mirror of
https://github.com/scylladb/scylladb.git
synced 2026-05-29 11:10:40 +00:00
"This series changes digest calculation to use a faster algorithm (xxHash) and to also cache calculated cell hashes that can be kept in memory to speed up subsequent digest requests. The MD5 hash function has proved to be slow for large cell values: size = 256; elapsed = 4us size = 512; elapsed = 8us size = 1024; elapsed = 14us size = 2048; elapsed = 21us size = 4096; elapsed = 33us size = 8192; elapsed = 51us size = 16384; elapsed = 86us size = 32768; elapsed = 150us size = 65536; elapsed = 278us size = 131072; elapsed = 531us size = 262144; elapsed = 1032us size = 524288; elapsed = 2026us size = 1048576; elapsed = 4004us size = 2097152; elapsed = 7943us size = 4194304; elapsed = 15800us size = 8388608; elapsed = 31731us size = 16777216; elapsed = 64681us size = 33554432; elapsed = 130752us size = 67108864; elapsed = 263154us The xxHash is a non-cryptographic, 64bit (there's work in progress on the 128 version) hash that can be used to replace MD5. It performs much better: size = 256; elapsed = 2us size = 512; elapsed = 1us size = 1024; elapsed = 1us size = 2048; elapsed = 2us size = 4096; elapsed = 2us size = 8192; elapsed = 3us size = 16384; elapsed = 5us size = 32768; elapsed = 8us size = 65536; elapsed = 14us size = 131072; elapsed = 28us size = 262144; elapsed = 59us size = 524288; elapsed = 116us size = 1048576; elapsed = 226us size = 2097152; elapsed = 456us size = 4194304; elapsed = 935us size = 8388608; elapsed = 1848us size = 16777216; elapsed = 4723us size = 33554432; elapsed = 10507us size = 67108864; elapsed = 21622us Performance was tested using a 3 node cluster with 1 cpu and 8GB, and with the following cassandra-stress loaders. Measurements are for the read workload. sudo taskset -c 4-15 ./cassandra-stress write cl=ALL n=5000000 -schema 'replication(factor=3)' -col 'size=FIXED(1024) n=FIXED(4)' -mode native cql3 -rate threads=100 sudo taskset -c 4-15 ./cassandra-stress mixed cl=ALL 'ratio(read=1)' n=10000000 -pop 'dist=gauss(1..5000000,5000000,500000)' -col 'size=FIXED(1024) n=FIXED(4)' -mode native cql3 -rate threads=100 xxhash + caching: Results: op rate : 32699 [READ:32699] partition rate : 32699 [READ:32699] row rate : 32699 [READ:32699] latency mean : 3.0 [READ:3.0] latency median : 3.0 [READ:3.0] latency 95th percentile : 3.9 [READ:3.9] latency 99th percentile : 4.5 [READ:4.5] latency 99.9th percentile : 6.6 [READ:6.6] latency max : 24.0 [READ:24.0] Total partitions : 10000000 [READ:10000000] Total errors : 0 [READ:0] total gc count : 0 total gc mb : 0 total gc time (s) : 0 avg gc time(ms) : NaN stdev gc time(ms) : 0 Total operation time : 00:05:05 END md5: Results: op rate : 25241 [READ:25241] partition rate : 25241 [READ:25241] row rate : 25241 [READ:25241] latency mean : 3.9 [READ:3.9] latency median : 3.9 [READ:3.9] latency 95th percentile : 5.1 [READ:5.1] latency 99th percentile : 5.8 [READ:5.8] latency 99.9th percentile : 8.0 [READ:8.0] latency max : 24.8 [READ:24.8] Total partitions : 10000000 [READ:10000000] Total errors : 0 [READ:0] total gc count : 0 total gc mb : 0 total