Web lists-archives.com

[PATCH v2 00/11] Add 'git multi-pack-index verify' command




The multi-pack-index file provides faster lookups in repos with many
packfiles by duplicating the information from multiple pack-indexes into a
single file. This series allows us to verify a multi-pack-index using 'git
multi-pack-index verify' and 'git fsck' (when core.multiPackIndex is true).

The pattern for the tests is similar to that found in t5318-commit-graph.sh.

During testing, I found a bug in how we check for the size of off_t (we are
not actually checking off_t, but instead uint32_t). See "multi-pack-index:
fix 32-bit vs 64-bit size check".

Thanks to Ævar [1], I added a commit that provides progress updates when
checking object offsets.

Based on ds/multi-pack-index

[1] 
https://public-inbox.org/git/20180904202729.13900-1-avarab@xxxxxxxxx/T/#u

Derrick Stolee (11):
  multi-pack-index: add 'verify' verb
  multi-pack-index: verify bad header
  multi-pack-index: verify corrupt chunk lookup table
  multi-pack-index: verify packname order
  multi-pack-index: verify missing pack
  multi-pack-index: verify oid fanout order
  multi-pack-index: verify oid lookup order
  multi-pack-index: fix 32-bit vs 64-bit size check
  multi-pack-index: verify object offsets
  multi-pack-index: report progress during 'verify'
  fsck: verify multi-pack-index

 Documentation/git-multi-pack-index.txt |  10 ++
 builtin/fsck.c                         |  18 ++++
 builtin/multi-pack-index.c             |   4 +-
 midx.c                                 | 113 ++++++++++++++++----
 midx.h                                 |   1 +
 t/t5319-multi-pack-index.sh            | 136 ++++++++++++++++++++++++-
 6 files changed, 262 insertions(+), 20 deletions(-)


base-commit: 6a22d521260f86dff8fe6f23ab329cebb62ba4f0
Published-As: https://github.com/gitgitgadget/git/releases/tags/pr-34%2Fderrickstolee%2Fmidx%2Fverify-v2
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-34/derrickstolee/midx/verify-v2
Pull-Request: https://github.com/gitgitgadget/git/pull/34

Range-diff vs v1:

  1:  8dc38afe2b !  1:  d8ffd84d67 multi-pack-index: add 'verify' verb
     @@ -47,7 +47,7 @@
       
       static char const * const builtin_multi_pack_index_usage[] = {
      -	N_("git multi-pack-index [--object-dir=<dir>] write"),
     -+	N_("git multi-pack-index [--object-dir=<dir>] [write|verify]"),
     ++	N_("git multi-pack-index [--object-dir=<dir>] (write|verify)"),
       	NULL
       };
       
  2:  787e1fb616 !  2:  9590895830 multi-pack-index: verify bad header
     @@ -61,10 +61,10 @@
       
      +# usage: corrupt_midx_and_verify <pos> <data> <objdir> <string>
      +corrupt_midx_and_verify() {
     -+	POS=$1
     -+	DATA="${2:-\0}"
     -+	OBJDIR=$3
     -+	GREPSTR="$4"
     ++	POS=$1 &&
     ++	DATA="${2:-\0}" &&
     ++	OBJDIR=$3 &&
     ++	GREPSTR="$4" &&
      +	FILE=$OBJDIR/pack/multi-pack-index &&
      +	chmod a+w $FILE &&
      +	test_when_finished mv midx-backup $FILE &&
  3:  b385aa2abf =  3:  2448173844 multi-pack-index: verify corrupt chunk lookup table
  4:  37ee24c82b =  4:  947241bfdc multi-pack-index: verify packname order
  5:  b747da415c =  5:  4058867380 multi-pack-index: verify missing pack
  6:  58e5c09468 =  6:  ea1c522702 multi-pack-index: verify oid fanout order
  7:  b21772d054 =  7:  511791de91 multi-pack-index: verify oid lookup order
  8:  b08d3f0055 =  8:  210649bf83 multi-pack-index: fix 32-bit vs 64-bit size check
  9:  e1498aea45 !  9:  ef20193d59 multi-pack-index: verify object offsets
     @@ -21,7 +21,8 @@
       
       	if (pack_int_id >= m->num_packs)
      -		BUG("bad pack-int-id");
     -+		die(_("bad pack-int-id"));
     ++		die(_("bad pack-int-id: %u (%u total packs"),
     ++		    pack_int_id, m->num_packs);
       
       	if (m->packs[pack_int_id])
       		return 0;
 10:  acf8cfd632 = 10:  29ebc17161 multi-pack-index: report progress during 'verify'
 11:  09d16aff20 ! 11:  406c88b456 fsck: verify multi-pack-index
     @@ -40,14 +40,14 @@
      --- a/t/t5319-multi-pack-index.sh
      +++ b/t/t5319-multi-pack-index.sh
      @@
     - 	DATA="${2:-\0}"
     - 	OBJDIR=$3
     - 	GREPSTR="$4"
     -+	COMMAND="$5"
     + 	DATA="${2:-\0}" &&
     + 	OBJDIR=$3 &&
     + 	GREPSTR="$4" &&
     ++	COMMAND="$5" &&
      +	if test -z "$COMMAND"
      +	then
      +		COMMAND="git multi-pack-index verify --object-dir=$OBJDIR"
     -+	fi
     ++	fi &&
       	FILE=$OBJDIR/pack/multi-pack-index &&
       	chmod a+w $FILE &&
       	test_when_finished mv midx-backup $FILE &&

-- 
gitgitgadget