Table of Contents |
---|
一、实验设置
实验目的
- 读一个TsFile的磁盘IO代价和CPU代价的大小比较
- 了解CPU代价里有没有突出的耗时瓶颈操作
IoTDB版本
- v0.13.1
实验环境
- CPU:Intel(R) Core(TM) i7-8700 CPU @ 3.20GHz,(6核12线程)
- L1 cache 284KB, L2 cache 1536KB, L3 cache 12MB
- 内存:16G
- 硬盘:1.8T HDD /dev/sdb1 mounted on /disk
- 操作系统:Ubuntu 16.04.7 LTS
...
实验设计
分析TsFile文件结构,然后把读取TsFile的耗时步骤进行分解和分类,最后进行实验测量统计。
TsFile结构
TsFile读耗时步骤分解与分类
耗时分类 | 耗时分解 |
(A)get_chunkMetadatas | (A)1_index_read_deserialize_MagicString_FileMetadataSize |
(A)2_index_read_deserialize_IndexRootNode_MetaOffset_BloomFilter | |
(A)3_2_index_read_deserialize_IndexRootNode_exclude_to_TimeseriesMetadata_forExactGet | |
(B)load_on_disk_chunk | (B)4_data_read_deserialize_ChunkHeader |
(B)5_data_read_ChunkData | |
(C)get_pageHeader | (C)6_data_deserialize_PageHeader |
(D-1)decompress_pageData | (D-1)7_1_data_ByteBuffer_to_ByteArray |
(D-1)7_2_data_decompress_PageDataByteArray | |
(D-1)7_3_data_ByteArray_to_ByteBuffer | |
(D-1)7_4_data_split_time_value_Buffer | |
(D-2)decode_pageData | (D-2)8_1_createBatchData |
(D-2)8_2_timeDecoder_hasNext | |
(D-2)8_3_timeDecoder_readLong | |
(D-2)8_4_valueDecoder_read | |
(D-2)8_5_checkValueSatisfyOrNot | |
(D-2)8_6_putIntoBatchData |
回答实验目的1:分析A、B、C、D-1、D-2类操作耗时占比,对比B类操作(磁盘IO代价所在)和D类操作(CPU代价主要所在)耗时
回答实验目的2:分析D-1操作内部各子步骤耗时占比、D-2操作内部各子步骤耗时占比
实验结论
- 本次实验使用的人工数据集不具有代表性:其编码压缩效率过低。甚至对于值列来说,和其它编码方式相比,采用PLAIN编码的空间大小是最小的。
- 在中车ZT11529数据集上的实验结果来看:
- 真实数据集的压缩率高、磁盘数据量相对小,此时【从磁盘加载Chunk数据的耗时】小于【解压缩和解码Page数据的耗时】
- D-1步骤内部的耗时瓶颈就是子步骤7_2_data_decompress_PageDataByteArray。注意:人工数据实验里发现另一个子步骤7_1_data_ByteBuffer_to_ByteArray(us)的占比也高,分析是因为人工数据压缩率很低,子步骤7_2_data_decompress_PageDataByteArray(us)耗时相对少,从而7_1_data_ByteBuffer_to_ByteArray(us)耗时占比相对偏高。
- D-1解压缩和D-2解码的空间压缩关系和耗时关系还有待探索
- 写数据的耗时可以也测量一下
- 注意RLE编码对于浮点数是有损的
实验设置
IoTDB版本
- v0.13.1
实验环境
- CPU:Intel(R) Core(TM) i7-8700 CPU @ 3.20GHz,(6核12线程)
- L1 cache 284KB, L2 cache 1536KB, L3 cache 12MB
- 内存:16G
- 硬盘:1.8T HDD /dev/sdb1 mounted on /disk
- 操作系统:Ubuntu 16.04.7 LTS
作图和csv部分截图如下所示。
RLTsFileReadCostBench用法
(1) 用人工数据写TsFile
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar WRITE_SYN [pagePointNum] [numOfPagesInChunk] [chunksWritten] [timeEncoding] [valueDataType] [valueEncoding] [compressionType] |
:用来标识是“写人工数据/写真实数据/读数据”中的“写人工数据”
pagePointNum(ppn)
:一个page内的点数numOfPagesInChunk(pic)
:一个chunk内的pages数chunksWritten(cw)
:写的chunks总数timeEncoding(te)
:时间戳列编码方式valueDataType(vt)
:值列数据类型valueEncoding(ve)
:值列编码方式compressionType(co)
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar WRITE_REAL [path_of_real_data_csv_to_write] [pagePointNum] [numOfPagesInChunk] [timeEncoding] [valueDataType] [valueEncoding] [compressionType] |
:用来标识是“写人工数据/写真实数据/读数据”中的“写真实数据”
path_of_real_data_csv_to_write
:用来写TsFile的真实数据集csv地址pagePointNum(ppn)
:一个page内的点数numOfPagesInChunk(pic)
:一个chunk内的pages数timeEncoding(te)
:时间戳列编码方式valueDataType(vt)
:值列数据类型valueEncoding(ve)
:值列编码方式compressionType(co)
(3) 读实验
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar READ [path_of_tsfile_to_read] [decomposeMeasureTime] [D_decompose_each_step] (timeEncoding) |
:用来标识是“写人工数据/写真实数据/读数据”中的“读数据”
path_of_tsfile_to_read
:要读取的TsFile地址decomposeMeasureTime
:FALSE
to measure the read process as a whole, in which caseD_decompose_each_step
is useless.TRUE
to measure the decomposed read process, and the decomposition granularity is controlled byD_decompose_each_step
.D_decompose_each_step
:WhendecomposeMeasureTime
isTRUE
,D_decompose_each_step=FALSE
to measure the "(D_1)decompress_pageData" and "(D_2)decode_pageData" steps without further deomposition,D_decompose_each_step=TRUE
to break down these two steps further and measure substeps inside.timeEncoding(te)
:IftimeEncoding
is not specified, TS_2DIFF will be used by default.timeEncoding
控制参数 | decomposeMeasureTime=FALSE | decomposeMeasureTime=TRUE & D_decompose_each_step=FALSE 用于分析A/B/C/D-1/D-2类操作耗时占比(&实验目标1) | |
---|---|---|---|
测量的最小单元步骤 | total_time(us) |
|
|
自动化脚本
- 输出:一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、一个读TsFile耗时结果csv文件(*readResult-T*csv
输入:见RLTsFileReadCostBench的写数据参数和读数据参数
输出:一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、一个读TsFile耗时结果csv文件(*readResult-T*csv
WRITE_READ_JAR_PATH
:RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar的地址Calculator_JAR_PATH
:把若干次重复读实验结果进行平均值和百分比计算的RLRepeatReadResultAvgPercCalculator-0.13.1-jar-with-dependencies.jar的地址FILE_NAME
:要读取的TsFile的地址decomposeMeasureTime
:见RLTsFileReadCostBench读数据参数D_decompose_each_step
:见RLTsFileReadCostBench读数据参数te
::见RLTsFileReadCostBench读数据参数REPEAT
:读实验重复次数
输出:
REPEAT个读TsFile耗时结果csv文件
*readResult-T*csv
一个把重复读实验结果横向拼接起来的csv文件
*readResult-combined.csv
一个把写结果和读结果拼接起来的csv文件
*allResult-combined.csv
一个把读结果取平均值并且按照不同粒度统计百分比的csv文件
工具地址:
WRITE_READ_JAR_PATH
:RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar的地址Calculator_JAR_PATH
:把若干次重复读实验结果进行平均值和百分比统计计算的RLRepeatReadResultAvgPercCalculator-0.13.1-jar-with-dependencies.jar的地址TOOL_PATH
:用于替换脚本中变量值的自动脚本工具RLtool.sh的地址READ_SCRIPT_PATH
:RLReadExpScripts.sh的地址
写数据参数:见RLTsFileReadCostBench写数据参数
读数据参数:见RLTsFileReadCostBench读数据参数
REPEAT
:读实验重复次数
输出:不同压缩方式下的一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、REPEAT个读TsFile耗时结果csv文件(*readResult-T*csv