gc time (s) : 0 avg gc time(ms) : NaN stdev gc time(ms) : 0 Total operation time : 00:06:36 END This translates into a 21% improvoment for this workload. Bigger cell values were also tested: sudo taskset -c 4-15 ./cassandra-stress write cl=ALL n=1000000 -schema 'replication(factor=3)' -col 'size=FIXED(4096) n=FIXED(4)' -mode native cql3 -rate threads=100 sudo taskset -c 4-15 ./cassandra-stress mixed cl=ALL 'ratio(read=1)' n=10000000 -pop 'dist=gauss(1..1000000,500000,100000)' -col 'size=FIXED(4096) n=FIXED(4)' -mode native cql3 -rate threads=100 xxhash + caching: Results: op rate : 19964 [READ:19964] partition rate : 19964 [READ:19964] row rate : 19964 [READ:19964] latency mean : 4.9 [READ:4.9] latency median : 4.6 [READ:4.6] latency 95th percentile : 7.2 [READ:7.2] latency 99th percentile : 11.5 [READ:11.5] latency 99.9th percentile : 13.6 [READ:13.6] latency max : 29.2 [READ:29.2] Total partitions : 10000000 [READ:10000000] Total errors : 0 [READ:0] total gc count : 0 total gc mb : 0 total gc time (s) : 0 avg gc time(ms) : NaN stdev gc time(ms) : 0 Total operation time : 00:08:20 END md5: Results: op rate : 12773 [READ:12773] partition rate : 12773 [READ:12773] row rate : 12773 [READ:12773] latency mean : 7.7 [READ:7.7] latency median : 7.3 [READ:7.3] latency 95th percentile : 10.2 [READ:10.2] latency 99th percentile : 16.8 [READ:16.8] latency 99.9th percentile : 19.2 [READ:19.2] latency max : 71.5 [READ:71.5] Total partitions : 10000000 [READ:10000000] Total errors : 0 [READ:0] total gc count : 0 total gc mb : 0 total gc time (s) : 0 avg gc time(ms) : NaN stdev gc time(ms) : 0 Total operation time : 00:13:02 END This translates into a 37% improvoment for this workload. Fixes #2884 Tests: unit-tests (release), dtests (smp=2) Note: dtests are kinda broken in master (> 30 failures), so take the tests tag with a grain of himalayan salt." * 'xxhash/v5' of https://github.com/duarten/scylla: (29 commits) tests/row_cache_test: Test hash caching tests/memtable_test: Test hash caching tests/mutation_test: Use xxHash instead of MD5 for some tests tests/mutation_test: Test xx_hasher alongside md5_hasher schema: Remove unneeded include service/storage_proxy: Enable hash caching service/storage_service: Add and use xxhash feature message/messaging_service: Specify algorithm when requesting digest storage_proxy: Extract decision about digest algorithm to use cache_flat_mutation_reader: Pre-calculate cell hash partition_snapshot_reader: Pre-calculate cell hash query::partition_slice: Add option to specify when digest is requested row: Use cached hash for hash calculation mutation_partition: Replace hash_row_slice with appending_hash mutation_partition: Allow caching cell hashes mutation_partition: Force vector_storage internal storage size test.py: Increase memory for row_cache_stress_test atomic_cell_hash: Add specialization for atomic_cell_or_collection query-result: Use digester instead of md5_hasher range_tombstone: Replace feed_hash() member function with appending_hash ...
581 lines
19 KiB
C++
581 lines
19 KiB
C++
/*
|
|
* Copyright (C) 2016 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/>.
