KPTI + Retpoline Ubuntu Linux Benchmarks Comparison

Tests by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1801096-FO-KPTIRETPO87
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Comparison
Transpose Comparison

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 4.14.0 Stock: i9-7980XE
January 08 2018
 
KPTI + Retpoline: i9-7980XE
January 08 2018
 
Linux 4.14.0 Stock: E3-1280 v5
January 08 2018
 
KPTI + Retpoline: E3-1280 v5
January 08 2018
 
Linux 4.14.0 Stock: i7-6800K
January 09 2018
 
KPTI + Retpoline: i7-6800K
January 09 2018
 
Invert Behavior (Only Show Selected Data)
 

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDisplay DriverLinux 4.14.0 StockKPTI + RetpolineLinux 4.14.0 StockKPTI + RetpolineLinux 4.14.0 StockKPTI + Retpoline i9-7980XE i9-7980XE E3-1280 v5 E3-1280 v5 i7-6800K i7-6800KIntel Core i9-7980XE @ 4.40GHz (18 Cores / 36 Threads)ASUS PRIME X299-AIntel Device 202016384MB120GB Force MP500NV137 2048MBRealtek ALC1220Acer B286HKIntel ConnectionUbuntu 17.104.14.0-041400-generic (x86_64)GNOME Shell 3.26.1Wayland4.3 Mesa 17.2.2GCC 7.2.0ext43840x21604.14.0-phx-retpoline-gcc-retpo (x86_64)Intel Xeon E3-1280 v5 @ 4.00GHz (4 Cores / 8 Threads)MSI C236A WORKSTATION (MS-7998) v1.0Intel Skylake256GB TOSHIBA-RD400Sapphire AMD Radeon 4096MBRealtek ALC1150ASUS PB2784.14.0-041400-generic (x86_64)GNOME Shell 3.26.2modesetting 1.19.54.5 Mesa 17.4.0-devel- padoka PPA (LLVM 6.0.0)2560x14404.14.0-phx-retpoline-gcc-retpo (x86_64)4.5 Mesa 17.4.0-devel- padoka PPA ()Intel Core i7-6800K @ 3.80GHz (6 Cores / 12 Threads)MSI X99A WORKSTATION (MS-7A54) v1.0Intel Xeon E7 v4/Xeon2 x 120GB TOSHIBA-TR150NV120 12288MB4.14.0-041400-generic (x86_64)GNOME Shell 3.26.1Wayland4.3 Mesa 17.2.24.14.0-phx-retpoline-gcc-retpo (x86_64)OpenBenchmarking.orgEnvironment Details- GJS_DEBUG_TOPICS=JS ERROR;JS LOG GJS_DEBUG_OUTPUT=stderrCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details- Linux 4.14.0 Stock: i9-7980XE: NONE / data=ordered,errors=remount-ro,relatime,rw- KPTI + Retpoline: i9-7980XE: NONE / data=ordered,errors=remount-ro,relatime,rw- Linux 4.14.0 Stock: E3-1280 v5: NONE / data=ordered,errors=remount-ro,relatime,rw- KPTI + Retpoline: E3-1280 v5: NONE / data=ordered,errors=remount-ro,relatime,rw- Linux 4.14.0 Stock: i7-6800K: CFQ / data=ordered,errors=remount-ro,relatime,rw- KPTI + Retpoline: i7-6800K: CFQ / data=ordered,errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: intel_pstate powersaveSystem Details- Python 2.7.14.