)、一个把重复读实验结果横向拼接起来的csv文件(*readResult-combined.csv
)、一个把写结果和读结果拼接起来的csv文件(*allResult-combined.csv
)、一个把读结果取平均值并且按照不同粒度统计百分比的csv文件(*allResult-combined-processed.csv
其它类似,不再赘述。
实验具体结果
中车数据实验结果
改变压缩方式
RLCompressionRealExpScripts.sh
压缩方式 | GZIP | LZ4 | SNAPPY | UNCOMPRESSED |
dataset | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv |
pagePointNum(ppn) | 10000 | 10000 | 10000 | 10000 |
numOfPagesInChunk(pic) | 100 | 100 | 100 | 100 |
chunksWritten(cw) | 13 | 13 | 13 | 13 |
timeEncoding(te) | TS_2DIFF | TS_2DIFF | TS_2DIFF | TS_2DIFF |
valueDataType(vt) | DOUBLE | DOUBLE | DOUBLE | DOUBLE |
valueEncoding(ve) | GORILLA | GORILLA | GORILLA | GORILLA |
compression(co) | GZIP | LZ4 | SNAPPY | UNCOMPRESSED |
totalPointNum | 12780287 | 12780287 | 12780287 | 12780287 |
tsfileSize(MB) | 19.34862614 | 23.77741051 | 23.15641212 | 36.30773735 |
chunkDataSize_stats_mean(MB) | 1.515139659 | 1.86007007 | 1.813184341 | 2.837062438 |
compressedPageSize_stats_mean(B) | 15824.16667 | 19440.275 | 18948.69 | 29684.7575 |
uncompressedPageSize_stats_mean(B) | 29684.7575 | 29684.7575 | 29684.7575 | 29684.7575 |
timeBufferSize_stats_mean(B) | 11461.4625 | 11461.4625 | 11461.4625 | 11461.4625 |
valueBufferSize_stats_mean(B) | 18221.26833 | 18221.26833 | 18221.26833 | 18221.26833 |
[2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData | ||||
[Avg&Per] (A)get_chunkMetadatas | 87316.85010000001 us - 8.19883087518919% | 100289.6416 us - 12.59103802007131% | 89466.6045 us - 11.199530364576052% | 88760.777 us - 10.335699109318087% |
[Avg&Per] (B)load_on_disk_chunk | 160699.6025 us - 15.089285299443361% | 176784.88239999997 us - 22.19476647997349% | 105802.9384 us - 13.244531050378352% | 191518.85280000002 us - 22.301305860612082% |
[Avg&Per] (C)get_pageHeader | 2436.5129999999995 us - 0.22878239411203669% | 2198.3668000000007 us - 0.27599779517870476% | 2319.9517000000005 us - 0.29041416798711567% | 3134.228800000001 us - 0.3649635223062446% |
[Avg&Per] (D_1)decompress_pageData | 356587.5454999999 us - 33.482666568996265% | 31158.160799999983 us - 3.911805656191469% | 115629.7179 us - 14.474658381255693% | 29640.983400000016 us - 3.4515277590088287% |
[Avg&Per] (D_2)decode_pageData | 457950.96670000016 us - 43.000434862259155% | 486085.0215000002 us - 61.02639204858503% | 485623.25309999986 us - 60.790866035802786% | 545723.8052999998 us - 63.54650374875476% |
SUM | 1064991.4778 us | 796516.0731000002 us | 798842.4655999999 us | 858778.6472999998 us |
[3] D_1 compare each step inside | ||||
[Avg&Per] (D-1)7_1_data_ByteBuffer_to_ByteArray(us) | 1269.7615999999996 us - 0.36377892330196115% | 1808.5776999999991 us - 7.207505165727991% | 1687.9916000000003 us - 1.412377327892232% | 3197.6313 us - 41.86667970732365% |
[Avg&Per] |
RLTsFileReadCostBench用法
(1) 用人工数据写TsFile
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar WRITE_SYN [pagePointNum] [numOfPagesInChunk] [chunksWritten] [timeEncoding] [valueDataType] [valueEncoding] [compressionType] |
:用来标识是“写人工数据/写真实数据/读数据”中的“写人工数据”
pagePointNum(ppn)
:一个page内的点数numOfPagesInChunk(pic)
:一个chunk内的pages数chunksWritten(cw)
:写的chunks总数timeEncoding(te)
:时间戳列编码方式valueDataType(vt)
:值列数据类型valueEncoding(ve)
:值列编码方式compressionType(co)
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar WRITE_REAL [path_of_real_data_csv_to_write] [pagePointNum] [numOfPagesInChunk] [timeEncoding] [valueDataType] [valueEncoding] [compressionType] |
:用来标识是“写人工数据/写真实数据/读数据”中的“写真实数据”
path_of_real_data_csv_to_write
:用来写TsFile的真实数据集csv地址pagePointNum(ppn)
:一个page内的点数numOfPagesInChunk(pic)
:一个chunk内的pages数timeEncoding(te)
:时间戳列编码方式valueDataType(vt)
:值列数据类型valueEncoding(ve)
:值列编码方式compressionType(co)
(3) 读实验
Code Block | ||
---|---|---|
| ||
java -jar RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar READ [path_of_tsfile_to_read] [decomposeMeasureTime] [D_decompose_each_step] (timeEncoding) |
:用来标识是“写人工数据/写真实数据/读数据”中的“读数据”
path_of_tsfile_to_read
:要读取的TsFile地址decomposeMeasureTime
:FALSE
to measure the read process as a whole, in which caseD_decompose_each_step
is useless.TRUE
to measure the decomposed read process, and the decomposition granularity is controlled byD_decompose_each_step
.D_decompose_each_step
:WhendecomposeMeasureTime
isTRUE
,D_decompose_each_step=FALSE
to measure the "(D_1)decompress_pageData" and "(D_2)decode_pageData" steps without further deomposition,D_decompose_each_step=TRUE
to break down these two steps further and measure substeps inside.timeEncoding(te)
:IftimeEncoding
is not specified, TS_2DIFF will be used by default.timeEncoding
控制参数 | decomposeMeasureTime=FALSE | decomposeMeasureTime=TRUE & D_decompose_each_step=FALSE | ||||
---|---|---|---|---|---|---|
测量最小单元步骤 | total_time(us) | 345856.23130000004 us - 99.08569249502276% | 21247.39440000001 us - 84.67466169480036% | 116100.69619999993 us - 97.14384305311928% | 2432.4552000000012 us - 31.84820675254647% | |
[Avg&Per] (D-1)7_3_data_ByteArray_to_ByteBuffer(us) | 374.18470000000025 us - 0.10720162531460037% | 442.10720000000003 us - 1.761876157051776% | 424.26030000000026 us - 0.35498732863644405% | 421.1930000000002 us - 5.51469221169019% | ||