|
|
*/
|
|
|
|
#include <boost/range/algorithm/heap_algorithm.hpp>
|
|
#include <seastar/util/defer.hh>
|
|
|
|
#include "partition_version.hh"
|
|
#include "partition_builder.hh"
|
|
#include "partition_snapshot_row_cursor.hh"
|
|
|
|
static void remove_or_mark_as_unique_owner(partition_version* current)
|
|
{
|
|
while (current && !current->is_referenced()) {
|
|
auto next = current->next();
|
|
current_allocator().destroy(current);
|
|
current = next;
|
|
}
|
|
if (current) {
|
|
current->back_reference().mark_as_unique_owner();
|
|
}
|
|
}
|
|
|
|
partition_version::partition_version(partition_version&& pv) noexcept
|
|
: anchorless_list_base_hook(std::move(pv))
|
|
, _backref(pv._backref)
|
|
, _partition(std::move(pv._partition))
|
|
{
|
|
if (_backref) {
|
|
_backref->_version = this;
|
|
}
|
|
pv._backref = nullptr;
|
|
}
|
|
|
|
partition_version& partition_version::operator=(partition_version&& pv) noexcept
|
|
{
|
|
if (this != &pv) {
|
|
this->~partition_version();
|
|
new (this) partition_version(std::move(pv));
|
|
}
|
|
return *this;
|
|
}
|
|
|
|
partition_version::~partition_version()
|
|
{
|
|
if (_backref) {
|
|
_backref->_version = nullptr;
|
|
}
|
|
}
|
|
|
|
size_t partition_version::size_in_allocator(allocation_strategy& allocator) const {
|
|
return allocator.object_memory_size_in_allocator(this) +
|
|
partition().external_memory_usage();
|
|
}
|
|
|
|
namespace {
|
|
|
|
GCC6_CONCEPT(
|
|
|
|
// A functor which transforms objects from Domain into objects from CoDomain
|
|
template<typename U, typename Domain, typename CoDomain>
|
|
concept bool Mapper() {
|
|
return requires(U obj, const Domain& src) {
|
|
{ obj(src) } -> const CoDomain&
|
|
};
|
|
}
|
|
|
|
// A functor which merges two objects from Domain into one. The result is stored in the first argument.
|
|
template<typename U, typename Domain>
|
|
concept bool Reducer() {
|
|
return requires(U obj, Domain& dst, const Domain& src) {
|
|
{ obj(dst, src) } -> void;
|
|
};
|
|
}
|
|
|
|
)
|
|
|
|
// Calculates the value of particular part of mutation_partition represented by
|
|
// the version chain starting from v.
|
|
// |map| extracts the part from each version.
|
|
// |reduce| Combines parts from the two versions.
|
|
template <typename Result, typename Map, typename Reduce>
|
|
GCC6_CONCEPT(
|
|
requires Mapper<Map, mutation_partition, Result>() && Reducer<Reduce, Result>()
|
|
)
|
|
inline Result squashed(const partition_version_ref& v, Map&& map, Reduce&& reduce) {
|
|
const partition_version* this_v = &*v;
|
|
partition_version* it = v->last();
|
|
Result r = map(it->partition());
|
|
while (it != this_v) {
|
|
it = it->prev();
|
|
reduce(r, map(it->partition()));
|
|
}
|
|
return r;
|
|
}
|
|
|
|
}
|
|
|
|
::static_row partition_snapshot::static_row(bool digest_requested) const {
|
|
return ::static_row(::squashed<row>(version(),
|
|
[&] (const mutation_partition& mp) -> const row& {
|
|
if (digest_requested) {
|
|
mp.static_row().prepare_hash(*_schema, column_kind::static_column);
|
|
}
|
|
return mp.static_row();
|
|
},
|
|
[this] (row& a, const row& b) { a.apply(*_schema, column_kind::static_column, b); }));
|
|
}
|
|
|
|
bool partition_snapshot::static_row_continuous() const {
|
|
return version()->partition().static_row_continuous();
|
|
}
|
|
|
|
tombstone partition_snapshot::partition_tombstone() const {
|
|
return ::squashed<tombstone>(version(),
|
|
