. Specifically,
> re-parse the raw form of the refspec into a new 'struct refspec' and
> modify the 'dst' member to replace a leading "refs/" substring with
> "refs/prefetch/", or prepend "refs/prefetch/" to 'dst' otherwise.
> Negative refspecs do not have a 'dst' so they can be transferred to the
> 'git fetch' command unmodified.
>
> This prefix change provides the benefit of keeping whatever collisions
> may exist in the custom refspecs, if that is a desirable outcome.
>
> This changes the names of the refs that would be fetched by the default
> refspec. Instead of "refs/prefetch/<remote>/<branch>" they will now go
> to "refs/prefetch/remotes/<remote>/<branch>". While this is a change, it
> is not a seriously breaking one: these refs are intended to be hidden
> and not used.
>
> Update the documentation to be more generic about the destination refs.
> Do not mention custom refpecs explicitly, as that does not need to be
> highlighted in this documentation. The important part of placing refs in
> refs/prefetch remains.
>
> Reported-by: Tom Saeger <tom.saeger@xxxxxxxxxx>
> Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx>
> ---
> Documentation/git-maintenance.txt | 3 +--
> builtin/gc.c | 34 +++++++++++++++++++++++-
> t/t7900-maintenance.sh | 43 ++++++++++++++++++++++++++-----
> 3 files changed, 71 insertions(+), 9 deletions(-)
>
> diff --git a/Documentation/git-maintenance.txt b/Documentation/git-maintenance.txt
> index 80ddd33ceba0..95a24264eb10 100644
> --- a/Documentation/git-maintenance.txt
> +++ b/Documentation/git-maintenance.txt
> @@ -94,8 +94,7 @@ prefetch::
> objects from all registered remotes. For each remote, a `git fetch`
> command is run. The refmap is custom to avoid updating local or remote
> branches (those in `refs/heads` or `refs/remotes`). Instead, the
> - remote refs are stored in `refs/prefetch/<remote>/`. Also, tags are
> - not updated.
> + refs are stored in `refs/prefetch/`. Also, tags are not updated.
> +
> This is done to avoid disrupting the remote-tracking branches. The end users
> expect these refs to stay unmoved unless they initiate a fetch. With prefetch
> diff --git a/builtin/gc.c b/builtin/gc.c
> index fa8128de9ae1..92cb8b4e0bfa 100644
> --- a/builtin/gc.c
> +++ b/builtin/gc.c
> @@ -32,6 +32,7 @@
> #include "remote.h"
> #include "object-store.h"
> #include "exec-cmd.h"
> +#include "refspec.h"
>
> #define FAILED_RUN "failed to run %s"
>
> @@ -877,6 +878,7 @@ static int fetch_remote(struct remote *remote, void *cbdata)
> {
> struct maintenance_run_opts *opts = cbdata;
> struct child_process child = CHILD_PROCESS_INIT;
> + int i;
>
> child.git_cmd = 1;
> strvec_pushl(&child.args, "fetch", remote->name, "--prune", "--no-tags",
> @@ -886,7 +888,37 @@ static int fetch_remote(struct remote *remote, void *cbdata)
> if (opts->quiet)
> strvec_push(&child.args, "--quiet");
>
> - strvec_pushf(&child.args, "+refs/heads/*:refs/prefetch/%s/*", remote->name);
> + for (i = 0; i < remote->fetch.nr; i++) {
> + struct refspec_item replace;
> + struct refspec_item *rsi = &remote->fetch.items[i];
> + struct strbuf new_dst = STRBUF_INIT;
> + size_t ignore_len = 0;
> +
> + if (rsi->negative) {
> + strvec_push(&child.args, remote->fetch.raw[i]);
> + continue;
> + }
> +
> + refspec_item_init(&replace, remote->fetch.raw[i], 1);
> +
> + /*
> + * If a refspec dst starts with "refs/" at the start,
> + * then we will replace "refs/" with "refs/prefetch/".
> + * Otherwise, we will prepend the dst string with
> + * "refs/prefetch/".
> + */
> + if (!strncmp(replace.dst, "refs/", 5))
> + ignore_len = 5;
> +
> + strbuf_addstr(&new_dst, "refs/prefetch/");
> + strbuf_addstr(&new_dst, replace.dst + ignore_len);
> + free(replace.dst);
> + replace.dst = strbuf_detach(&new_dst, NULL);
> +
> + strvec_push(&child.args, refspec_item_format(&replace));
see comment on 3/5, think refspec_item_format is leaking here.
this code looks fine though.
