Retbleed EPYC 7742 2P 2 x AMD EPYC 7742 Retbleed benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2207131-PTS-RETBVLEE94 retbleed=auto Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
retbleed=off Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 22.04, Kernel: 5.19.0-rc6-phx-retbleed (x86_64), Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Retbleed EPYC 7742 2P OpenBenchmarking.org Phoronix Test Suite 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads) Supermicro H11DSi-NT v2.00 (2.1 BIOS) AMD Starship/Matisse 128GB 280GB INTEL SSDPE21D280GA ASPEED VE228 2 x Intel 10G X550T Ubuntu 22.04 5.19.0-rc6-phx-retbleed (x86_64) X Server 1.21.1.3 1.2.204 GCC 11.2.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Display Server Vulkan Compiler File-System Screen Resolution Retbleed EPYC 7742 2P Benchmarks System Logs - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034 - OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1) - Python 3.10.4 - retbleed=auto: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - retbleed=off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
retbleed=auto vs. retbleed=off Comparison Phoronix Test Suite Baseline +8.1% +8.1% +16.2% +16.2% +24.3% +24.3% 32.3% 29.6% 29.4% 29.2% 27.2% 25% 19.3% 18.4% 17.4% 16.1% 15.4% 14.6% 13.7% 13.4% 12.2% 12% 11.5% 10.7% 10.4% 10.2% 9% 9% 9% 8.3% 8.1% 6.8% 6% 5.8% 5.3% 5.1% 4.2% 4.2% 4% 3.9% 3.7% 3.6% 3.5% 3.3% 3.2% 2.9% 2.9% 2.7% 2.6% 2.5% Syscall Basic 200 100 - 500 - Read Only 100 - 500 - Read Only - Average Latency Context Switching C.S.T Compile 1.F.1.S 1000 4.F.3.S.D.1.S 500 Create Files Futex Hash Initial Create SENDFILE Memory Allocations 5.F.1.S.4.T 200 Read Compiled Tree MEMFD 100 Sched Pipe 100 Create Processes 32 - Process allmodconfig 20 Rand Read 1.R.W.A.D.T.R defconfig Update Rand 1.R.W.A.D.S.R 1.R.W.A.D.F.R.C.C 100 - 50 - Read Only R.R.W.R 100 - 50 - Read Only - Average Latency Create Threads Timed Time - Size 1,000 1000 Futex Read While Writing H2 Semaphores Socket Activity perf-bench Apache HTTP Server PostgreSQL pgbench PostgreSQL pgbench Stress-NG ctx_clock Compile Bench FS-Mark nginx FS-Mark nginx OSBench perf-bench Compile Bench Stress-NG OSBench FS-Mark nginx Compile Bench Stress-NG nginx perf-bench Apache HTTP Server OSBench Hackbench Timed Linux Kernel Compilation nginx Facebook RocksDB ClickHouse Timed Linux Kernel Compilation Facebook RocksDB ClickHouse ClickHouse PostgreSQL pgbench Facebook RocksDB PostgreSQL pgbench OSBench SQLite Speedtest Apache HTTP Server Stress-NG Facebook RocksDB DaCapo Benchmark Stress-NG Stress-NG retbleed=auto retbleed=off
Retbleed EPYC 7742 2P compilebench: Compile compilebench: Initial Create compilebench: Read Compiled Tree ctx-clock: Context Switch Time hackbench: 32 - Process stress-ng: Futex stress-ng: MEMFD stress-ng: SENDFILE stress-ng: Semaphores stress-ng: Socket Activity stress-ng: Context Switching dacapobench: H2 dacapobench: Jython fs-mark: 1000 Files, 1MB Size fs-mark: 5000 Files, 1MB Size, 4 Threads fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size namd: ATPase Simulation - 327,506 Atoms osbench: Create Files osbench: Create Threads osbench: Launch Programs osbench: Create Processes osbench: Memory Allocations perf-bench: Futex Hash perf-bench: Memset 1MB perf-bench: Sched Pipe perf-bench: Syscall Basic build-linux-kernel: defconfig build-linux-kernel: allmodconfig build-godot: Time To Compile nginx: 20 nginx: 100 nginx: 200 nginx: 500 nginx: 1000 apache: 100 apache: 200 apache: 500 apache: 1000 clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache clickhouse: 100M Rows Web Analytics Dataset, Second Run clickhouse: 100M Rows Web Analytics Dataset, Third Run rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand sqlite-speedtest: Timed Time - Size 1,000 pgbench: 100 - 50 - Read Only pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 500 - Read Only pgbench: 100 - 500 - Read Only - Average Latency retbleed=auto retbleed=off 1101.42 349.30 2241.24 225 20.231 2707104.77 1600.44 1376114.26 10767143.65 35929.59 31273805.27 8699 5426 523.0 1244.3 534.8 0.27787 26.059672 86.399714 122.163296 130.027135 109.018723 2007401 52.753380 