mirror of
https://github.com/scylladb/scylladb.git
synced 2026-05-02 22:25:48 +00:00
The design of the tree goes from the row-cache needs, which are
1. Insert/Remove do not invalidate iterators
2. Elements are LSA-manageable
3. Low key overhead
4. External tri-comparator
5. As little actions on insert/remove as possible
With the above the design is
Two types of nodes -- inner and leaf. Both types keep pointer on parent nodes
and N pointers on keys (not keys themselves). Two differences: inner nodes have
array of pointers on kids, leaf nodes keep pointer on the tree (to update left-
and rightmost tree pointers on node move).
Nodes do not keep pointers/references on trees, thus we have O(1) move of any
object, but O(logN) to get the tree size. Fortunately, with big keys-per-node
value this won't result in too many steps.
In turn, the tree has 3 pointers -- root, left- and rightmost leaves. The latter
is for constant-time begin() and end().
Keys are managed by user with the help of embeddable member_hook instance,
which is 1 pointer in size.
The code was copied from the B+ tree one, then heavily reworked, the internal
algorythms turned out to differ quite significantly.
For the sake of mutation_partition::apply_monotonically(), which needs to move
an element from one tree into another, there's a key_grabber helping wrapper
that allows doing this move respecting the exception-safety requirement.
As measured by the perf_collections test the B-tree with 8 keys is faster, than
the std::set, but slower than the B+tree:
vs set vs b+tree
fill: +13% -6%
find: +23% -35%
Another neat thing is that 1-key insertion-removal is ~40% faster than
for BST (the same number of allocations, but the key object is smaller,
less pointers to set-up and less instructions to execute when linking
node with root).
v4:
- equip insertion methods with on_alloc_point() calls to catch
potential exception guarantees violations eariler
- add unlink_leftmost_without_rebalance. The method is borrowed from
boost intrusive set, and is added to kill two birds -- provide it,
as it turns out to be popular, and use a bit faster step-by-step
tree destruction than plain begin+erase loop
v3:
- introduce "inline" root node that is embedded into tree object and in
which the 1st key is inserted. This greatly improves the 1-key-tree
performance, which is pretty common case for rows cache
v2:
- introduce "linear" root leaf that grows on demand
This improves the memory consumption for small trees. This linear node may
and should over-grow the NodeSize parameter. This comes from the fact that
there are two big per-key memory spikes on small trees -- 1-key root leaf
and the first split, when the tree becomes 1-key root with two half-filled
leaves. If the linear extention goes above NodeSize it can flatten even the
2nd peak
- mitigate the keys indirection a bit
Prefetching the keys while doing the intra-node linear scan and the nodes
while descending the tree gives ~+5% of fill and find
- generalize stress tests for B and B+ trees
- cosmetic changes
TODO:
- fix few inefficincies in the core code (walks the sub-tree twice sometimes)
- try to optimize the leaf nodes, that are not lef-/righmost not to carry
unused tree pointer on board
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
126 lines
3.5 KiB
C++
126 lines
3.5 KiB
C++
/*
|
|
* Copyright (C) 2020 ScyllaDB
|
|
*/
|
|
|
|
/*
|
|
* This file is part of Scylla.
|
|
*
|
|
* Scylla is free software: you can redistribute it and/or modify
|
|
* it under the terms of the GNU Affero General Public License as published by
|
|
* the Free Software Foundation, either version 3 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* Scylla 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 Scylla. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
/*
|
|
* Helper class that helps to check that tree
|
|
* - works with keys without default contstuctor
|
|
* - moves the keys around properly
|
|
*/
|
|
class tree_test_key_base {
|
|
int _val;
|
|
int* _cookie;
|
|
int* _p_cookie;
|
|
|
|
public:
|
|
int cookie() const noexcept { return *_cookie; }
|
|
|
|
bool is_alive() const {
|
|
if (_val == -1) {
|
|
fmt::print("key value is reset\n");
|
|
return false;
|
|
}
|
|
|
|
if (_cookie == nullptr) {
|
|
fmt::print("key cookie is reset\n");
|
|
return false;
|
|
}
|
|
|
|
if (*_cookie != 0) {
|
|
fmt::print("key cookie value is corrupted {}\n", *_cookie);
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
bool less(const tree_test_key_base& o) const noexcept {
|
|
return _val < o._val;
|
|
}
|
|
|
|
int compare(const int o) const noexcept {
|
|
if (_val > o) {
|
|
return 1;
|
|
} else if (_val < o) {
|
|
return -1;
|
|
} else {
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
int compare(const tree_test_key_base& o) const noexcept {
|
|
return compare(o._val);
|
|
}
|
|
|
|
explicit tree_test_key_base(int nr, int cookie = 0) : _val(nr) {
|
|
_cookie = new int(cookie);
|
|
_p_cookie = new int(1);
|
|
}
|
|
|
|
operator int() const noexcept { return _val; }
|
|
|
|
tree_test_key_base& operator=(const tree_test_key_base& other) = delete;
|
|
tree_test_key_base& operator=(tree_test_key_base&& other) = delete;
|
|
|
|
private:
|
|
/*
|
|
* Keep this private to make bptree.hh explicitly call the
|
|
* copy_key in the places where the key is copied
|
|
*/
|
|
tree_test_key_base(const tree_test_key_base& other) : _val(other._val) {
|
|
_cookie = new int(*other._cookie);
|
|
_p_cookie = new int(*other._p_cookie);
|
|
}
|
|
|
|
friend tree_test_key_base copy_key(const tree_test_key_base&);
|
|
|
|
public:
|
|
struct force_copy_tag {};
|
|
tree_test_key_base(const tree_test_key_base& other, force_copy_tag) : tree_test_key_base(other) {}
|
|
|
|
tree_test_key_base(tree_test_key_base&& other) noexcept : _val(other._val) {
|
|
other._val = -1;
|
|
_cookie = other._cookie;
|
|
other._cookie = nullptr;
|
|
_p_cookie = new int(*other._p_cookie);
|
|
}
|
|
|
|
~tree_test_key_base() {
|
|
if (_cookie != nullptr) {
|
|
delete _cookie;
|
|
}
|
|
assert(_p_cookie != nullptr);
|
|
delete _p_cookie;
|
|
}
|
|
};
|
|
|
|
tree_test_key_base copy_key(const tree_test_key_base& other) { return tree_test_key_base(other); }
|
|
|
|
struct test_key_compare {
|
|
bool operator()(const tree_test_key_base& a, const tree_test_key_base& b) const noexcept { return a.less(b); }
|
|
};
|
|
|
|
struct test_key_tri_compare {
|
|
int operator()(const tree_test_key_base& a, const tree_test_key_base& b) const noexcept { return a.compare(b); }
|
|
int operator()(const int a, const tree_test_key_base& b) const noexcept { return -b.compare(a); }
|
|
};
|