[Avg&Per] (D-1)7_4_data_split_time_value_Buffer(us)time_value_Buffer(us) | 1547.4220999999993 us - 0.443326956360674% | 1594.8989000000004 us - 6.355956982419887% | 1301.2614999999998 us - 1.0887922903520593% | 1586.372500000001 us - 20.770421328439692% | ||
[3] D_2 compare each step inside | ||||||
[Avg&Per] (D-2)8_1_createBatchData(us)(D-2)8_2_timeDecoder_hasNext(us)(D-2)8_3_timeDecoder_readLong(us) | 3430.8672 us - 0.22855030377902266% | 4174.8958 us - 0.275155541260775% | 3438.1465 us - 0.22874736939899784% | 3730.6205 us - 0.24721094086707432% | ||
[Avg&Per] (D-2)8_4_valueDecoder_read(us) (D-2)8_5_checkValueSatisfyOrNot(us)(D-2)8_6timeDecoder_putIntoBatchDatahasNext(us) |
结合实验目的,
- 目的1:decomposeMeasureTime=TRUE & D_decompose_each_step=FALSE:对比B类操作(磁盘IO代价所在)和D类操作(CPU代价主要所在)耗时
- 目的2:decomposeMeasureTime=TRUE & D_decompose_each_step=TRUE:分析D-1操作内部各子步骤耗时占比,分析D-2操作内部各子步骤耗时占比
自动化脚本
- 输出:一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、一个读TsFile耗时结果csv文件(*readResult-T*csv
输入:见RLTsFileReadCostBench的写数据参数和读数据参数
输出:一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、一个读TsFile耗时结果csv文件(*readResult-T*csv
WRITE_READ_JAR_PATH
:RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar的地址Calculator_JAR_PATH
:把若干次重复读实验结果进行平均值和百分比计算的RLRepeatReadResultAvgPercCalculator-0.13.1-jar-with-dependencies.jar的地址FILE_NAME
:要读取的TsFile的地址decomposeMeasureTime
:见RLTsFileReadCostBench读数据参数D_decompose_each_step
:见RLTsFileReadCostBench读数据参数te
::见RLTsFileReadCostBench读数据参数REPEAT
:读实验重复次数
输出:
REPEAT个读TsFile耗时结果csv文件
*readResult-T*csv
一个把重复读实验结果横向拼接起来的csv文件
*readResult-combined.csv
一个把写结果和读结果拼接起来的csv文件
*allResult-combined.csv
一个把读结果取平均值并且按照不同粒度统计百分比的csv文件
工具地址:
WRITE_READ_JAR_PATH
:RLTsFileReadCostBench-0.13.1-jar-with-dependencies.jar的地址Calculator_JAR_PATH
:把若干次重复读实验结果进行平均值和百分比统计计算的RLRepeatReadResultAvgPercCalculator-0.13.1-jar-with-dependencies.jar的地址TOOL_PATH
:用于替换脚本中变量值的自动脚本工具RLtool.sh的地址READ_SCRIPT_PATH
:RLReadExpScripts.sh的地址
写数据参数:见RLTsFileReadCostBench写数据参数
读数据参数:见RLTsFileReadCostBench读数据参数
REPEAT
:读实验重复次数
输出:不同压缩方式下的一个TsFile文件、一个TsFile空间统计结果文件(
*writeResult.csv
)、REPEAT个读TsFile耗时结果csv文件(*readResult-T*csv
)、一个把重复读实验结果横向拼接起来的csv文件(*readResult-combined.csv
)、一个把写结果和读结果拼接起来的csv文件(*allResult-combined.csv
)、一个把读结果取平均值并且按照不同粒度统计百分比的csv文件(*allResult-combined-processed.csv
其它类似,不再赘述。
二、实验结果
改变压缩方式
人工数据实验结果
234016.77980000002 us - 15.589238228946503% | 236135.9462 us - 15.56305048087338% | 235278.4135 us - 15.65358490817499% | 234469.6457 us - 15.537217392727715% | |
[Avg&Per] (D-2)8_3_timeDecoder_readLong(us) | 357893.9434 us - 23.841426880277478% | 360253.1425 us - 23.743262865502565% | 358341.1524 us - 23.84121675993312% | 363063.0738 us - 24.058508247673558% |
[Avg&Per] (D-2)8_4_valueDecoder_read(us) | 353821.6809 us - 23.570149451806063% | 359477.8899 us - 23.692168165422427% | 356440.4841 us - 23.714761161335133% | 355773.1939 us - 23.5754416723178% |
[Avg&Per] (D-2)8_5_checkValueSatisfyOrNot(us) | 223758.3096 us - 14.905861011513531% | 224938.2721 us - 14.825043539994219% | 224282.1638 us - 14.921980483485841% | 226053.6587 us - 14.979528915812129% |
[Avg&Per] (D-2)8_6_putIntoBatchData(us) | 328221.5562 us - 21.864774123677403% | 332305.597 us - 21.90131940694663% | 325251.7878 us - 21.639709317671908% | 325993.7043 us - 21.602092830601723% |
补充实验
时间戳和值都使用PLAIN编码,然后改变压缩。
RLCompressionRealExpScriptsRLCompressionSynExpScripts.sh
压缩方式 | GZIP | LZ4 | SNAPPY | UNCOMPRESSED | ||||
dataset | synthetic | synthetic | synthetic | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csvsynthetic | |
pagePointNum(ppn) | 10000 | 10000 | 10000 | 10000 | ||||
numOfPagesInChunk(pic) | 10001001000 | 100 | 10001001000 | 100 | ||||
chunksWritten(cw) | 101310 | 13 | 101310 | 13 | ||||
timeEncoding(te) | TS_2DIFF | TS_2DIFF | TS_2DIFF | PLAIN | PLAIN | PLAIN | PLAINTS_2DIFF | |
valueDataType(vt) | INT64DOUBLEINT64 | DOUBLE | INT64DOUBLEINT64 | DOUBLE | ||||
valueEncoding(ve) | PLAIN | PLAIN | PLAIN | PLAIN | ||||
compression(co) | GZIP | LZ4 | SNAPPY | UNCOMPRESSED | ||||
totalPointNum | 10000000012780287100000000 | 12780287 | 10000000012780287100000000 | 12780287 | ||||
tsfileSize(MB) | 76750.13128667578783 | 77074.844431971146107 | 76775.942390481546879 | 781195.42261510946026 | ||||
chunkDataSize_stats_mean(MB) | 763.71300761977135579 | 775.08436436846096277 | 765.7941264932730039 | 7815.1421661426517868 | ||||
compressedPageSize_stats_mean(B) | 8037541639.4186728917 | 8076461236.814447625 | 8046062145.4778918333 | 81874160003 | ||||
uncompressedPageSize_stats_mean(B) | 8187416000381874 | 160003 | 8187416000381874 | 160003 | ||||
timeBufferSize_stats_mean(B) | 1872800001872 | 80000 | 1872800001872 | 80000 | ||||
valueBufferSize_stats_mean(B) | 80000 | 80000 | 80000 | 80000 | ||||
total_time(us) | 2096685.5981 | 1244193.0404 | 1195582.1173 | 1895095.384 | ||||
[2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData | ||||||||
[Avg&Per] (A)get_chunkMetadatas | 10165486791.7566 3859 us - 04.9318259204986696%1844839300349514% | 86735100869.1136 9527 us - 18.1689451651044902%731470875680406%82918 | 99547.49919999999 05960000001 us - 17.0656107165107132%911992556094877%93896 | 88166.1409 6213 us - 14.2531889263513831%659966496653105% | ||||
