From b069b588cfe10e6bf20ed723cf796686ba4fc0dc Mon Sep 17 00:00:00 2001 From: Tom de Vries Date: Fri, 5 Aug 2022 16:12:56 +0200 Subject: [PATCH] [gdb/symtab] Use task size in parallel_for_each in dwarf2_build_psymtabs_hard In dwarf2_build_psymtabs_hard, we use a parallel_for_each to distribute CUs over threads. Ensuring a fair distribution over the worker threads and main thread in terms of number of CUs might not be the most efficient way, given that CUs can vary in size. Fix this by using per_cu->get_length () as the task size. I've used this experiment to verify the performance impact: ... $ for n in $(seq 1 10); do \ time gdb -q -batch ~/firefox/libxul.so-93.0-1.1.x86_64.debug \ 2>&1 \ | grep "real:"; \ done ... and without the patch got: ... real: 4.71 real: 4.88 real: 4.29 real: 4.30 real: 4.65 real: 4.27 real: 4.27 real: 4.27 real: 4.75 real: 4.41 ... and with the patch: ... real: 3.68 real: 3.81 real: 3.80 real: 3.68 real: 3.75 real: 3.69 real: 3.69 real: 3.74 real: 3.67 real: 3.74 ... so that seems a reasonable improvement. With parallel_for_each_debug set to true, we get some more detail about the difference in behaviour. Without the patch we have: ... Parallel for: n_elements: 2818 Parallel for: minimum elements per thread: 1 Parallel for: elts_per_thread: 704 Parallel for: elements on worker thread 0 : 705 Parallel for: elements on worker thread 1 : 705 Parallel for: elements on worker thread 2 : 704 Parallel for: elements on worker thread 3 : 0 Parallel for: elements on main thread : 704 ... and with the patch: ... Parallel for: n_elements: 2818 Parallel for: total_size: 1483674865 Parallel for: size_per_thread: 370918716 Parallel for: elements on worker thread 0 : 752 (size: 371811790) Parallel for: elements on worker thread 1 : 360 (size: 371509370) Parallel for: elements on worker thread 2 : 1130 (size: 372681710) Parallel for: elements on worker thread 3 : 0 (size: 0) Parallel for: elements on main thread : 576 (size: 367671995) ... Tested on x86_64-linux. --- gdb/dwarf2/read.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/gdb/dwarf2/read.c b/gdb/dwarf2/read.c index f03151983dc..348fbe12da1 100644 --- a/gdb/dwarf2/read.c +++ b/gdb/dwarf2/read.c @@ -7085,6 +7085,13 @@ dwarf2_build_psymtabs_hard (dwarf2_per_objfile *per_objfile) using iter_type = decltype (per_bfd->all_comp_units.begin ()); + auto task_size_ = [] (iter_type iter) + { + dwarf2_per_cu_data *per_cu = iter->get (); + return (size_t)per_cu->length (); + }; + auto task_size = gdb::make_function_view (task_size_); + /* Each thread returns a pair holding a cooked index, and a vector of errors that should be printed. The latter is done because GDB's I/O system is not thread-safe. run_on_main_thread could be @@ -7113,7 +7120,7 @@ dwarf2_build_psymtabs_hard (dwarf2_per_objfile *per_objfile) } } return result_type (thread_storage.release (), std::move (errors)); - }); + }, task_size); /* Only show a given exception a single time. */ std::unordered_set seen_exceptions; -- 2.30.2