Skip to content

Instantly share code, notes, and snippets.

View mdcallag's full-sized avatar
🎯
Focusing

Mark Callaghan mdcallag

🎯
Focusing
View GitHub Profile
Level Files Size(MB) Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) Comp(cnt) Avg(sec) Stall(cnt) KeyIn KeyDrop
---------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 206 0.8 0.0 0.0 0.0 468.8 468.8 0.0 0.0 0.0 38.1 12589 6968 1.807 3291 0 0
L1 1/0 69 0.5 0.0 0.0 0.0 0.0 0.0 468.6 0.0 0.0 0.0 0 0 0.000 0 0 0
L2 14/0 964 0.9 0.0 0.0 0.0 0.0 0.0 468.5 0.0 0.0 0.0 0 0 0.000 0 0 0
L3 118/0 8126 1.0 0.0 0.0 0.0 0.0 0.0 467.6 0.0 0.0 0.0 0 0 0.000 0 0 0
L4 951/0 65520 1.0
merge QPS for 1, 4, 16, 32 threads
ops/sec mb/sec L0_GB Sum_GB W-Amp W-MB/s usec/op p50 p75 p99 p99.9 p99.99 Uptime Stall-time Stall% Test
86694 34.7 123.6 2038.8 16.4 589.2 11.5 6.3 7.8 172 185 234 3543 00:18:23.863 31.2 mergerandom.t1.s0
84998 34.0 121.4 2028.8 16.7 586.3 11.8 43.4 51.3 194 240 430 3543 00:04:23.355 7.4 mergerandom.t4.s0
88910 35.6 127.1 2073.9 16.3 598.3 11.2 150.0 199.0 345 428 1484 3549 00:09:32.971 16.1 mergerandom.t16.s0
91949 36.8 131.6 2069.3 15.7 596.0 10.9 322.8 393.4 608 917 4063 3555 00:10:41.759 18.1 mergerandom.t32.s0
read QPS with 1 merge and 1, 4, 16, 32 point read threads
ops/sec mb/sec L0_GB Sum_GB W-Amp W-MB/s usec/op p50 p75 p99 p99.9 p99.99 Uptime Stall-time Stall% Test
6048 2.4 13.2 211.7 16.0 61.1 165.3 139.4 160.7 959
ops/sec mb/sec L0_GB Sum_GB W-Amp W-MB/s usec/op p50 p75 p99 p99.9 p99.99 Uptime Stall-time Stall% Test
658214 263.6 860.7 860.7 1.0 271.3 1.5 0.6 0.8 2 5 7 3248 00:23:30.171 43.4 bulkload
15638 489.0 553.1 553.1 1.0 269.0 63.9 18.4 19.7 29 254 176980 2105 00:24:4.416 68.6 fillseq.v32768
1125383 450.8 463.6 463.6 1.0 255.2 0.9 0.6 0.8 2 5 9 1860 00:00:28.256 1.5 fillseq.v400
./db_bench --benchmarks=fillseq --use_existing_db=0 --sync=0 --db=ldb --num=1048576 --value_size=800 --cache_size=34359738368 --compression_ratio=0.5 --write_buffer_size=2097152 --histogram=1 --bloom_bits=10 --open_files=20480 --threads=1 --seed=1429748618
./db_bench --benchmarks=overwrite --use_existing_db=1 --sync=0 --db=ldb --num=1048576 --value_size=800 --cache_size=34359738368 --compression_ratio=0.5 --write_buffer_size=2097152 --histogram=1 --bloom_bits=10 --open_files=20480 --threads=1 --seed=1429748625
./db_bench --benchmarks=readwhilewriting --use_existing_db=1 --sync=0 --db=ldb --num=1048576 --value_size=800 --cache_size=34359738368 --compression_ratio=0.5 --write_buffer_size=2097152 --histogram=1 --bloom_bits=10 --open_files=20480 --threads=1 --writes_per_second=1000 --seed=1429748674
./db_bench --benchmarks=readwhilewriting --use_existing_db=1 --sync=0 --db=ldb --num=1048576 --value_size=800 --cache_size=34359738368 --compression_ratio=0.5 --write_buffer_size=2097152 --histogram=1 --bloom_bits=1
./db_bench --benchmarks=fillseq --use_existing_db=0 --sync=0 --db=ldb --wal_dir=/txlogs --disable_data_sync=0 --num=1048576 --num_levels=6 --key_size=20 --value_size=800 --block_size=16384 --cache_size=34359738368 --cache_numshardbits=4 --compression_type=snappy --min_level_to_compress=0 --compression_ratio=0.5 --level_compaction_dynamic_level_bytes=true --bytes_per_sync=2097152 --hard_rate_limit=3 --rate_limit_delay_max_milliseconds=1000000 --write_buffer_size=134217728 --max_write_buffer_number=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_grandparent_overlap_factor=8 --max_bytes_for_level_multiplier=8 --statistics=1 --stats_per_interval=1 --stats_interval_seconds=60 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=20480 --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=12 --level0_stop_writes_trigger=20 --max_background_compactions=16 --max_background_flushes=7 --min_