[Avg&Per] (B)load_on_disk_chunk | 5949593349328.8917000005 55549999996 us - 5416.53739687304131%84222128306944% | 4849630452828.197000001 32 us - 6539.35936296194448%197572537012675%5086618 | 450015.179 7795 us - 6535.36966894765757%76721916082827% | 48513861155773.484999999 8993 us - 6461.74924062031137%08737716190697% | ||||
[Avg&Per] (C)get_pageHeader | 66132818.381399999991 293900000001 us - 0.060622054656159316%13587875585087916% | 71203913.158900000014 898699999998 us - 0.09595969816001626%3387935811871694% | 76923502.346500000014 114700000002 us - 0.09885667184764595%27834780402685505% | 76054450.696300000007 306 us - 0.10150975630087579%23521687180559223% | ||||
[Avg&Per] (D_1)decompress_pageData | 28594281350175.0031000106 8349000001 us - 2665.211160404158996%09619618668371% | 521804261417.2723000004 90119999985 us - 722.032452670194604%628768326063632%605202 | 395144.8143000009 6617 us - 731.777644443672276%40606698493612% | 498170173785.42259999976 97769999996 us - 69.648853201570805%185299626198828% | ||||
[Avg&Per] (D_2)decode_pageData | 1991910.319299996 us - 18.25899474764487% | 1954657.4198999994 us - 26.343279504596413% | 1998880.5966999987 us - 25.68821922031179% | 285009.94010000007 us - 13.74121984436101% | 336215.7518000001 us - 29.103394680056127% | 309969.7735 us - 24.636373494113883% | 469824.3798999997 us - 24.832139843435506% | |
SUM | 2074124.0103 | 1155245.8243999998 | 1258179.389 | 1892001.18419999962041517.9070999995 us - 27.247207495465567% | ||||
[3] D_1 compare each step inside | ||||||||
[Avg&Per] (D-1)7_1_data_ByteBuffer_to_ByteArray(us) | 659524312.37819999998 080999999998 us - 20.5136549346918415%3365746911741179% | 10880910247.34350000018 3701 us - 595.6896105506002%205625954425964% | 1081329355.35939999981 254500000003 us - 432.622622294156905%648386471251286% | 11076533088.11740000003 566800000015 us - 6356.813731447511664%71920599957147% | ||||
[Avg&Per] (D-1)7_2_data_decompress_PageDataByteArray(us) | 25546871274619.926599999 9271000002 us - 9799.36728361519128%48904214184739% | 68904183796.38600000006 93149999995 us - 3793.79892271446546%36815862249874% | 135345341381.91170000008 81159999996 us - 5496.601079805416944%64204980983628% | 5754721318.215800000035 842899999996 us - 3336.15396273496119%54397754446109% | ||||
[Avg&Per] (D-1)7_3_data_ByteArray_to_ByteBuffer(us) | 811454.8335000000624 68920000000026 us - 0.03094155721322126%03549026028736633% | 1239659.949800000022 1047999999998 us - 0.680200047933345%334822790636471% | 1184604.7460000000272 4583000000001 us - 0.47794876167766753%17111658310904862%1229 | 973.1439000000355 5250000000001 us - 01.7081314098345313%6687808013713306% | ||||
[Avg&Per] (D-1)7_4_data_split_time_value_Buffer(us) | 23121779.0582000000422 4489000000008 us - 0.08811989290364733%1388929066911369% | 33382148.2513999999974 4263999999994 us - 1.8312666870009688%091392632438828%3218 | 1902.3657999999955 0298000000007 us - 10.29834913874849%5384471358033915% | 40342956.201500000018 5653000000016 us - 25.3241744076926314%068035654596102% | ||||
[3] D_2 compare each step inside | ||||||||
[Avg&Per] (D-2)8_1_createBatchData(us) | 53843343.7852 3923 us - 0.053292019060348375%259976288059772% | 58483522.7599 578 us - 0.05759123169122766%27212097540020236% | 59133458.4963 9225 us - 0.058362326692940975%2672966393395521% | 60193730.3023 5984 us - 0.05943520403215091%2816327187407449% | ||||
[Avg&Per] (D-2)8_2_timeDecoder_hasNext(us) | 1859842232202.2956 511 us - 18.406444711361424%05565768873081%1862234 | 231677.7849 2947 us - 1817.336946086748988%897191037883086%1864092 | 231911.3926 8133 us - 1817.397368271414525%921548782382853%1857778 | 237390.6739 8697 us - 1817.343895858133802%921263258420133% | ||||
[Avg&Per] (D-2)8_3_timeDecoder_readLong(us) | 2074757254086.7936 67 us - 2019.533415498567617%75733129255225%2084700 | 255389.4377 3804 us - 2019.527508047369906%72896194244707%2063043 | 255976.8916 5501 us - 2019.360888969091857%78120978179259%2069930 | 261059.4964 1494 us - 2019.43870456313607%70804415658043% | ||||
[Avg&Per] (D-2)8_4_valueDecoder_read(us) | 1876012241634.952 0221 us - 18.56648209392724%78903535624908% | 1881471242640.5433999998 7293 us - 18.526365490982297%744122040429612% | 1877809242328.2412 9765 us - 18.532744562964893%726560376256852% | 1876843246610.1276 5964 us - 18.53214021585961%6172847590372% | ||||
[Avg&Per] (D-2)8_5_checkValueSatisfyOrNot(us) | 1780379230100.6374 908 us - 17.620020492363725%892240746329144% | 1780782231053.3133 5736 us - 17.534904586680103%849008259784295% | 1781949231043.2049 8535 us - 17.586668929952697%85447508020484% | 1780599235200.5789 0462 us - 17.5818216126948%755872210542634% | ||||
[Avg&Per] (D-2)8_6_putIntoBatchData(us) | 2507922324669.0072 8983 us - 2425.82034518471963%24575862807894% | 2540605330206.1784 1447 us - 25.016684556527476%508595744055732% | 2539577329318.912 78729999997 us - 25.063966939883077% | 2536332.2055 us - 25.044002546143567% |
RLCompressionRealExpScripts.sh
ZT11529传感器数据如下图所示,共12,780,287个点。
448909340023306% | 340641.1962 us - 25.715902896678855% |
