From 809e0327f579267ea78a1b2f727d3b63c1f5d044 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 18 Sep 2020 09:27:27 -0400 Subject: builtin/commit-graph.c: introduce '--max-new-filters=' Introduce a command-line flag to specify the maximum number of new Bloom filters that a 'git commit-graph write' is willing to compute from scratch. Prior to this patch, a commit-graph write with '--changed-paths' would compute Bloom filters for all selected commits which haven't already been computed (i.e., by a previous commit-graph write with '--split' such that a roll-up or replacement is performed). This behavior can cause prohibitively-long commit-graph writes for a variety of reasons: * There may be lots of filters whose diffs take a long time to generate (for example, they have close to the maximum number of changes, diffing itself takes a long time, etc). * Old-style commit-graphs (which encode filters with too many entries as not having been computed at all) cause us to waste time recomputing filters that appear to have not been computed only to discover that they are too-large. This can make the upper-bound of the time it takes for 'git commit-graph write --changed-paths' to be rather unpredictable. To make this command behave more predictably, introduce '--max-new-filters=' to allow computing at most '' Bloom filters from scratch. This lets "computing" already-known filters proceed quickly, while bounding the number of slow tasks that Git is willing to do. Helped-by: Junio C Hamano Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- t/t4216-log-bloom.sh | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 't') diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh index ec9845c9be..48ab1b16a6 100755 --- a/t/t4216-log-bloom.sh +++ b/t/t4216-log-bloom.sh @@ -305,4 +305,74 @@ test_expect_success 'correctly report commits with no changed paths' ' ) ' +test_expect_success 'Bloom generation is limited by --max-new-filters' ' + ( + cd limits && + test_commit c2 filter && + test_commit c3 filter && + test_commit c4 no-filter && + + rm -f trace.event && + GIT_TRACE2_EVENT="$(pwd)/trace.event" \ + git commit-graph write --reachable --split=replace \ + --changed-paths --max-new-filters=2 && + + test_filter_computed 2 trace.event && + test_filter_not_computed 3 trace.event && + test_filter_trunc_empty 0 trace.event && + test_filter_trunc_large 0 trace.event + ) +' + +test_expect_success 'Bloom generation backfills previously-skipped filters' ' + ( + cd limits && + + rm -f trace.event && + GIT_TRACE2_EVENT="$(pwd)/trace.event" \ + git commit-graph write --reachable --changed-paths \ + --split=replace --max-new-filters=1 && + test_filter_computed 1 trace.event && + test_filter_not_computed 4 trace.event && + test_filter_trunc_empty 0 trace.event && + test_filter_trunc_large 0 trace.event + ) +' + +test_expect_success 'Bloom generation backfills empty commits' ' + git init empty && + test_when_finished "rm -fr empty" && + ( + cd empty && + for i in $(test_seq 1 6) + do + git commit --allow-empty -m "$i" + done && + + # Generate Bloom filters for empty commits 1-6, two at a time. + for i in $(test_seq 1 3) + do + rm -f trace.event && + GIT_TRACE2_EVENT="$(pwd)/trace.event" \ + git commit-graph write --reachable \ + --changed-paths --max-new-filters=2 && + test_filter_computed 2 trace.event && + test_filter_not_computed 4 trace.event && + test_filter_trunc_empty 2 trace.event && + test_filter_trunc_large 0 trace.event + done && + + # Finally, make sure that once all commits have filters, that + # none are subsequently recomputed. + rm -f trace.event && + GIT_TRACE2_EVENT="$(pwd)/trace.event" \ + git commit-graph write --reachable \ + --changed-paths --max-new-filters=2 && + test_filter_computed 0 trace.event && + test_filter_not_computed 6 trace.event && + test_filter_trunc_empty 0 trace.event && + test_filter_trunc_large 0 trace.event + ) +' + test_done -- cgit v1.2.3