mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 22:41:48 +00:00
1104eaa35e
Summary:
This PR adds support for `TimedPut` API. We introduced a new type `kTypeValuePreferredSeqno` for entries added to the DB via the `TimedPut` API.
The life cycle of such an entry on the write/flush/compaction paths are:
1) It is initially added to memtable as:
`<user_key, seq, kTypeValuePreferredSeqno>: {value, write_unix_time}`
2) When it's flushed to L0 sst files, it's converted to:
`<user_key, seq, kTypeValuePreferredSeqno>: {value, preferred_seqno}`
when we have easy access to the seqno to time mapping.
3) During compaction, if certain conditions are met, we swap in the `preferred_seqno` and the entry will become:
`<user_key, preferred_seqno, kTypeValue>: value`. This step helps fast track these entries to the cold tier if they are eligible after the sequence number swap.
On the read path:
A `kTypeValuePreferredSeqno` entry acts the same as a `kTypeValue` entry, the unix_write_time/preferred seqno part packed in value is completely ignored.
Needed follow ups:
1) The seqno to time mapping accessible in flush needs to be extended to cover the `write_unix_time` for possible `kTypeValuePreferredSeqno` entries. This also means we need to track these `write_unix_time` in memtable.
2) Compaction filter support for the new `kTypeValuePreferredSeqno` type for feature parity with other `kTypeValue` and equivalent types.
3) Stress test coverage for the feature
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12419
Test Plan: Added unit tests
Reviewed By: pdillinger
Differential Revision: D54920296
Pulled By: jowlyzhang
fbshipit-source-id: c8b43f7a7c465e569141770e93c748371ff1da9e
57 lines
1.8 KiB
C++
57 lines
1.8 KiB
C++
// Copyright (c) 2016-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
#pragma once
|
|
|
|
#include <cstdint>
|
|
|
|
#include "rocksdb/rocksdb_namespace.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
struct CompactionIterationStats {
|
|
// Compaction statistics
|
|
|
|
// Doesn't include records skipped because of
|
|
// CompactionFilter::Decision::kRemoveAndSkipUntil.
|
|
int64_t num_record_drop_user = 0;
|
|
|
|
int64_t num_record_drop_hidden = 0;
|
|
int64_t num_record_drop_obsolete = 0;
|
|
int64_t num_record_drop_range_del = 0;
|
|
int64_t num_range_del_drop_obsolete = 0;
|
|
// Deletions obsoleted before bottom level due to file gap optimization.
|
|
int64_t num_optimized_del_drop_obsolete = 0;
|
|
uint64_t total_filter_time = 0;
|
|
|
|
// Input statistics
|
|
// TODO(noetzli): The stats are incomplete. They are lacking everything
|
|
// consumed by MergeHelper.
|
|
uint64_t num_input_records = 0;
|
|
uint64_t num_input_deletion_records = 0;
|
|
uint64_t num_input_corrupt_records = 0;
|
|
uint64_t total_input_raw_key_bytes = 0;
|
|
uint64_t total_input_raw_value_bytes = 0;
|
|
|
|
// Single-Delete diagnostics for exceptional situations
|
|
uint64_t num_single_del_fallthru = 0;
|
|
uint64_t num_single_del_mismatch = 0;
|
|
|
|
// Blob related statistics
|
|
uint64_t num_blobs_read = 0;
|
|
uint64_t total_blob_bytes_read = 0;
|
|
uint64_t num_blobs_relocated = 0;
|
|
uint64_t total_blob_bytes_relocated = 0;
|
|
|
|
// TimedPut diagnostics
|
|
// Total number of kTypeValuePreferredSeqno records encountered.
|
|
uint64_t num_input_timed_put_records = 0;
|
|
// Number of kTypeValuePreferredSeqno records we ended up swapping in
|
|
// preferred seqno.
|
|
uint64_t num_timed_put_swap_preferred_seqno = 0;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|