From aff250145af6c7a8ea9332bc1306c1219f4a63db Mon Sep 17 00:00:00 2001 From: Andrew Burgess Date: Fri, 24 Nov 2023 12:04:36 +0000 Subject: gdb: generate gdb-index identically regardless of work thread count It was observed that changing the number of worker threads that GDB uses (maintenance set worker-threads NUM) would have an impact on the layout of the generated gdb-index. The cause seems to be how the CU are distributed between threads, and then symbols that appear in multiple CU can be encountered earlier or later depending on whether a particular CU moves between threads. I certainly found this behaviour was reproducible when generating an index for GDB itself, like: gdb -q -nx -nh -batch \ -eiex 'maint set worker-threads NUM' \ -ex 'save gdb-index /tmp/' And then setting different values for NUM will change the generated index. Now, the question is: does this matter? I would like to suggest that yes, this does matter. At Red Hat we generate a gdb-index as part of the build process, and we would ideally like to have reproducible builds: for the same source, compiled with the same tool-chain, we should get the exact same output binary. And we do .... except for the index. Now we could simply force GDB to only use a single worker thread when we build the index, but, I don't think the idea of reproducible builds is that strange, so I think we should ensure that our generated indexes are always reproducible. To achieve this, I propose that we add an extra step when building the gdb-index file. After constructing the initial symbol hash table contents, we will pull all the symbols out of the hash, sort them, then re-insert them in sorted order. This will ensure that the structure of the generated hash will remain consistent (given the same set of symbols). I've extended the existing index-file test to check that the generated index doesn't change if we adjust the number of worker threads used. Given that this test is already rather slow, I've only made one change to the worker-thread count. Maybe this test should be changed to use a smaller binary, which is quicker to load, and for which we could then try many different worker thread counts. Approved-By: Tom Tromey --- gdb/testsuite/gdb.gdb/index-file.exp | 41 ++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'gdb/testsuite/gdb.gdb') diff --git a/gdb/testsuite/gdb.gdb/index-file.exp b/gdb/testsuite/gdb.gdb/index-file.exp index c6edd28..0841592 100644 --- a/gdb/testsuite/gdb.gdb/index-file.exp +++ b/gdb/testsuite/gdb.gdb/index-file.exp @@ -35,6 +35,9 @@ with_timeout_factor $timeout_factor { clean_restart $filename } +# Record how many worker threads GDB is using. +set worker_threads [gdb_get_worker_threads] + # Generate an index file. set dir1 [standard_output_file "index_1"] remote_exec host "mkdir -p ${dir1}" @@ -113,3 +116,41 @@ proc check_symbol_table_usage { filename } { set index_filename_base [file tail $filename] check_symbol_table_usage "$dir1/${index_filename_base}.gdb-index" + +# If GDB is using more than 1 worker thread then reduce the number of +# worker threads, regenerate the index, and check that we get the same +# index file back. At one point the layout of the index would vary +# based on the number of worker threads used. +if { $worker_threads > 1 } { + # Start GDB, but don't load a file yet. + clean_restart + + # Adjust the number of threads to use. + set reduced_threads [expr $worker_threads / 2] + gdb_test_no_output "maint set worker-threads $reduced_threads" + + with_timeout_factor $timeout_factor { + # Now load the test binary. + gdb_file_cmd $filename + } + + # Generate an index file. + set dir2 [standard_output_file "index_2"] + remote_exec host "mkdir -p ${dir2}" + with_timeout_factor $timeout_factor { + gdb_test_no_output "save gdb-index $dir2" \ + "create second gdb-index file" + } + + # Close GDB. + gdb_exit + + # Now check that the index files are identical. + foreach suffix { gdb-index } { + set result \ + [remote_exec host \ + "cmp -s \"$dir1/${index_filename_base}.${suffix}\" \"$dir2/${index_filename_base}.${suffix}\""] + gdb_assert { [lindex $result 0] == 0 } \ + "$suffix files are identical" + } +} -- cgit v1.1