[] (const mutation_partition& mp) { return mp.partition_tombstone(); },
|
|
[] (tombstone& a, tombstone b) { a.apply(b); });
|
|
}
|
|
|
|
mutation_partition partition_snapshot::squashed() const {
|
|
return ::squashed<mutation_partition>(version(),
|
|
[] (const mutation_partition& mp) -> const mutation_partition& { return mp; },
|
|
[this] (mutation_partition& a, const mutation_partition& b) { a.apply(*_schema, b, *_schema); });
|
|
}
|
|
|
|
tombstone partition_entry::partition_tombstone() const {
|
|
return ::squashed<tombstone>(_version,
|
|
[] (const mutation_partition& mp) { return mp.partition_tombstone(); },
|
|
[] (tombstone& a, tombstone b) { a.apply(b); });
|
|
}
|
|
|
|
partition_snapshot::~partition_snapshot() {
|
|
with_allocator(_region.allocator(), [this] {
|
|
if (_version && _version.is_unique_owner()) {
|
|
auto v = &*_version;
|
|
_version = {};
|
|
remove_or_mark_as_unique_owner(v);
|
|
} else if (_entry) {
|
|
_entry->_snapshot = nullptr;
|
|
}
|
|
});
|
|
}
|
|
|
|
void merge_versions(const schema& s, mutation_partition& newer, mutation_partition&& older) {
|
|
older.apply_monotonically(s, std::move(newer));
|
|
newer = std::move(older);
|
|
}
|
|
|
|
void partition_snapshot::merge_partition_versions() {
|
|
if (_version && !_version.is_unique_owner()) {
|
|
auto v = &*_version;
|
|
_version = { };
|
|
auto first_used = v;
|
|
while (first_used->prev() && !first_used->is_referenced()) {
|
|
first_used = first_used->prev();
|
|
}
|
|
|
|
auto current = first_used->next();
|
|
while (current && !current->is_referenced()) {
|
|
auto next = current->next();
|
|
merge_versions(*_schema, first_used->partition(), std::move(current->partition()));
|
|
current_allocator().destroy(current);
|
|
current = next;
|
|
}
|
|
}
|
|
}
|
|
|
|
unsigned partition_snapshot::version_count()
|
|
{
|
|
unsigned count = 0;
|
|
for (auto&& v : versions()) {
|
|
(void)v;
|
|
count++;
|
|
}
|
|
return count;
|
|
}
|
|
|
|
partition_entry::partition_entry(mutation_partition mp)
|
|
{
|
|
auto new_version = current_allocator().construct<partition_version>(std::move(mp));
|
|
_version = partition_version_ref(*new_version, partition_version::is_evictable::no);
|
|
}
|
|
|
|
partition_entry::partition_entry(partition_entry::evictable_tag, const schema& s, mutation_partition&& mp)
|
|
: partition_entry(std::move(mp))
|
|
{
|
|
_version->partition().ensure_last_dummy(s);
|
|
_version.make_evictable();
|
|
}
|
|
|
|
partition_entry::partition_entry(partition_entry::evictable_tag, const schema& s, partition_entry&& e)
|
|
: partition_entry(std::move(e))
|
|
{
|
|
if (_snapshot) {
|
|
// We must not change evictability of existing snapshots
|
|
// FIXME: https://github.com/scylladb/scylla/issues/1938
|
|
add_version(s);
|
|
}
|
|
_version.make_evictable();
|
|
}
|
|
|
|
partition_entry partition_entry::make_evictable(const schema& s, mutation_partition&& mp) {
|
|
return {evictable_tag(), s, std::move(mp)};
|
|
}
|
|
|
|
partition_entry partition_entry::make_evictable(const schema& s, const mutation_partition& mp) {
|
|
return make_evictable(s, mutation_partition(mp));
|
|
}
|
|
|
|
partition_entry partition_entry::make_evictable(const schema& s, partition_entry&& pe) {
|
|
// If we can assume that _pe is fully continuous, we don't need to check all versions
|
|
// to determine what the continuity is.
|
|
// This doesn't change value and doesn't invalidate iterators, so can be called even with a snapshot.