** Compaction Stats [default] **
Level Files Size(MB) Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) Comp(cnt) Avg(sec) Stall(cnt) KeyIn KeyDrop
---------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 14/11 934 0.8 0.0 0.0 0.0 709.8 709.8 0.0 0.0 0.0 114.9 6326 10892 0.581 14503 0 0
L3 6/6 597 0.0 1312.8 709.2 603.5 1297.2 693.6 0.0 1.8 102.3 101.1 13141 966 13.604 0 1674M 36M
L4 68/3 5812 1.0 4130.4 694.2 3436.3 4047.9 611.6 0.3 5.8 108.0 105.9 39153 5450 7.184 0 1640M 194M
L5 370/0 44831 0.0 3894.4 611.6 3282.8 3282.8 -0.0 0.0 5.4 118.2 99.7 33725 4804 7.020 0 1444M 1445M
./db_bench --benchmarks=fillseq --use_existing_db=0 --sync=0 --db=ldb --wal_dir=/txlogs --disable_data_sync=0 --num=1048576 --num_levels=6 --key_size=20 --value_size=800 --block_size=16384 --cache_size=34359738368 --cache_numshardbits=4 --compression_type=snappy --min_level_to_compress=0 --compression_ratio=0.5 --level_compaction_dynamic_level_bytes=true --bytes_per_sync=2097152 --hard_rate_limit=3 --rate_limit_delay_max_milliseconds=1000000 --write_buffer_size=134217728 --max_write_buffer_number=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_grandparent_overlap_factor=8 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=0 --stats_interval_seconds=60 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=20480 --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=12 --level0_stop_writes_trigger=20 --max_background_compactions=16 --max_background_flushes=7 --min_
1M keys, 4kb values 50% compressible, merge operator was "put"
The "Test" column has the test name, number of threads (t1, t2, t4, t8, t16, t32 for 1,2,4,8,16,32 threads) and s0 means "sync=0".
I don't list results
Notes:
* overwrite and mergerandom have similar ops/sec rates. overwrite is slightly faster and I assume that is because compaction is cheaper
from not handling merges.
* overwrite and mergerandom reach peak throughput at 1 thread when sync=0.
1M keys, 4kb values 50% compressible, merge operator was "put"
The "Test" column has the test name, number of threads (t1, t2, t4, t8, t16, t32 for 1,2,4,8,16,32 threads) and s0 means "sync=0".
I don't list results
Notes:
* overwrite and mergerandom have similar ops/sec rates. overwrite is slightly faster and I assume that is because compaction is cheaper
from not handling merges.
* overwrite and mergerandom reach peak throughput at 1 thread when sync=0.
2B keys, 400b values 50% compressible. This shows better throughput with concurrency when sync=1
with sync=0
ops/sec mb/sec L0_GB Sum_GB W-Amp W-MB/s usec/op p50 p75 p99 p99.9 p99.99 Uptime Stall-time Stall% Test
91417 36.6 130.4 2132.9 16.3 616.4 10.9 5.7 7.0 172 183 232 3543 00:19:56.100 33.8 overwrite.t1.s0
88425 35.4 126.5 2099.0 16.5 606.3 11.3 42.3 50.6 189 234 447 3545 00:03:19.459 5.6 overwrite.t4.s0
91574 36.7 130.9 2146.3 16.3 619.8 10.9 148.1 187.7 340 419 1738 3546 00:07:20.348 12.4 overwrite.t16.s0
95147 38.1 136.4 2149.5 15.7 619.3 10.5 307.7 379.3 589 929 4282 3554 00:08:14.198 13.9 overwrite.t32.s0