- 可以看到,当时间戳列和值列都使用PLAIN编码之后,压缩负责了全部的压缩率,此时D-1操作和耗时占比有了明显提高;但是也可以看到,即便如此,除了GZIP之外的压缩方式的D-1耗时占比也没有增大到60%以上,D-2解码操作仍然有不小的基础耗时
改变值列编码方式
RLValueEncodingRealExpScripts.sh
编码方式 | GORILLA | PLAIN | RLE | TS_2DIFF | |||||||||
压缩方式 | GZIP | LZ4 | SNAPPY | UNCOMPRESSED | |||||||||
dataset | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | /disk/rl/zc_data/ZT11529.csv | |||||||||
pagePointNum(ppn) | 10000 | 10000 | 10000 | 10000 | |||||||||
numOfPagesInChunk(pic) | 100 | 100 | 100 | 100 | |||||||||
chunksWritten(cw) | 13 | 13 | 13 | 13 | |||||||||
timeEncoding(te) | TS_2DIFF | TS_2DIFF | TS_2DIFF | TS_2DIFF | |||||||||
valueDataType(vt) | DOUBLE | DOUBLE | DOUBLE | DOUBLE | |||||||||
valueEncoding(ve) | GORILLAGORILLA | PLAIN | GORILLARLEGORILLA | TS_2DIFF | |||||||||
compression(co) | GZIPSNAPPY | LZ4SNAPPY | SNAPPY | UNCOMPRESSEDSNAPPY | |||||||||
totalPointNum | 12780287 | 12780287 | 12780287 | 12780287 | |||||||||
tsfileSize(MB) | 1923.348626141564121223 | 26.7774105159960175 | 2322.1564121210147858 | 3620.3077373598550797 | |||||||||
chunkDataSize_stats_mean(MB) | 1.5151396598131843411 | 2.86007007081166744 | 1.813184341740072568 | 21.837062438642661015 | |||||||||
compressedPageSize_stats_mean(B) | 1582418948.1666769 | 1944021758.27561667 | 1894818182.6929917 | 2968417160.75758925 | |||||||||
uncompressedPageSize_stats_mean(B) | 29684.757529684 | 91463.75754891729684 | 25245.75759341729684 | 22210.757536417 | |||||||||
timeBufferSize_stats_mean(B) | 11461.4625 | 11461.4625 | 11461.4625 | 11461.4625 | |||||||||
valueBufferSize_stats_mean(B) | 18221.2683318221.26833 | 80000 | 1822113782.2683344518221 | 10746.26833875 | |||||||||
[2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData | [Avg&Per] (A)get_chunkMetadatas | 87316.85010000001 us - 8.19883087518919% | 100289.6416 us - 12.59103802007131% | 89466.6045 us - 11.199530364576052% | 88760.777 us - 10.335699109318087%)load in-memory PageData | ||||||||
[Avg&Per] (BA)load_on_disk_chunk | 160699.6025 us - 15.089285299443361% | 176784.88239999997 us - 22.19476647997349% | 105802.9384 us - 13.244531050378352% | get_chunkMetadatas | 88753.03020000001 us - 11.21274000219672% | 97256.88870000001 us - 12.181751942467722% | 84509.5108 us - 9.498496964807579% | 86370.7961 us - 11.6687579647861%191518.85280000002 us - 22.301305860612082% | |||||
[Avg&Per] (C)get_pageHeader | 2436.5129999999995 us - 0.22878239411203669% | 2198.3668000000007 us - 0.27599779517870476% | 2319.9517000000005 us - 0.29041416798711567% | B)load_on_disk_chunk | 105215.9241 us - 13.29260306229143% | 138228.6108 us - 17.313597737139155% | 139816.5536 us - 15.714765088895252% | 96826.5282 us - 13.081335047881257%3134.228800000001 us - 0.3649635223062446% | |||||
[Avg&Per] (D_1C)decompressget_pageDatapageHeader | 3565872352.5454999999 1583 us - 330.482666568996265%2971632563133493% | 311582625.160799999983 5312999999983 us - 30.911805656191469%328856613051254% | 1156293388.7179 6254999999987 us - 140.474658381255693%38086658793698225% | 296403159.983400000016 255499999999 us - 30.4515277590088287%4268177375109232% | |||||||||
[Avg&Per] (D_21)decodedecompress_pageData | 457950114457.96670000016 26139999992 us - 4314.000434862259155%460120522641777% | 486085182862.0215000002 35910000015 us - 6122.02639204858503%904124612107367% | 485623155021.25309999986 76800000004 us - 6017.790866035802786%42376424722015% | 545723120684.8052999998 50350000002 us - 6316.54650374875476%304565026949902% | |||||||||
[ | 3] D_1 compare each step inside[Avg&Per] (D-1_2)7_1_data_ByteBuffer_to_ByteArray(us) | 1269.7615999999996 us - 0.36377892330196115% | 1808.5776999999991 us - 7.207505165727991% | 1687.9916000000003 us - 1.412377327892232% | 3197.6313 us - 41.86667970732365%decode_pageData | 480759.0216999998 us - 60.73737315655672% | 377408.39589999994 us - 47.27166909523449% | 506978.10549999995 us - 56.982107111140046% | 433147.3443000001 us - 58.51852422287182% | ||||
SUM | 791537.3956999998 us | 798381.7858000002 us | 889714.5634 us | 740188.4276000002 | |||||||||
[3] D_1 compare each step inside | |||||||||||||
[Avg&Per] (D-1)7_21_data_ByteBuffer_decompressto_PageDataByteArrayByteArray(us) | 3458561754.23130000004 3673999999999 us - 991.08569249502276%6860113426598728% | 212472320.39440000001 3632000000002 us - 841.67466169480036%489795195953362% | 1161001825.69619999993 1960999999988 us - 971.14384305311928%548613686329812% | 24321607.4552000000012 3271999999997 us - 311.84820675254647%758246074195737% | |||||||||
[Avg&Per] (D-1)7_32_data_ByteArraydecompress_to_ByteBufferPageDataByteArray(us) | 374100527.18470000000025 56879999992 us - 096.10720162531460037%61067644486589% | 442151532.10720000000003 73299999998 us - 197.761876157051776%29198327791244% | 424113686.26030000000026 73430000001 us - 096.35498732863644405%4591326329927% | 42187212.1930000000002 82 us - 595.51469221169019%4016073295714% | |||||||||
[Avg&Per] (D-1)7_43_data_splitByteArray_timeto_value_BufferByteBuffer(us) | 1547431.4220999999993 9958999999999 us - 0.443326956360674%41516388607230165% | 1594468.8989000000004 2119000000003 us - 60.355956982419887%30061666178303303% | 1301474.2614999999998 28859999999975 us - 10.0887922903520593%4024169332984032% | 1586663.372500000001 3730000000002 us - 20.770421328439692% | [3] D_2 compare each step inside0.7256599483773118% | ||||||||
