mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-03 18:45:35 +00:00
discord9
ba0f7acd93
* feat(mito2): add opt-in byte stream split encoding Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(mito2): correct float encoding checks Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(compat): cover float SST encoding Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(mito2): compile float encoding tests Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(mito2): release parquet test writer Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(mito2): register float test primary key Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(mito2): verify BSS write lifecycles Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(metric-engine): verify BSS physical SST Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(mito2): verify bulk BSS lifecycle Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(mito2): compile bulk BSS test Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * refactor(mito2): narrow bulk encoding constructors Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(compat): accept generated float upgrade output Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(compat): accept generated float downgrade output Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * refactor(mito2): narrow bulk encoding builder Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(perf): add default versus BSS storage comparison Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(perf): align BSS reader benchmarks with prior study Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(perf): parse current read benchmark averages Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(perf): retain default float encoding in direct SST fixtures Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(perf): isolate BSS user SSTs and benchmark every file Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * docs(perf): record measured BSS storage and reader tradeoffs Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * docs(perf): expose warm scan variability and evidence limits Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * docs(perf): clarify BSS baseline and storage measurement scope Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(perf): model bounded mixed integer and fractional metric series Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * docs(perf): report bounded mixed BSS measurements and query regressions Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * docs(perf): qualify timings affected by concurrent host builds Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * test(perf): include float BSS comparison in default regression cases Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> * fix(perf): omit unsupported float encoding option from baseline setup Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> --------- Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com>
84 lines
2.7 KiB
TOML
84 lines
2.7 KiB
TOML
# Default all-group default-versus-BSS storage and warmed-query comparison.
|
|
|
|
[case]
|
|
name = "sst_float_bss"
|
|
description = "Compare default and byte-stream-split floating-point SST bytes and warmed value-scanning query latency with bounded 95/5 per-series DOUBLE values"
|
|
|
|
[scenario]
|
|
kind = "prom_remote_write_then_query"
|
|
|
|
[scenario.remote_write]
|
|
database = "public"
|
|
metric = "sst_float_bss"
|
|
physical_table = "sst_float_bss_physical"
|
|
series_count = 1000
|
|
samples_per_series = 4320
|
|
sample_chunk_size = 1440
|
|
flush_every_sample_chunks = 1
|
|
start_unix_millis = 1_704_067_200_000 # 2024-01-01T00:00:00Z
|
|
step_millis = 60000
|
|
chunk_series_count = 128
|
|
timeout_seconds = 600
|
|
visibility_timeout_seconds = 300
|
|
|
|
# Omit the default encoding from base setup because older binaries do not recognize it.
|
|
# The high shared TWCS trigger avoids compaction changing the three-flush layout.
|
|
base_setup_sql = [
|
|
"CREATE TABLE sst_float_bss_physical (greptime_timestamp TIMESTAMP TIME INDEX, greptime_value DOUBLE) ENGINE=metric WITH ('physical_metric_table'='', 'compaction.twcs.trigger_file_num'='100')",
|
|
]
|
|
candidate_setup_sql = [
|
|
"CREATE TABLE sst_float_bss_physical (greptime_timestamp TIMESTAMP TIME INDEX, greptime_value DOUBLE) ENGINE=metric WITH ('physical_metric_table'='', 'experimental_sst_float_field_encoding'='byte_stream_split', 'compaction.twcs.trigger_file_num'='100')",
|
|
]
|
|
|
|
[scenario.remote_write.value]
|
|
# Synthetic, not empirical: 95% integral and 5% nonintegral series vary
|
|
# smoothly within deterministic per-series ranges; series are not a global monotonic counter.
|
|
pattern = "bounded_mixed"
|
|
base = 0
|
|
step = 1
|
|
cardinality = 1000
|
|
seed = 42
|
|
mixed_every = 20
|
|
run_length = 60
|
|
|
|
[scenario.remote_write.prom_store]
|
|
pending_rows_flush_interval = "1s"
|
|
max_batch_rows = 100000
|
|
|
|
[scenario.remote_write.storage]
|
|
root_suffix = "data/greptime/public"
|
|
column = "greptime_value"
|
|
min_files = 1
|
|
min_files_with_column = 1
|
|
max_candidate_total_file_size_regression_pct = -5.0
|
|
|
|
[scenario.remote_write.read_bench]
|
|
enabled = true
|
|
parquetbench = true
|
|
scanbench = true
|
|
iterations = 7
|
|
projection = ["greptime_value"]
|
|
parquet_reader = "direct"
|
|
scan_scanner = "seq"
|
|
parallelism = 1
|
|
|
|
[[scenario.queries]]
|
|
name = "sum_all_values"
|
|
kind = "sql"
|
|
query = "SELECT sum(greptime_value) FROM sst_float_bss"
|
|
warmup = 3
|
|
iterations = 15
|
|
|
|
[scenario.queries.thresholds]
|
|
max_candidate_latency_regression_pct = 25
|
|
|
|
[[scenario.queries]]
|
|
name = "hourly_sum_values"
|
|
kind = "sql"
|
|
query = "SELECT date_bin(INTERVAL '1 hour', greptime_timestamp) AS time_window, sum(greptime_value) FROM sst_float_bss WHERE greptime_timestamp >= TIMESTAMP '2024-01-01 00:00:00' AND greptime_timestamp < TIMESTAMP '2024-01-04 00:00:00' GROUP BY time_window ORDER BY time_window"
|
|
warmup = 3
|
|
iterations = 15
|
|
|
|
[scenario.queries.thresholds]
|
|
max_candidate_latency_regression_pct = 25
|