From 20a26f4e018cd0cb40a3b81568be0d4f164eed0f Mon Sep 17 00:00:00 2001 From: Tom Tromey Date: Fri, 13 May 2022 13:46:52 -0600 Subject: Finalize each cooked index separately After DWARF has been scanned, the cooked index code does a "finalization" step in a worker thread. This step combines all the index entries into a single master list, canonicalizes C++ names, and splits Ada names to synthesize package names. While this step is run in the background, gdb will wait for the results in some situations, and it turns out that this step can be slow. This is PR symtab/29105. This can be sped up by parallelizing, at a small memory cost. Now each index is finalized on its own, in a worker thread. The cost comes from name canonicalization: if a given non-canonical name is referred to by multiple indices, there will be N canonical copies (one per index) rather than just one. This requires changing the users of the index to iterate over multiple results. However, this is easily done by introducing a new "chained range" class. When run on gdb itself, the memory cost seems rather low -- on my current machine, "maint space 1" reports no change due to the patch. For performance testing, using "maint time 1" and "file" will not show correct results. That approach measures "time to next prompt", but because the patch only affects background work, this shouldn't (and doesn't) change. Instead, a simple way to make gdb wait for the results is to set a breakpoint. Before: $ /bin/time -f%e ~/gdb/install/bin/gdb -nx -q -batch \ -ex 'break main' /tmp/gdb Breakpoint 1 at 0x43ec30: file ../../binutils-gdb/gdb/gdb.c, line 28. 2.00 After: $ /bin/time -f%e ./gdb/gdb -nx -q -batch \ -ex 'break main' /tmp/gdb Breakpoint 1 at 0x43ec30: file ../../binutils-gdb/gdb/gdb.c, line 28. 0.65 Regression tested on x86-64 Fedora 34. Bug: https://sourceware.org/bugzilla/show_bug.cgi?id=29105 --- gdbsupport/range-chain.h | 121 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) create mode 100644 gdbsupport/range-chain.h (limited to 'gdbsupport') diff --git a/gdbsupport/range-chain.h b/gdbsupport/range-chain.h new file mode 100644 index 0000000..5742737 --- /dev/null +++ b/gdbsupport/range-chain.h @@ -0,0 +1,121 @@ +/* A range adapter that wraps multiple ranges + Copyright (C) 2022 Free Software Foundation, Inc. + + This file is part of GDB. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . */ + +#ifndef GDBSUPPORT_RANGE_CHAIN_H +#define GDBSUPPORT_RANGE_CHAIN_H + +/* A range adapter that presents a number of ranges as if it were a + single range. That is, iterating over a range_chain will iterate + over each sub-range in order. */ +template +struct range_chain +{ + /* The type of the iterator that is created by this range. */ + class iterator + { + public: + + iterator (const std::vector &ranges, size_t idx) + : m_index (idx), + m_ranges (ranges) + { + skip_empty (); + } + + bool operator== (const iterator &other) const + { + if (m_index != other.m_index || &m_ranges != &other.m_ranges) + return false; + if (m_current.has_value () != other.m_current.has_value ()) + return false; + if (m_current.has_value ()) + return *m_current == *other.m_current; + return true; + } + + bool operator!= (const iterator &other) const + { + return !(*this == other); + } + + iterator &operator++ () + { + ++*m_current; + if (*m_current == m_ranges[m_index].end ()) + { + ++m_index; + skip_empty (); + } + return *this; + } + + typename Range::iterator::value_type operator* () const + { + return **m_current; + } + + private: + /* Skip empty sub-ranges. If this finds a valid sub-range, + m_current is updated to point to its start; otherwise, + m_current is reset. */ + void skip_empty () + { + for (; m_index < m_ranges.size (); ++m_index) + { + m_current = m_ranges[m_index].begin (); + if (*m_current != m_ranges[m_index].end ()) + return; + } + m_current.reset (); + } + + /* Index into the vector indicating where the current iterator + comes from. */ + size_t m_index; + /* The current iterator into one of the vector ranges. If no + value then this (outer) iterator is at the end of the overall + range. */ + gdb::optional m_current; + /* Vector of ranges. */ + const std::vector &m_ranges; + }; + + /* Create a new range_chain. */ + template + range_chain (T &&ranges) + : m_ranges (std::forward (ranges)) + { + } + + iterator begin () const + { + return iterator (m_ranges, 0); + } + + iterator end () const + { + return iterator (m_ranges, m_ranges.size ()); + } + +private: + + /* The sub-ranges. */ + std::vector m_ranges; +}; + +#endif /* GDBSUPPORT_RANGE_CHAIN_H */ -- cgit v1.1