[Avg&Per] (D-2)8_1_createBatchData-1)7_4_data_split_time_value_Buffer(us) | 34301340.8672 373799999999 us - 01.22855030377902266%288148326401935% | 41741429.8958 1740000000002 us - 0.275155541260775%9176048643511714%3438 | 1873.1465 7816000000007 us - 01.22874736939899784%5898367473790769%3730 | 1932.6205 989900000001 us - 0.24721094086707432%2.1144866478555286% | |||||||||
[3] D_2 compare each step inside | |||||||||||||
[Avg&Per] (D-2)8_21_timeDecoder_hasNextcreateBatchData(us) | 2340163348.77980000002 9259 us - 150.589238228946503%2218271110091239%236135 | 3442.9462 3069 us - 150.56305048087338%24318767981262365%235278 | 3466.4135 6887 us - 150.65358490817499%22277034162258696%234469 | 3338.6457 6453 us - 150.537217392727715%22194982158403212% | |||||||||
[Avg&Per] (D-2)8_32_timeDecoder_readLonghasNext(us) | 357893235317.9434 741 us - 2315.841426880277478%587043790733997%360253 | 244839.1425 8323 us - 2317.743262865502565%29713023052909%358341 | 239308.1524 8755 us - 2315.84121675993312%37805224577913% | 363063240223.0738 005 us - 2415.058508247673558%969786637750962% | |||||||||
[Avg&Per] (D-2)8_43_valueDecodertimeDecoder_readreadLong(us) | 353821361562.6809 5392 us - 23.570149451806063%949282819264262%359477 | 363364.8899 4154 us - 2325.692168165422427%67050285597614% | 356440362143.4841 5815 us - 23.714761161335133%271443255687238% | 355773357833.1939 1113 us - 23.5754416723178%788389623148674% | |||||||||
[Avg&Per] (D-2)8_54_valueDecoder_checkValueSatisfyOrNotread(us) | 223758356325.3096 4946 us - 1423.905861011513531%602389962111484%224938 | 241625.2721 5526 us - 1417.825043539994219%07005192367858%224282 | 396438.1638 5566 us - 1425.921980483485841%475247513902037%226053 | 335421.6587 7093 us - 1422.979528915812129%298501890735768% | |||||||||
[Avg&Per] (D-2)8_65_putIntoBatchDatacheckValueSatisfyOrNot(us) | 328221225554.5562 2633 us - 2114.864774123677403%940327764084076%332305 | 232364.597 86419999998 us - 2116.90131940694663%415814695306036%325251 | 224510.7878 63450000001 us - 2114.639709317671908%4271133273284%325993 | 230332.7043 4743 us - 2115.602092830601723% |
...
312273986066641% |
[Avg&Per] (D-2)8_6_putIntoBatchData(us) |
...
- 人工数据实验里发现另一个子步骤7_1_data_ByteBuffer_to_ByteArray(us)的占比也高,其主要因为人工数据实验里数据压缩率很低,从而子步骤7_2_data_decompress_PageDataByteArray(us)耗时少,从而相对来说7_1_data_ByteBuffer_to_ByteArray(us)占比高了。
327591.9399 us - 21.699128552797042% | 329856.9807 us - 23.30331261469754% | 330303.223 us - 21.225373315680617% | 337085.3345 us - 22.409098040713936% |
人工数据实验结果
改变压缩方式
RLCompressionSynExpScripts.sh
压缩方式 | GZIP | LZ4 | SNAPPY | UNCOMPRESSED |
...
改变编码方式
人工数据实验结果
RLValueEncodingSynExpScripts.sh
编码方式 | GORILLA | PLAIN | RLE | TS_2DIFF | |||||
dataset | synthetic | synthetic | synthetic | synthetic | |||||
pagePointNum(ppn) | 10000 | 10000 | 10000 | 10000 | |||||
numOfPagesInChunk(pic) | 1000 | 1000 | 1000 | 1000 | |||||
chunksWritten(cw) | 10 | 10 | 10 | 10 | |||||
timeEncoding(te) | TS_2DIFF | TS_2DIFF | TS_2DIFF | TS_2DIFF | |||||
valueDataType(vt) | INT64 | INT64 | INT64 | INT64 | |||||
valueEncoding(ve) | GORILLAPLAIN | PLAIN | RLEPLAIN | TS_2DIFFPLAIN | |||||
compression(co) | UNCOMPRESSEDGZIPUNCOMPRESSED | LZ4 | UNCOMPRESSEDSNAPPY | UNCOMPRESSED | |||||
totalPointNum | 100000000 | 100000000 | 100000000 | 100000000 | |||||
tsfileSize(MB) | 805767.38128951312866 | 781770.42261518444319781 | 767.84223189423904 | 793781.32447054226151 | |||||
chunkDataSize_stats_mean(MB) | 8076.5380362471300761 | 7877.142166140843643678 | 76.184127817941264 | 7978.3323516814216614 | |||||
compressedPageSize_stats_mean(B) | 84386.25189 | 81874 | 80375.41867 | 80764.81444 | 80460.47789 | 81874 | |||
81918 | 83122 | uncompressedPageSize_stats_mean(B) | 84386.2518981874 | 81874 | 8191881874 | 8312281874 | |||
timeBufferSize_stats_mean(B) | 1872 | 1872 | 1872 | 1872 | |||||
valueBufferSize_stats_mean(B) | 82512.25189 | 80000 | 80044 | 81248 | 80000 | 80000 | 80000 | 80000 | |
[2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData | |||||||||
[Avg&Per] (A)get_chunkMetadatas | 101654.7566 us - 0.9318259204986696% | 86735.1136 us - 1.1689451651044902% | 82918.49919999999 us - 1.0656107165107132% | 93896.1409 us - 1.2531889263513831% | |||||
[Avg&Per] (B)load_on_disk_chunk | 5949593.8917000005 us - 54.53739687304131% | 4849630.197000001 us - 65.35936296194448% | 5086618.179 us - 65.36966894765757% | 4851386.484999999 us - 64.74924062031137% | [2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData|||||
[Avg&Per] (AC)get_chunkMetadataspageHeader | 913316613.98490000001 381399999991 us - 0.8580518676474486%060622054656159316% | 1009447120.7581 158900000014 us - 10.2939556377951902%09595969816001626% | 880987692.20449999999 346500000014 us - 0.9671805828234409%09885667184764595% | 882317605.2157 696300000007 us - 0.9257222461823116%10150975630087579% | |||||