|
|
pe.version()->partition().ensure_last_dummy(s);
|
|
return partition_entry(evictable_tag(), s, std::move(pe));
|
|
}
|
|
|
|
partition_entry::~partition_entry() {
|
|
if (!_version) {
|
|
return;
|
|
}
|
|
if (_snapshot) {
|
|
_snapshot->_version = std::move(_version);
|
|
_snapshot->_version.mark_as_unique_owner();
|
|
_snapshot->_entry = nullptr;
|
|
} else {
|
|
auto v = &*_version;
|
|
_version = { };
|
|
remove_or_mark_as_unique_owner(v);
|
|
}
|
|
}
|
|
|
|
void partition_entry::set_version(partition_version* new_version)
|
|
{
|
|
bool evictable = _version.evictable();
|
|
|
|
if (_snapshot) {
|
|
_snapshot->_version = std::move(_version);
|
|
_snapshot->_entry = nullptr;
|
|
}
|
|
|
|
_snapshot = nullptr;
|
|
_version = partition_version_ref(*new_version, partition_version::is_evictable(evictable));
|
|
}
|
|
|
|
partition_version& partition_entry::add_version(const schema& s) {
|
|
auto new_version = current_allocator().construct<partition_version>(mutation_partition(s.shared_from_this()));
|
|
new_version->partition().set_static_row_continuous(_version->partition().static_row_continuous());
|
|
new_version->insert_before(*_version);
|
|
set_version(new_version);
|
|
return *new_version;
|
|
}
|
|
|
|
void partition_entry::apply(const schema& s, const mutation_partition& mp, const schema& mp_schema)
|
|
{
|
|
apply(s, mutation_partition(mp), mp_schema);
|
|
}
|
|
|
|
void partition_entry::apply(const schema& s, mutation_partition&& mp, const schema& mp_schema)
|
|
{
|
|
if (s.version() != mp_schema.version()) {
|
|
mp.upgrade(mp_schema, s);
|
|
}
|
|
auto new_version = current_allocator().construct<partition_version>(std::move(mp));
|
|
if (!_snapshot) {
|
|
try {
|
|
_version->partition().apply_monotonically(s, std::move(new_version->partition()));
|
|
current_allocator().destroy(new_version);
|
|
return;
|
|
} catch (...) {
|
|
// fall through
|
|
}
|
|
}
|
|
new_version->insert_before(*_version);
|
|
set_version(new_version);
|
|
}
|
|
|
|
void partition_entry::apply(const schema& s, mutation_partition_view mpv, const schema& mp_schema)
|
|
{
|
|
mutation_partition mp(mp_schema.shared_from_this());
|
|
partition_builder pb(mp_schema, mp);
|
|
mpv.accept(mp_schema, pb);
|
|
apply(s, std::move(mp), mp_schema);
|
|
}
|
|
|
|
// Iterates over all rows in mutation represented by partition_entry.
|
|
// It abstracts away the fact that rows may be spread across multiple versions.
|
|
class partition_entry::rows_iterator final {
|
|
struct version {
|
|
mutation_partition::rows_type::iterator current_row;
|
|
mutation_partition::rows_type* rows;
|
|
bool can_move;
|
|
struct compare {
|
|
const rows_entry::tri_compare& _cmp;
|
|
public:
|
|
explicit compare(const rows_entry::tri_compare& cmp) : _cmp(cmp) { }
|
|
bool operator()(const version& a, const version& b) const {
|
|
return _cmp(*a.current_row, *b.current_row) > 0;
|
|
}
|
|
};
|
|
};
|
|
const schema& _schema;
|
|
rows_entry::tri_compare _rows_cmp;
|
|
rows_entry::compare _rows_less_cmp;
|
|
version::compare _version_cmp;
|
|
std::vector<version> _heap;
|
|
std::vector<version> _current_row;
|
|
public:
|
|
rows_iterator(partition_version* version, const schema& schema)
|
|
: _schema(schema)
|
|
, _rows_cmp(schema)
|
|
, _rows_less_cmp(schema)
|
|
, _version_cmp(_rows_cmp)
|
|
{
|
|
bool can_move = true;
|
|
while (version) {
|
|
can_move &= !version->is_referenced();
|
|
auto& rows = version->partition().clustered_rows();
|
|
if (!rows.empty()) {
|
|
_heap.push_back({rows.begin(), &rows, can_move});
|
|
}
|
|
version = version->next();
|
|
}
|
|
boost::range::make_heap(_heap, _version_cmp);
|
|
move_to_next_row();
|
|
}
|
|
bool done() const {
|
|
return _current_row.empty();
|
|
}
|
|
// Return clustering key of the current row in source.
|
|
// Valid only when !is_dummy().
|
|
const clustering_key& key() const {
|
|
return _current_row[0].current_row->key();
|
|
}
|
|
position_in_partition_view position() const {
|
|
return _current_row[0].current_row->position();
|
|
}
|
|
bool is_dummy() const {
|
|
return bool(_current_row[0].current_row->dummy());
|
|
}
|
|
template<typename RowConsumer>
|
|
void consume_row(RowConsumer&& consumer) {
|
|
assert(!_current_row.empty());
|
|
// versions in _current_row are not ordered but it is not a problem
|
|
// due to the fact that all rows are continuous.