fs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizepgbench: Buffer Test - Normal Load - Read Writebuild-linux-kernel: Time To Compilecompilebench: Initial Createapache: Static Web Page Servingfio: Rand Write - Libaio - No - Yes - 4KB - Default Test Directorynginx: Static Web Page Servingfio: Seq Write - Libaio - No - Yes - 4KB - Default Test Directorycompilebench: Read Compiled Treebuild-gcc: Time To Compileredis: LPUSHredis: SETredis: SADDredis: GETredis: LPOPcompilebench: Compilefs-mark: 5000 Files, 1MB Size, 4 Threadsfs-mark: 1000 Files, 1MB SizeLinux 4.14.0 StockKPTI + RetpolineLinux 4.14.0 StockKPTI + RetpolineLinux 4.14.0 StockKPTI + Retpoline i9-7980XE i9-7980XE E3-1280 v5 E3-1280 v5 i7-6800K i7-6800K366.087756.9537.95768.9551621.45753.2454668.12726.283341.51761.832227561.192229753.792334920.582722404.672114991.471728.79673.93224.93264.506594.4039.23652.2535205.88684.1542867.70687.382901.76817.091920204.672005842.482162591.792428046.711876687.361617.36500.60185.1359.402251.69129.07564.6132278.00663.8339061.22730.543554.881069.582044989.172109357.272445696.922882051.003174795.251025.74111.4799.9756.732231.11131.39502.7025399.47560.5329838.35728.602940.481095.891809081.161919907.832212974.502553195.252198334.67890.3083.8768.1042.632487.2098.92437.8639258.74287.0444577.66431.812873.761043.441927479.211986985.082153727.132436558.692736121.25673.1651.7361.4342.632515.03100.28341.7229046.8175.0032738.39432.222462.601067.351749531.251790310.781997466.832276820.752157675.11625.7350.1347.93OpenBenchmarking.org

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Sizei9-7980XEE3-1280 v5i7-6800K80160240320400SE +/- 6.11, N = 4SE +/- 0.83, N = 5SE +/- 0.62, N = 6SE +/- 4.67, N = 6SE +/- 0.68, N = 3SE +/- 0.75, N = 3366.0859.4042.63264.5056.7342.631. (CC) gcc options: -static

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Writei9-7980XEi7-6800KE3-1280 v517003400510068008500SE +/- 595.12, N = 6SE +/- 15.24, N = 3SE +/- 109.80, N = 6SE +/- 12.11, N = 37756.952487.202251.696594.402515.032231.111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -fPIC -lpgcommon -lpgport -lpthread -lrt -lcrypt -ldl -lm

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To Compilei9-7980XEi7-6800KE3-1280 v5306090120150SE +/- 0.59, N = 6SE +/- 0.82, N = 3SE +/- 0.94, N = 3SE +/- 0.59, N = 6SE +/- 1.40, N = 3SE +/- 0.94, N = 337.9598.92129.0739.23100.28131.39

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Createi9-7980XEE3-1280 v5i7-6800K170340510680850SE +/- 12.77, N = 3SE +/- 13.54, N = 3SE +/- 57.83, N = 3SE +/- 15.02, N = 3SE +/- 16.09, N = 3SE +/- 17.75, N = 3768.95564.61437.86652.25502.70341.72

Apache Benchmark

This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.7Static Web Page Servingi9-7980XEi7-6800KE3-1280 v511K22K33K44K55KSE +/- 1205.80, N = 6SE +/- 79.64, N = 3SE +/- 56.03, N = 3SE +/- 684.78, N = 3SE +/- 49.82, N = 3SE +/- 24.35, N = 351621.4539258.7432278.0035205.8829046.8125399.471. (CC) gcc options: -shared -fPIC -O2 -pthread

Flexible IO Tester

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryi9-7980XEE3-1280 v5i7-6800K40K80K120K160K200KSE +/- 2780.12, N = 4SE +/- 2398.77, N = 3SE +/- 247.77, N = 3SE +/- 7798.31, N = 6SE +/- 4650.61, N = 6SE +/- 323.27, N = 318830616595371757171034140128187471. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Random Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryi9-7980XEE3-1280 v5i7-6800K160320480640800SE +/- 11.12, N = 4SE +/- 9.60, N = 3SE +/- 0.99, N = 3SE +/- 31.19, N = 6SE +/- 18.60, N = 6SE +/- 1.29, N = 3753.24663.83287.04684.15560.5375.001. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

NGINX Benchmark

This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Servingi9-7980XEi7-6800KE3-1280 v512K24K36K48K60KSE +/- 66.93, N = 3SE +/- 187.32, N = 3SE +/- 149.45, N = 3SE +/- 653.05, N = 3SE +/- 158.01, N = 3SE +/- 85.74, N = 354668.1244577.6639061.2242867.7032738.3929838.351. (CC) gcc options: -lpthread -lcrypt -lz -O3 -march=native