[Avg&Per] (BD_1)load_on_disk_chunk | 5552645.935400001 us - 52.16637107440095% | 5170158.3812 us - 66.27343223726832% | 5270914.364100001 us - 57.866400973957255% | decompress_pageData | 2859428.0031000106 us - 26.211160404158996% | 521804.2723000004 us - 7.032452670194604% | 605202.8143000009 us - 7.777644443672276% | 498170.42259999976 us - 6.648853201570805%5526099.6186 us - 57.97985793317826% | |
[Avg&Per] (CD_2)getdecode_pageHeaderpageData | 81851991910.805399999992 319299996 us - 018.07690455451459878%25899474764487%7712 | 1954657.402700000001 4198999994 us - 026.09886107156476356%343279504596413%7813 | 1998880.90999999998 5966999987 us - 025.08578451820695045%68821922031179%7725 | 2041517.986500000003 9070999995 us - 0.08106107934716146%27.247207495465567% | |||||
[3] D_1 compare each step inside | |||||||||
[Avg&Per] (D-1)7_1)decompress_pageData | 548160.3352000009 us - 5.149893543905802% | 525441.0348000005 us - 6.7353412114264035% | 585036.2351000007 us - 6.422783415941812% | _data_ByteBuffer_to_ByteArray(us) | 65952.37819999998 us - 2.5136549346918415% | 108809.34350000018 us - 59.6896105506002% | 108132.35939999981 us - 43.622622294156905% | 110765.11740000003 us - 63.813731447511664%632154.6457000006 us - 6.632568914631739% | |
[Avg&Per] (D-1)7_2)decode_pageData | 4443785.968300003 us - 41.748778959531215% | 1996996.816400002 us - 25.598409841945312% | 3156902.088299994 us - 34.65785050907054% | 3276856.417400001 us - 34.38078982666053% | [3] D_1 compare each step inside_data_decompress_PageDataByteArray(us) | 2554687.926599999 us - 97.36728361519128% | 68904.38600000006 us - 37.79892271446546% | 135345.91170000008 us - 54.601079805416944% | 57547.215800000035 us - 33.15396273496119% |
[Avg&Per] (D-1)7_13_data_ByteBufferByteArray_to_ByteArrayByteBuffer(us) | 110421811.72189999989 8335000000624 us - 640.93156378407389%03094155721322126% | 1096871239.91739999971 949800000022 us - 630.92643734398307%680200047933345% | 1136581184.35759999987 7460000000272 us - 620.901942587101885%47794876167766753% | 1091871229.47799999996 1439000000355 us - 630.08420663361515%7081314098345313% | |||||
[Avg&Per] (D-1)7_24_data_split_time_decompressvalue_PageDataByteArrayBuffer(us) | 546242312.26410000002 0582000000422 us - 320.12084386602246%08811989290364733% | 570953338.555900000094 2513999999974 us - 331.27545607007074%8312666870009688% | 621643218.880499999985 3657999999955 us - 341.403908579311135%29834913874849%59072 | 4034.25890000005 201500000018 us - 34.12961499817788%2.3241744076926314% | |||||
[3] D_2 compare each step inside | |||||||||
[Avg&Per] (D-12)78_3_data_ByteArray_to_ByteBuffer1_createBatchData(us) | 11795384.3427000000347 7852 us - 0.6934918640164246%053292019060348375% | 12345848.10400000004 7599 us - 0.7192394012210651%05759123169122766% | 10325913.115900000022 4963 us - 0.5712038820191121%058362326692940975% | 11936019.2719000000652 3023 us - 0.6894253122110825%05943520403215091% | |||||
[Avg&Per] (D-12)78_42_data_split_time_value_BuffertimeDecoder_hasNext(us) | 38331859842.2921999999994 2956 us - 218.254100485887217%406444711361424%3567 | 1862234.0158000000133 7849 us - 218.0788671847251163%336946086748988%3835 | 1864092.9775000000177 3926 us - 218.122944951567873%397368271414525%3629 | 1857778.1045000000054 6739 us - 218.0967530559958814%343895858133802% | |||||
[ | 3] D_2 compare each step inside[Avg&Per] (D-2)8_3_1timeDecoder_createBatchDatareadLong(us) | 60082074757.9294 7936 us - 020.04720551599260821%533415498567617%6005 | 2084700.094 4377 us - 020.058953749593284185%527508047369906%9136 | 2063043.1988 8916 us - 020.07959246314858166%360888969091857%6219 | 2069930.250599999999 4964 us - 020.053213386787106826%43870456313607% | ||||
[Avg&Per] (D-2)8_24_timeDecodervalueDecoder_hasNextread(us) | 17950671876012.4479 952 us - 1418.10186066084482%56648209392724% | 18626311881471.8749 5433999998 us - 18.285997377780266%526365490982297% | 18051001877809.2815999999 2412 us - 1518.725618584694368%532744562964893%1838661 | 1876843.8702 1276 us - 1518.732028111177547%53214021585961% | |||||
[Avg&Per] (D-2)8_35_timeDecoder_readLongcheckValueSatisfyOrNot(us) | 20736151780379.2138 6374 us - 1617.290102549307967%620020492363725% | 20894931780782.8765 3133 us - 2017.513167449482335%534904586680103% | 20634691781949.3846 2049 us - 17.976470800088325%586668929952697% | 21720291780599.5514 5789 us - 1817.58440125112089%5818216126948% | |||||
[Avg&Per] (D-2)8_46_valueDecoder_readputIntoBatchData(us) | 4636195.4124 us - 36.42146247963989% | 1880348.902 us - 18.459930571697104% | 3352494.9242 us - 29.206164899804453% | 3364558.2458 us - 28.787960289219587% | |||||
[Avg&Per] (D-2)8_5_checkValueSatisfyOrNot(us) | 1724239.435 us - 13.545443257159627% | 1784205.2864 us - 17.516060810611705% | 1723128.802 us - 15.01150190311584% | 1780807.3196 us - 15.237010821076382% | |||||
[Avg&Per] (D-2)8_6_putIntoBatchData(us) | 2494168.5891 us - 19.59392553705509% | 2563425.3348 us - 25.165890040835308% | 2525393.9444 us - 22.000651349148434% | 2525103.5280999998 us - 21.605386140618513% |
- 总的来说,使用的人工数据集不太好,其随机生成的取值,编码压缩效率不高,甚至PLAIN编码的空间是最小的
RLValueEncodingRealExpScripts.sh
ZT11529传感器数据如下图所示,共12,780,287个点。