|
|
for (version& v : _current_row) {
|
|
if (!v.can_move) {
|
|
consumer(deletable_row(v.current_row->row()));
|
|
} else {
|
|
consumer(std::move(v.current_row->row()));
|
|
}
|
|
}
|
|
}
|
|
void remove_current_row_when_possible() {
|
|
assert(!_current_row.empty());
|
|
auto deleter = current_deleter<rows_entry>();
|
|
for (version& v : _current_row) {
|
|
if (v.can_move) {
|
|
v.rows->erase_and_dispose(v.current_row, deleter);
|
|
}
|
|
}
|
|
}
|
|
void move_to_next_row() {
|
|
_current_row.clear();
|
|
while (!_heap.empty() &&
|
|
(_current_row.empty() || _rows_cmp(*_current_row[0].current_row, *_heap[0].current_row) == 0)) {
|
|
boost::range::pop_heap(_heap, _version_cmp);
|
|
auto& curr = _heap.back();
|
|
_current_row.push_back({curr.current_row, curr.rows, curr.can_move});
|
|
++curr.current_row;
|
|
if (curr.current_row == curr.rows->end()) {
|
|
_heap.pop_back();
|
|
} else {
|
|
boost::range::push_heap(_heap, _version_cmp);
|
|
}
|
|
}
|
|
}
|
|
};
|
|
|
|
template<typename Func>
|
|
void partition_entry::with_detached_versions(Func&& func) {
|
|
partition_version* current = &*_version;
|
|
auto snapshot = _snapshot;
|
|
if (snapshot) {
|
|
snapshot->_version = std::move(_version);
|
|
snapshot->_entry = nullptr;
|
|
_snapshot = nullptr;
|
|
}
|
|
auto prev = std::exchange(_version, {});
|
|
|
|
auto revert = defer([&] {
|
|
if (snapshot) {
|
|
_snapshot = snapshot;
|
|
snapshot->_entry = this;
|
|
_version = std::move(snapshot->_version);
|
|
} else {
|
|
_version = std::move(prev);
|
|
}
|
|
});
|
|
|
|
func(current);
|
|
}
|
|
|
|
void partition_entry::apply_to_incomplete(const schema& s, partition_entry&& pe, const schema& pe_schema,
|
|
logalloc::region& reg)
|
|
{
|
|
if (s.version() != pe_schema.version()) {
|
|
partition_entry entry(pe.squashed(pe_schema.shared_from_this(), s.shared_from_this()));
|
|
entry.with_detached_versions([&] (partition_version* v) {
|
|
apply_to_incomplete(s, v, reg);
|
|
});
|
|
} else {
|
|
pe.with_detached_versions([&](partition_version* v) {
|
|
apply_to_incomplete(s, v, reg);
|
|
});
|
|
}
|
|
}
|
|
|
|
void partition_entry::apply_to_incomplete(const schema& s, partition_version* version,
|
|
logalloc::region& reg) {
|
|
partition_version& dst = open_version(s);
|
|
auto snp = read(reg, s.shared_from_this());
|
|
bool can_move = true;
|
|
auto current = version;
|
|
bool static_row_continuous = snp->static_row_continuous();
|
|
while (current) {
|
|
can_move &= !current->is_referenced();
|
|
dst.partition().apply(current->partition().partition_tombstone());
|
|
if (static_row_continuous) {
|
|
row& static_row = dst.partition().static_row();
|
|
if (can_move) {
|
|
static_row.apply(s, column_kind::static_column, std::move(current->partition().static_row()));
|
|
} else {
|
|
static_row.apply(s, column_kind::static_column, current->partition().static_row());
|
|
}
|
|
}
|
|
range_tombstone_list& tombstones = dst.partition().row_tombstones();
|
|
if (can_move) {
|
|
tombstones.apply_monotonically(s, std::move(current->partition().row_tombstones()));
|
|
} else {
|
|
tombstones.apply_monotonically(s, current->partition().row_tombstones());
|
|
}
|
|
current = current->next();
|
|
}
|
|
|
|
partition_entry::rows_iterator source(version, s);
|
|
partition_snapshot_row_cursor cur(s, *snp);
