upload-pack: add tracing for fetches

Information on how users are accessing hosted repositories can be
helpful to server operators. For example, being able to broadly
differentiate between fetches and initial clones; the use of shallow
repository features; or partial clone filters.

a29263c (fetch-pack: add tracing for negotiation rounds, 2022-08-02)
added some information on have counts to fetch-pack itself to help
diagnose negotiation; but from a git-upload-pack (server) perspective,
there's no means of accessing such information without using
GIT_TRACE_PACKET to examine the protocol packets.

Improve this by emitting a Trace2 JSON event from upload-pack with
summary information on the contents of a fetch request.

* haves, wants, and want-ref counts can help determine (broadly) between
  fetches and clones, and the use of single-branch, etc.
* shallow clone depth, tip counts, and deepening options.
* any partial clone filter type.

Signed-off-by: Robert Coup <robert@coup.net.nz>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh
index d18f2823d86e8b94c5331b1087f962469fc91f2c..bb15ac34f777641bacda13bf2b19874ca75b67e6 100755 (executable)
--- a/t/t5500-fetch-pack.sh
+++ b/t/t5500-fetch-pack.sh
@@ -132,13 +132,18 @@ test_expect_success 'single branch object count' '
 '
 
 test_expect_success 'single given branch clone' '
-       git clone --single-branch --branch A "file://$(pwd)/." branch-a &&
-       test_must_fail git --git-dir=branch-a/.git rev-parse origin/B
+       GIT_TRACE2_EVENT="$(pwd)/branch-a/trace2_event" \
+               git clone --single-branch --branch A "file://$(pwd)/." branch-a &&
+       test_must_fail git --git-dir=branch-a/.git rev-parse origin/B &&
+       grep \"fetch-info\".*\"haves\":0 branch-a/trace2_event &&
+       grep \"fetch-info\".*\"wants\":1 branch-a/trace2_event
 '
 
 test_expect_success 'clone shallow depth 1' '
-       git clone --no-single-branch --depth 1 "file://$(pwd)/." shallow0 &&
-       test "$(git --git-dir=shallow0/.git rev-list --count HEAD)" = 1
+       GIT_TRACE2_EVENT="$(pwd)/shallow0/trace2_event" \
+               git clone --no-single-branch --depth 1 "file://$(pwd)/." shallow0 &&
+       test "$(git --git-dir=shallow0/.git rev-list --count HEAD)" = 1 &&
+       grep \"fetch-info\".*\"depth\":1 shallow0/trace2_event
 '
 
 test_expect_success 'clone shallow depth 1 with fsck' '
@@ -235,7 +240,10 @@ test_expect_success 'add two more (part 2)' '
 test_expect_success 'deepening pull in shallow repo' '
        (
                cd shallow &&
-               git pull --depth 4 .. B
+               GIT_TRACE2_EVENT="$(pwd)/trace2_event" \
+                       git pull --depth 4 .. B &&
+               grep \"fetch-info\".*\"depth\":4 trace2_event &&
+               grep \"fetch-info\".*\"shallows\":2 trace2_event
        )
 '
 
@@ -306,9 +314,12 @@ test_expect_success 'fetch --depth --no-shallow' '
 test_expect_success 'turn shallow to complete repository' '
        (
                cd shallow &&
-               git fetch --unshallow &&
+               GIT_TRACE2_EVENT="$(pwd)/trace2_event" \
+                       git fetch --unshallow &&
                ! test -f .git/shallow &&
-               git fsck --full
+               git fsck --full &&
+               grep \"fetch-info\".*\"shallows\":2 trace2_event &&
+               grep \"fetch-info\".*\"depth\":2147483647 trace2_event
        )
 '
 
@@ -826,13 +837,15 @@ test_expect_success 'clone shallow since ...' '
 '
 
 test_expect_success 'fetch shallow since ...' '
-       git -C shallow11 fetch --shallow-since "200000000 +0700" origin &&
+       GIT_TRACE2_EVENT=$(pwd)/shallow11/trace2_event \
+               git -C shallow11 fetch --shallow-since "200000000 +0700" origin &&
        git -C shallow11 log --pretty=tformat:%s origin/main >actual &&
        cat >expected <<-\EOF &&
        three
        two
        EOF
-       test_cmp expected actual
+       test_cmp expected actual &&
+       grep \"fetch-info\".*\"deepen-since\":true shallow11/trace2_event
 '
 
 test_expect_success 'clone shallow since selects no commits' '
@@ -987,13 +1000,16 @@ test_expect_success 'filtering by size' '
        test_config -C server uploadpack.allowfilter 1 &&
 
        test_create_repo client &&
-       git -C client fetch-pack --filter=blob:limit=0 ../server HEAD &&
+       GIT_TRACE2_EVENT=$(pwd)/client/trace2_event \
+               git -C client fetch-pack --filter=blob:limit=0 ../server HEAD &&
 
        # Ensure that object is not inadvertently fetched
        commit=$(git -C server rev-parse HEAD) &&
        blob=$(git hash-object server/one.t) &&
        git -C client rev-list --objects --missing=allow-any "$commit" >oids &&
-       ! grep "$blob" oids
+       ! grep "$blob" oids &&
+
+       grep \"fetch-info\".*\"filter\":\"blob:limit\" client/trace2_event
 '
 
 test_expect_success 'filtering by size has no effect if support for it is not advertised' '

diff --git a/upload-pack.c b/upload-pack.c
index 83f3d2651ab3feee758178f86394627ffe4f76b0..ea234ab6a4522489c7a70a3cfa6d6449c46013c5 100644 (file)
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -33,6 +33,7 @@
 #include "commit-reach.h"
 #include "shallow.h"
 #include "write-or-die.h"
+#include "json-writer.h"
 
 /* Remember to update object flag allocation in object.h */
 #define THEY_HAVE      (1u << 11)
@@ -1552,6 +1553,30 @@ static int parse_have(const char *line, struct oid_array *haves)
        return 0;
 }
 
+static void trace2_fetch_info(struct upload_pack_data *data)
+{
+       struct json_writer jw = JSON_WRITER_INIT;
+
+       jw_object_begin(&jw, 0);
+       jw_object_intmax(&jw, "haves", data->haves.nr);
+       jw_object_intmax(&jw, "wants", data->want_obj.nr);
+       jw_object_intmax(&jw, "want-refs", data->wanted_refs.nr);
+       jw_object_intmax(&jw, "depth", data->depth);
+       jw_object_intmax(&jw, "shallows", data->shallows.nr);
+       jw_object_bool(&jw, "deepen-since", data->deepen_since);
+       jw_object_intmax(&jw, "deepen-not", data->deepen_not.nr);
+       jw_object_bool(&jw, "deepen-relative", data->deepen_relative);
+       if (data->filter_options.choice)
+               jw_object_string(&jw, "filter", list_object_filter_config_name(data->filter_options.choice));
+       else
+               jw_object_null(&jw, "filter");
+       jw_end(&jw);
+
+       trace2_data_json("upload-pack", the_repository, "fetch-info", &jw);
+
+       jw_release(&jw);
+}
+
 static void process_args(struct packet_reader *request,
                         struct upload_pack_data *data)
 {
@@ -1640,6 +1665,9 @@ static void process_args(struct packet_reader *request,
 
        if (request->status != PACKET_READ_FLUSH)
                die(_("expected flush after fetch arguments"));
+
+       if (trace2_is_enabled())
+               trace2_fetch_info(data);
 }
 
 static int process_haves(struct upload_pack_data *data, struct oid_array *common)