> +
> + refspec_item_clear(&replace);
> + }
>
> return !!run_command(&child);
> }
> diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh
> index fc2315edec11..3366ea188782 100755
> --- a/t/t7900-maintenance.sh
> +++ b/t/t7900-maintenance.sh
> @@ -142,20 +142,51 @@ test_expect_success 'prefetch multiple remotes' '
> test_commit -C clone2 two &&
> GIT_TRACE2_EVENT="$(pwd)/run-prefetch.txt" git maintenance run --task=prefetch 2>/dev/null &&
> fetchargs="--prune --no-tags --no-write-fetch-head --recurse-submodules=no --refmap= --quiet" &&
> - test_subcommand git fetch remote1 $fetchargs +refs/heads/*:refs/prefetch/remote1/* <run-prefetch.txt &&
> - test_subcommand git fetch remote2 $fetchargs +refs/heads/*:refs/prefetch/remote2/* <run-prefetch.txt &&
> + test_subcommand git fetch remote1 $fetchargs +refs/heads/*:refs/prefetch/remotes/remote1/* <run-prefetch.txt &&
> + test_subcommand git fetch remote2 $fetchargs +refs/heads/*:refs/prefetch/remotes/remote2/* <run-prefetch.txt &&
> test_path_is_missing .git/refs/remotes &&
> - git log prefetch/remote1/one &&
> - git log prefetch/remote2/two &&
> + git log prefetch/remotes/remote1/one &&
> + git log prefetch/remotes/remote2/two &&
> git fetch --all &&
> - test_cmp_rev refs/remotes/remote1/one refs/prefetch/remote1/one &&
> - test_cmp_rev refs/remotes/remote2/two refs/prefetch/remote2/two &&
> + test_cmp_rev refs/remotes/remote1/one refs/prefetch/remotes/remote1/one &&
> + test_cmp_rev refs/remotes/remote2/two refs/prefetch/remotes/remote2/two &&
>
> test_cmp_config refs/prefetch/ log.excludedecoration &&
> git log --oneline --decorate --all >log &&
> ! grep "prefetch" log
> '
>
> +test_expect_success 'prefetch custom refspecs' '
> + git -C clone1 branch -f special/fetched HEAD &&
> + git -C clone1 branch -f special/secret/not-fetched HEAD &&
> +
> + # create multiple refspecs for remote1
> + git config --add remote.remote1.fetch +refs/heads/special/fetched:refs/heads/fetched &&
> + git config --add remote.remote1.fetch ^refs/heads/special/secret/not-fetched &&
> +
> + GIT_TRACE2_EVENT="$(pwd)/prefetch-refspec.txt" git maintenance run --task=prefetch 2>/dev/null &&
> +
> + fetchargs="--prune --no-tags --no-write-fetch-head --recurse-submodules=no --refmap= --quiet" &&
> +
> + # skips second refspec because it is not a pattern type
> + rs1="+refs/heads/*:refs/prefetch/remotes/remote1/*" &&
> + rs2="+refs/heads/special/fetched:refs/prefetch/heads/fetched" &&
> + rs3="^refs/heads/special/secret/not-fetched" &&
> +
> + test_subcommand git fetch remote1 $fetchargs $rs1 $rs2 $rs3 <prefetch-refspec.txt &&
> + test_subcommand git fetch remote2 $fetchargs +refs/heads/*:refs/prefetch/remotes/remote2/* <prefetch-refspec.txt &&
> +
> + # first refspec is overridden by second
> + test_must_fail git rev-parse refs/prefetch/special/fetched &&
> + git rev-parse refs/prefetch/heads/fetched &&
> +
> + # possible incorrect places for the non-fetched ref
> + test_must_fail git rev-parse refs/prefetch/remotes/remote1/secret/not-fetched &&
> + test_must_fail git rev-parse refs/prefetch/remotes/remote1/not-fetched &&
> + test_must_fail git rev-parse refs/heads/secret/not-fetched &&
> + test_must_fail git rev-parse refs/heads/not-fetched
> +'
> +
> test_expect_success 'prefetch and existing log.excludeDecoration values' '
> git config --unset-all log.excludeDecoration &&
> git config log.excludeDecoration refs/remotes/remote1/ &&
> --
> gitgitgadget
