From e8f8bcb35f22965c8e4309c4aa4227241c485fe7 Mon Sep 17 00:00:00 2001 From: Pedro Alves Date: Mon, 12 Jun 2017 02:40:18 +0100 Subject: [PATCH] .gdb_index prod perf regression: Estimate size of psyms_seen Using the same test as the previous patch, perf shows GDB spending over 7% in "free". A substantial number of those calls comes from insertions in the psyms_seen unordered_set causing lots of rehashing and recreating buckets. Fix this by computing an estimate of the size of the set upfront. Using the same test as in the previous patch, against the same gdb inferior, timing improves ~8% further: ~6.5s => ~6.0s (average of 5 runs). gdb/ChangeLog: 2017-06-12 Pedro Alves * dwarf2read.c (recursively_count_psymbols): New function. (write_psymtabs_to_index): Call it to compute number of psyms and pass estimate size of psyms_seen to unordered_set's ctor. --- gdb/ChangeLog | 6 ++++++ gdb/dwarf2read.c | 36 +++++++++++++++++++++++++++++++++++- 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/gdb/ChangeLog b/gdb/ChangeLog index 01b66a1..9dbc059 100644 --- a/gdb/ChangeLog +++ b/gdb/ChangeLog @@ -1,5 +1,11 @@ 2017-06-12 Pedro Alves + * dwarf2read.c (recursively_count_psymbols): New function. + (write_psymtabs_to_index): Call it to compute number of psyms and + pass estimate size of psyms_seen to unordered_set's ctor. + +2017-06-12 Pedro Alves + * dwarf2read.c (write_hash_table): Check if key already exists before emplacing. diff --git a/gdb/dwarf2read.c b/gdb/dwarf2read.c index 93fd275..bff2fcb 100644 --- a/gdb/dwarf2read.c +++ b/gdb/dwarf2read.c @@ -23691,6 +23691,22 @@ write_one_signatured_type (void **slot, void *d) return 1; } +/* Recurse into all "included" dependencies and count their symbols as + if they appeared in this psymtab. */ + +static void +recursively_count_psymbols (struct partial_symtab *psymtab, + size_t &psyms_seen) +{ + for (int i = 0; i < psymtab->number_of_dependencies; ++i) + if (psymtab->dependencies[i]->user != NULL) + recursively_count_psymbols (psymtab->dependencies[i], + psyms_seen); + + psyms_seen += psymtab->n_global_syms; + psyms_seen += psymtab->n_static_syms; +} + /* Recurse into all "included" dependencies and write their symbols as if they appeared in this psymtab. */ @@ -23764,7 +23780,6 @@ write_psymtabs_to_index (struct objfile *objfile, const char *dir) mapped_symtab symtab; data_buf cu_list; - std::unordered_set psyms_seen; /* While we're scanning CU's create a table that maps a psymtab pointer (which is what addrmap records) to its index (which is what is recorded @@ -23776,6 +23791,25 @@ write_psymtabs_to_index (struct objfile *objfile, const char *dir) /* The CU list is already sorted, so we don't need to do additional work here. Also, the debug_types entries do not appear in all_comp_units, but only in their own hash table. */ + + /* The psyms_seen set is potentially going to be largish (~40k + elements when indexing a -g3 build of GDB itself). Estimate the + number of elements in order to avoid too many rehashes, which + require rebuilding buckets and thus many trips to + malloc/free. */ + size_t psyms_count = 0; + for (int i = 0; i < dwarf2_per_objfile->n_comp_units; ++i) + { + struct dwarf2_per_cu_data *per_cu + = dwarf2_per_objfile->all_comp_units[i]; + struct partial_symtab *psymtab = per_cu->v.psymtab; + + if (psymtab != NULL && psymtab->user == NULL) + recursively_count_psymbols (psymtab, psyms_count); + } + /* Generating an index for gdb itself shows a ratio of + TOTAL_SEEN_SYMS/UNIQUE_SYMS or ~5. 4 seems like a good bet. */ + std::unordered_set psyms_seen (psyms_count / 4); for (int i = 0; i < dwarf2_per_objfile->n_comp_units; ++i) { struct dwarf2_per_cu_data *per_cu -- 2.7.4