|
|
|
|
while (!source.done()) {
|
|
if (!source.is_dummy()) {
|
|
rows_entry* e = cur.ensure_entry_if_complete(source.position());
|
|
if (e) {
|
|
source.consume_row([&] (deletable_row&& row) {
|
|
e->row().apply_monotonically(s, std::move(row));
|
|
});
|
|
}
|
|
}
|
|
source.remove_current_row_when_possible();
|
|
source.move_to_next_row();
|
|
}
|
|
}
|
|
|
|
mutation_partition partition_entry::squashed(schema_ptr from, schema_ptr to)
|
|
{
|
|
mutation_partition mp(to);
|
|
mp.set_static_row_continuous(_version->partition().static_row_continuous());
|
|
for (auto&& v : _version->all_elements()) {
|
|
auto older = v.partition();
|
|
if (from->version() != to->version()) {
|
|
older.upgrade(*from, *to);
|
|
}
|
|
merge_versions(*to, mp, std::move(older));
|
|
}
|
|
return mp;
|
|
}
|
|
|
|
mutation_partition partition_entry::squashed(const schema& s)
|
|
{
|
|
return squashed(s.shared_from_this(), s.shared_from_this());
|
|
}
|
|
|
|
void partition_entry::upgrade(schema_ptr from, schema_ptr to)
|
|
{
|
|
auto new_version = current_allocator().construct<partition_version>(squashed(from, to));
|
|
auto old_version = &*_version;
|
|
set_version(new_version);
|
|
remove_or_mark_as_unique_owner(old_version);
|
|
}
|
|
|
|
lw_shared_ptr<partition_snapshot> partition_entry::read(logalloc::region& r,
|
|
schema_ptr entry_schema, partition_snapshot::phase_type phase)
|
|
{
|
|
with_allocator(r.allocator(), [&] {
|
|
open_version(*entry_schema, phase);
|
|
});
|
|
if (_snapshot) {
|
|
return _snapshot->shared_from_this();
|
|
} else {
|
|
auto snp = make_lw_shared<partition_snapshot>(entry_schema, r, this, phase);
|
|
_snapshot = snp.get();
|
|
return snp;
|
|
}
|
|
}
|
|
|
|
std::vector<range_tombstone>
|
|
partition_snapshot::range_tombstones(position_in_partition_view start, position_in_partition_view end)
|
|
{
|
|
partition_version* v = &*version();
|
|
if (!v->next()) {
|
|
return boost::copy_range<std::vector<range_tombstone>>(
|
|
v->partition().row_tombstones().slice(*_schema, start, end));
|
|
}
|
|
range_tombstone_list list(*_schema);
|
|
while (v) {
|
|
for (auto&& rt : v->partition().row_tombstones().slice(*_schema, start, end)) {
|
|
list.apply(*_schema, rt);
|
|
}
|
|
v = v->next();
|
|
}
|
|
return boost::copy_range<std::vector<range_tombstone>>(list.slice(*_schema, start, end));
|
|
}
|
|
|
|
std::vector<range_tombstone>
|
|
partition_snapshot::range_tombstones()
|
|
{
|
|
return range_tombstones(
|
|
position_in_partition_view::before_all_clustered_rows(),
|
|
position_in_partition_view::after_all_clustered_rows());
|
|
}
|
|
|
|
std::ostream& operator<<(std::ostream& out, const partition_entry& e) {
|
|
out << "{";
|
|
bool first = true;
|
|
if (e._version) {
|
|
const partition_version* v = &*e._version;
|
|
while (v) {
|
|
if (!first) {
|
|
out << ", ";
|
|
}
|
|
if (v->is_referenced()) {
|
|
out << "(*) ";
|
|
}
|
|
out << v->partition();
|
|
v = v->next();
|
|
first = false;
|
|
}
|
|
}
|
|
out << "}";
|
|
return out;
|
|
}
|
|
|
|
void partition_entry::evict() noexcept {
|
|
if (!_version) {
|
|
return;
|
|
}
|
|
for (auto&& v : versions()) {
|
|
if (v.is_referenced() && !v.back_reference().evictable()) {
|
|
break;
|
|
}
|
|
v.partition().evict();
|
|
}
|
|
current_allocator().invalidate_references();
|
|
}
|