Fix bug in archive streamer with LZ4 decompression

When decompressing some input data, the calculation for the initial
starting point and the initial size were incorrect, potentially leading
to failures when decompressing contents with LZ4.  These initialization
points are fixed in this commit, bringing the logic closer to what
exists for gzip and zstd.

The contents of the compressed data is clear (for example backups taken
with LZ4 can still be decompressed with a "lz4" command), only the
decompression part reading the input data was impacted by this issue.

This code path impacts pg_basebackup and pg_verifybackup, which can use
the LZ4 decompression routines with an archive streamer, or any tools
that try to use the archive streamers in src/fe_utils/.

The issue is easier to reproduce with files that have a low-compression
rate, like ones filled with random data, for a size of at least 512kB,
but this could happen with anything as long as it is stored in a data
folder.  Some tests are added based on this idea, with a file filled
with random bytes grabbed from the backend, written at the root of the
data folder.  This is proving good enough to reproduce the original
problem.

Author: Mikhail Gribkov <youzhick@gmail.com>
Discussion: https://postgr.es/m/CAMEv5_uQS1Hg6KCaEP2JkrTBbZ-nXQhxomWrhYQvbdzR-zy-wA@mail.gmail.com
Backpatch-through: 15

diff --git a/src/bin/pg_basebackup/bbstreamer_lz4.c b/src/bin/pg_basebackup/bbstreamer_lz4.c
index eda62caeded4d4acf026a9e1c8d7af0028ab8330..96e74ae7649d0357887bd5149a456646608c5ac4 100644 (file)
--- a/src/bin/pg_basebackup/bbstreamer_lz4.c
+++ b/src/bin/pg_basebackup/bbstreamer_lz4.c
@@ -320,9 +320,9 @@ bbstreamer_lz4_decompressor_content(bbstreamer *streamer,
 
        mystreamer = (bbstreamer_lz4_frame *) streamer;
        next_in = (uint8 *) data;
-       next_out = (uint8 *) mystreamer->base.bbs_buffer.data;
+       next_out = (uint8 *) mystreamer->base.bbs_buffer.data + mystreamer->bytes_written;
        avail_in = len;
-       avail_out = mystreamer->base.bbs_buffer.maxlen;
+       avail_out = mystreamer->base.bbs_buffer.maxlen - mystreamer->bytes_written;
 
        while (avail_in > 0)
        {

diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index 7a09f3b75b2a7a8e665bad77b64a26e708d0d54f..7b589dd4bf13e012ee480f52ce5f064c90028ac6 100644 (file)
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -16,6 +16,22 @@ my $primary = PostgreSQL::Test::Cluster->new('primary');
 $primary->init(allows_streaming => 1);
 $primary->start;
 
+# Create file with some random data and an arbitrary size, useful to check
+# the solidity of the compression and decompression logic.  The size of the
+# file is chosen to be around 640kB.  This has proven to be large enough to
+# detect some issues related to LZ4, and low enough to not impact the runtime
+# of the test significantly.
+my $junk_data = $primary->safe_psql(
+       'postgres', qq(
+               SELECT string_agg(encode(sha256(i::text::bytea), 'hex'), '')
+               FROM generate_series(1, 10240) s(i);));
+my $data_dir = $primary->data_dir;
+my $junk_file = "$data_dir/junk";
+open my $jf, '>', $junk_file
+  or die "Could not create junk file: $!";
+print $jf $junk_data;
+close $jf;
+
 my $backup_path = $primary->backup_dir . '/server-backup';
 my $extract_path = $primary->backup_dir . '/extracted-backup';
 
@@ -42,6 +58,14 @@ my @test_configuration = (
                'decompress_flags' => [ '-d', '-m' ],
                'enabled' => check_pg_config("#define USE_LZ4 1")
        },
+       {
+               'compression_method' => 'lz4',
+               'backup_flags' => [ '--compress', 'server-lz4:5' ],
+               'backup_archive' => 'base.tar.lz4',
+               'decompress_program' => $ENV{'LZ4'},
+               'decompress_flags' => [ '-d', '-m' ],
+               'enabled' => check_pg_config("#define USE_LZ4 1")
+       },
        {
                'compression_method' => 'zstd',
                'backup_flags' => [ '--compress', 'server-zstd' ],

diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index 8c076d46dee00c53af8600e0b85272cd120287f7..dc26c296ad771cfcb898139ebba14fb4da62e84a 100644 (file)
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -15,6 +15,22 @@ my $primary = PostgreSQL::Test::Cluster->new('primary');
 $primary->init(allows_streaming => 1);
 $primary->start;
 
+# Create file with some random data and an arbitrary size, useful to check
+# the solidity of the compression and decompression logic.  The size of the
+# file is chosen to be around 640kB.  This has proven to be large enough to
+# detect some issues related to LZ4, and low enough to not impact the runtime
+# of the test significantly.
+my $junk_data = $primary->safe_psql(
+       'postgres', qq(
+               SELECT string_agg(encode(sha256(i::text::bytea), 'hex'), '')
+               FROM generate_series(1, 10240) s(i);));
+my $data_dir = $primary->data_dir;
+my $junk_file = "$data_dir/junk";
+open my $jf, '>', $junk_file
+  or die "Could not create junk file: $!";
+print $jf $junk_data;
+close $jf;
+
 my $backup_path = $primary->backup_dir . '/client-backup';
 my $extract_path = $primary->backup_dir . '/extracted-backup';
 
@@ -42,6 +58,15 @@ my @test_configuration = (
                'output_file' => 'base.tar',
                'enabled' => check_pg_config("#define USE_LZ4 1")
        },
+       {
+               'compression_method' => 'lz4',
+               'backup_flags' => [ '--compress', 'client-lz4:1' ],
+               'backup_archive' => 'base.tar.lz4',
+               'decompress_program' => $ENV{'LZ4'},
+               'decompress_flags' => ['-d'],
+               'output_file' => 'base.tar',
+               'enabled' => check_pg_config("#define USE_LZ4 1")
+       },
        {
                'compression_method' => 'zstd',
                'backup_flags' => [ '--compress', 'client-zstd:5' ],