2507922.0072 us - 24.82034518471963% | 2540605.1784 us - 25.016684556527476% | 2539577.912 us - 25.063966939883077% | 2536332.2055 us - 25.044002546143567% |
改变值列编码方式
RLValueEncodingSynExpScripts.sh
编码方式 | GORILLA | PLAIN | RLE | TS_2DIFF | ||||||||
dataset | synthetic | synthetic | synthetic | synthetic | ||||||||
pagePointNum(ppn) | 10000 | 10000 | 10000 | 10000 | ||||||||
numOfPagesInChunk(pic) | 1000 | 1000 | 1000 | 1000 | ||||||||
chunksWritten(cw) | 10 | 10 | 10 | 10 | ||||||||
timeEncoding(te) | TS_2DIFF | TS_2DIFF | TS_2DIFF | TS_2DIFF | ||||||||
valueDataType(vt) | INT64 | INT64 | INT64 | INT64 | ||||||||
valueEncoding(ve)编码方式GORILLAPLAINRLETS_2DIFF | GORILLA | PLAIN | RLE | TS_2DIFF | ||||||||
dataset | pagePointNumcompression(ppnco) | numOfPagesInChunk(pic) | chunksWritten(cw) | timeEncoding(te) | valueDataType(vt) | valueEncoding(ve) | compression(co) | UNCOMPRESSED | UNCOMPRESSED | UNCOMPRESSED | UNCOMPRESSED | |
totalPointNum | 100000000 | 100000000 | 100000000 | 100000000totalPointNum | ||||||||
tsfileSize(MB) | 805.3812895 | 781.4226151 | 781.8422318 | 793.3244705 | ||||||||
chunkDataSize_stats_mean(MB)(MB) | 80.53803624 | 78.14216614 | 78.18412781 | 79.33235168 | ||||||||
compressedPageSize_stats_mean(B) | 84386.25189 | 81874 | 81918 | 83122 | ||||||||
uncompressedPageSize_stats_mean(B) | 84386.25189 | 81874 | 81918 | 83122 | ||||||||
timeBufferSize_stats_mean(B) | 1872 | 1872 | 1872 | 1872 | ||||||||
valueBufferSize_stats_mean(B) | 82512.25189 | 80000 | 80044 | 81248 | ||||||||
[2] category: (A)get ChunkStatistic->(B)load on-disk Chunk->(C)get PageStatistics->(D)load in-memory PageData | ||||||||||||
[Avg&Per] (A)get_chunkMetadatasA)get_chunkMetadatas | 91331.98490000001 us - 0.8580518676474486% | 100944.7581 us - 1.2939556377951902% | 88098.20449999999 us - 0.9671805828234409% | 88231.2157 us - 0.9257222461823116% | ||||||||
[Avg&Per] (B)load_on_disk_chunk | 5552645.935400001 us - 52.16637107440095% | 5170158.3812 us - 66.27343223726832% | 5270914.364100001 us - 57.866400973957255% | 5526099.6186 us - 57.97985793317826% | ||||||||
[Avg&Per] (C)get_pageHeader)get_pageHeader | 8185.805399999992 us - 0.07690455451459878% | 7712.402700000001 us - 0.09886107156476356% | 7813.90999999998 us - 0.08578451820695045% | 7725.986500000003 us - 0.08106107934716146% | ||||||||
[Avg&Per] (D_1)decompress_pageData | 548160.3352000009 us - 5.149893543905802% | 525441.0348000005 us - 6.7353412114264035% | 585036.2351000007 us - 6.422783415941812% | 632154.6457000006 us - 6.632568914631739% | ||||||||
[Avg&Per] (D_2)decode_pageData_2)decode_pageData | 4443785.968300003 us - 41.748778959531215% | 1996996.816400002 us - 25.598409841945312% | 3156902.088299994 us - 34.65785050907054% | 3276856.417400001 us - 34.38078982666053% | ||||||||
[3] D_1 compare each step inside | ||||||||||||
[Avg&Per] (D-1)7_1_data_ByteBuffer_to_ByteArray(us) | 110421.72189999989 us - 64.93156378407389% | 109687.91739999971 us - 63.92643734398307% | 113658.35759999987 us - 62.901942587101885% | 109187.47799999996 us - 63.08420663361515% | ||||||||
[Avg&Per] (D-1)7_2_data_decompress_PageDataByteArray(us)decompress_PageDataByteArray(us) | 54624.26410000002 us - 32.12084386602246% | 57095.555900000094 us - 33.27545607007074% | 62164.880499999985 us - 34.403908579311135% | 59072.25890000005 us - 34.12961499817788% | ||||||||
[Avg&Per] (D-1)7_3_data_ByteArray_to_ByteBuffer(us) | 1179.3427000000347 us - 0.6934918640164246% | 1234.10400000004 us - 0.7192394012210651% | 1032.115900000022 us - 0.5712038820191121% | 1193.2719000000652 us - 0.6894253122110825% | ||||||||
[Avg&Per] (D-1)7_4_data_split_time_value_Buffer(us)_Buffer(us) | 3833.2921999999994 us - 2.254100485887217% | 3567.0158000000133 us - 2.0788671847251163% | 3835.9775000000177 us - 2.122944951567873% | 3629.1045000000054 us - 2.0967530559958814% | ||||||||
[3] D_2 compare each step inside | ||||||||||||
[Avg&Per] (D-2)8_1_createBatchData(us) | 6008.9294 us - 0.04720551599260821% | 6005.094 us - 0.058953749593284185% | 9136.1988 us - 0.07959246314858166% | 6219.250599999999 us - 0.053213386787106826% | ||||||||
[Avg&Per] (D-2)8_2_timeDecoder_hasNext(us)timeDecoder_hasNext(us) | 1795067.4479 us - 14.10186066084482% | 1862631.8749 us - 18.285997377780266% | 1805100.2815999999 us - 15.725618584694368% | 1838661.8702 us - 15.732028111177547% | ||||||||
[Avg&Per] (D-2)8_3_timeDecoder_readLong(us) | 2073615.2138 us - 16.290102549307967% | 2089493.8765 us - 20.513167449482335% | 2063469.3846 us - 17.976470800088325% | 2172029.5514 us - 18.58440125112089% | ||||||||
[Avg&Per] (D-2)8_4_valueDecoder_read(us)read(us) | 4636195.4124 us - 36.42146247963989% | 1880348.902 us - 18.459930571697104% | 3352494.9242 us - 29.206164899804453% | 3364558.2458 us - 28.787960289219587% | ||||||||
[Avg&Per] (D-2)8_5_checkValueSatisfyOrNot(us) | 1724239.435 us - 13.545443257159627% | 1784205.2864 us - 17.516060810611705% | 1723128.802 us - 15.01150190311584% | 1780807.3196 us - 15.237010821076382% | ||||||||
[Avg&Per] (D-2)8_6_putIntoBatchData(us) | 2494168.5891 us - 19.59392553705509% | 2563425.3348 us - 25.165890040835308% | 2525393.9444 us - 22.000651349148434% | 2525103.5280999998 us - 21.605386140618513% |