Flexible IO Tester

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryE3-1280 v5i9-7980XEi7-6800K40K80K120K160K200KSE +/- 3136.58, N = 3SE +/- 1480.84, N = 3SE +/- 178.98, N = 3SE +/- 1994.25, N = 3SE +/- 370.79, N = 3SE +/- 63.34, N = 31826311815661079481821471718411080501. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 2.1.13Type: Sequential Write - IO Engine: Libaio - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryE3-1280 v5i9-7980XEi7-6800K160320480640800SE +/- 12.55, N = 3SE +/- 5.92, N = 3SE +/- 0.72, N = 3SE +/- 7.98, N = 3SE +/- 1.48, N = 3SE +/- 0.25, N = 3730.54726.28431.81728.60687.38432.221. (CC) gcc options: -rdynamic -std=gnu99 -O3 -ffast-math -include -lrt -laio -lz -lm -lpthread -ldl

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeE3-1280 v5i9-7980XEi7-6800K8001600240032004000SE +/- 38.73, N = 3SE +/- 75.95, N = 3SE +/- 32.02, N = 3SE +/- 24.97, N = 3SE +/- 62.38, N = 3SE +/- 8.43, N = 33554.883341.512873.762940.482901.762462.60

Timed GCC Compilation

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 7.2Time To Compilei9-7980XEi7-6800KE3-1280 v52004006008001000SE +/- 2.09, N = 3SE +/- 4.41, N = 3SE +/- 2.02, N = 3SE +/- 2.40, N = 3SE +/- 5.19, N = 3SE +/- 0.29, N = 3761.831043.441069.58817.091067.351095.89

Redis

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPUSHi9-7980XEE3-1280 v5i7-6800K500K1000K1500K2000K2500KSE +/- 55151.41, N = 6SE +/- 37986.60, N = 3SE +/- 25747.66, N = 3SE +/- 27558.02, N = 6SE +/- 26097.14, N = 3SE +/- 15140.06, N = 32227561.192044989.171927479.211920204.671809081.161749531.251. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETi9-7980XEE3-1280 v5i7-6800K500K1000K1500K2000K2500KSE +/- 47497.72, N = 6SE +/- 40430.85, N = 6SE +/- 15063.42, N = 3SE +/- 26640.15, N = 6SE +/- 22355.81, N = 3SE +/- 28769.97, N = 42229753.792109357.271986985.082005842.481919907.831790310.781. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SADDE3-1280 v5i9-7980XEi7-6800K500K1000K1500K2000K2500KSE +/- 29396.74, N = 3SE +/- 65858.31, N = 6SE +/- 41887.25, N = 3SE +/- 25445.22, N = 3SE +/- 42952.11, N = 6SE +/- 11424.47, N = 32445696.922334920.582153727.132212974.502162591.791997466.831. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETE3-1280 v5i9-7980XEi7-6800K600K1200K1800K2400K3000KSE +/- 17221.38, N = 3SE +/- 91567.19, N = 6SE +/- 102786.69, N = 6SE +/- 2174.75, N = 3SE +/- 77877.56, N = 6SE +/- 27034.12, N = 32882051.002722404.672436558.692553195.252428046.712276820.751. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPOPE3-1280 v5i7-6800Ki9-7980XE700K1400K2100K2800K3500KSE +/- 17457.60, N = 3SE +/- 43737.19, N = 3SE +/- 316898.84, N = 6SE +/- 24068.05, N = 3SE +/- 140310.61, N = 6SE +/- 269003.08, N = 63174795.252736121.252114991.472198334.672157675.111876687.361. (CC) gcc options: -ggdb -rdynamic -lm -pthread

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compilei9-7980XEE3-1280 v5i7-6800K400800120016002000SE +/- 20.69, N = 3SE +/- 33.40, N = 6SE +/- 36.31, N = 6SE +/- 23.74, N = 3SE +/- 31.82, N = 6SE +/- 31.93, N = 61728.791025.74673.161617.36890.30625.73

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threadsi9-7980XEE3-1280 v5i7-6800K150300450600750SE +/- 53.36, N = 6SE +/- 14.86, N = 6SE +/- 0.35, N = 3SE +/- 62.72, N = 6SE +/- 1.24, N = 6SE +/- 0.27, N = 3673.93111.4751.73500.6083.8750.131. (CC) gcc options: -static

Linux 4.14.0 StockKPTI + RetpolineOpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Sizei9-7980XEE3-1280 v5i7-6800K50100150200250SE +/- 12.40, N = 6SE +/- 2.85, N = 6SE +/- 12.52, N = 6SE +/- 2.54, N = 3SE +/- 3.63, N = 6SE +/- 3.52, N = 6224.9399.9761.43185.1368.1047.931. (CC) gcc options: -static