110268 8627866 26.486 184.029 50.843 80844.74 79833.15 77808.77 75068.64 76951.03 65387.82 69689.87 81585.24 89406.07 236.71 251.45 250.55 390711139 225667 12884590 1977818 80.046 873851 0.057 1660368 0.301 1314.17 396.22 2473.51 180 18.722 2785464.67 1764.24 1543380.12 11048906.13 36818.67 39792969.95 8467 5350 619.1 1387.7 621.1 0.27284 22.730186 83.463192 120.882988 120.026270 97.354651 2283376 53.553233 120185 11418673 25.209 172.389 49.980 85686.86 87033.03 86136.21 86620.66 90346.19 71255.26 90288.68 81880.36 92301.66 246.15 261.98 263.86 413365525 235226 13256142 2051455 77.515 908268 0.055 2148641 0.233 OpenBenchmarking.org
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.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile retbleed=auto retbleed=off 300 600 900 1200 1500 SE +/- 2.09, N = 3 SE +/- 1.46, N = 3 1101.42 1314.17
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MEMFD retbleed=auto retbleed=off 400 800 1200 1600 2000 SE +/- 1.45, N = 3 SE +/- 1.80, N = 3 1600.44 1764.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -lrt -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: SENDFILE retbleed=auto retbleed=off 300K 600K 900K 1200K 1500K SE +/- 3704.66, N = 3 SE +/- 2133.74, N = 3 1376114.26 1543380.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -lrt -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Semaphores retbleed=auto retbleed=off 2M 4M 6M 8M 10M SE +/- 6629.77, N = 3 SE +/- 8649.55, N = 3 10767143.65 11048906.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -lrt -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Socket Activity retbleed=auto retbleed=off 8K 16K 24K 32K 40K SE +/- 255.36, N = 12 SE +/- 342.49, N = 15 35929.59 36818.67 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -lrt -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Context Switching retbleed=auto retbleed=off 9M 18M 27M 36M 45M SE +/- 32202.50, N = 3 SE +/- 185538.10, N = 3 31273805.27 39792969.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -lrt -lz -pthread
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads retbleed=auto retbleed=off 300 600 900 1200 1500 SE +/- 10.94, N = 3 SE +/- 4.42, N = 3 1244.3 1387.7
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size retbleed=auto retbleed=off 130 260 390 520 650 SE +/- 3.51, N = 3 SE +/- 3.45, N = 3 534.8 621.1
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms retbleed=auto retbleed=off 0.0625 0.125 0.1875 0.25 0.3125 SE +/- 0.00017, N = 3 SE +/- 0.00290, N = 3 0.27787 0.27284
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files retbleed=auto retbleed=off 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 26.06 22.73 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads retbleed=auto retbleed=off 20 40 60 80 100 SE +/- 0.71, N = 3 SE +/- 0.36, N = 3 86.40 83.46 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs retbleed=auto retbleed=off 30 60 90 120 150 SE +/- 0.52, N = 3 SE +/- 0.85, N = 3 122.16 120.88 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes retbleed=auto retbleed=off 30 60 90 120 150 SE +/- 0.73, N = 3 SE +/- 0.15, N = 3 130.03 120.03 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations retbleed=auto retbleed=off 20 40 60 80 100 SE +/- 0.56, N = 3 SE +/- 0.24, N = 3 109.02 97.35 1. (CC) gcc options: -lm
perf-bench This test profile is used for running Linux perf-bench, the benchmark support within the Linux kernel's perf tool. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash retbleed=auto retbleed=off 500K 1000K 1500K 2000K 2500K SE +/- 14837.52, N = 3 SE +/- 1599.52, N = 3 2007401 2283376 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lz -lnuma
OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB retbleed=auto retbleed=off 12 24 36 48 60 SE +/- 0.37, N = 3 SE +/- 0.26, N = 3 52.75 53.55 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lz -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe retbleed=auto retbleed=off 30K 60K 90K 120K 150K SE +/- 1101.26, N = 15 SE +/- 1111.97, N = 7 110268 120185 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lz -lnuma
OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic retbleed=auto retbleed=off 2M 4M 6M 8M 10M SE +/- 44396.20, N = 3 SE +/- 72399.51, N = 3 8627866 11418673 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -lunwind-x86_64 -lunwind -llzma -Xlinker -lpthread -lrt -lm -ldl -lelf -lz -lnuma
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 20 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 66.36, N = 3 SE +/- 192.77, N = 3 80844.74 85686.86 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 42.75, N = 3 SE +/- 258.26, N = 3 79833.15 87033.03 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 141.18, N = 3 SE +/- 153.84, N = 3 77808.77 86136.21 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 500 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 54.46, N = 3 SE +/- 160.87, N = 3 75068.64 86620.66 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 172.03, N = 3 SE +/- 142.94, N = 3 76951.03 90346.19 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
Apache HTTP Server This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 100 retbleed=auto retbleed=off 15K 30K 45K 60K 75K SE +/- 134.24, N = 3 SE +/- 736.58, N = 3 65387.82 71255.26 1. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 200 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 165.68, N = 3 SE +/- 909.60, N = 15 69689.87 90288.68 1. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 500 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 505.29, N = 3 SE +/- 661.87, N = 3 81585.24 81880.36 1. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1000 retbleed=auto retbleed=off 20K 40K 60K 80K 100K SE +/- 749.92, N = 8 SE +/- 705.48, N = 10 89406.07 92301.66 1. (CC) gcc options: -shared -fPIC -O2
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 100M Rows Web Analytics Dataset, First Run / Cold Cache retbleed=auto retbleed=off 50 100 150 200 250 SE +/- 5.00, N = 12 SE +/- 3.48, N = 15 236.71 246.15 MIN: 30.05 / MAX: 15000 MIN: 30.17 / MAX: 15000 1. ClickHouse server version 22.7.1.687 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 100M Rows Web Analytics Dataset, Second Run retbleed=auto retbleed=off 60 120 180 240 300 SE +/- 2.89, N = 12 SE +/- 2.10, N = 15 251.45 261.98 MIN: 34.25 / MAX: 15000 MIN: 34.64 / MAX: 15000 1. ClickHouse server version 22.7.1.687 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 100M Rows Web Analytics Dataset, Third Run retbleed=auto retbleed=off 60 120 180 240 300 SE +/- 2.47, N = 12 SE +/- 2.16, N = 15 250.55 263.86 MIN: 33.63 / MAX: 20000 MIN: 32.95 / MAX: 20000 1. ClickHouse server version 22.7.1.687 (official build).
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Random Read retbleed=auto retbleed=off 90M 180M 270M 360M 450M SE +/- 802548.74, N = 3 SE +/- 3595901.73, N = 3 390711139 413365525 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Update Random retbleed=auto retbleed=off 50K 100K 150K 200K 250K SE +/- 569.03, N = 3 SE +/- 554.44, N = 3 225667 235226 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing retbleed=auto retbleed=off 3M 6M 9M 12M 15M SE +/- 279296.63, N = 15 SE +/- 269144.10, N = 15 12884590 13256142 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random retbleed=auto retbleed=off 400K 800K 1200K 1600K 2000K SE +/- 13157.37, N = 3 SE +/- 3062.67, N = 3 1977818 2051455 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency retbleed=auto retbleed=off 0.0128 0.0256 0.0384 0.0512 0.064 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.057 0.055 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only retbleed=auto retbleed=off 500K 1000K 1500K 2000K 2500K SE +/- 11288.59, N = 3 SE +/- 16790.56, N = 12 1660368 2148641 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency retbleed=auto retbleed=off 0.0677 0.1354 0.2031 0.2708 0.3385 SE +/- 0.002, N = 3 SE +/- 0.002, N = 12 0.301 0.233 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
retbleed=auto Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 12 July 2022 15:34 by user phoronix.
retbleed=off Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 22.04, Kernel: 5.19.0-rc6-phx-retbleed (x86_64), Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Vulnerable + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 July 2022 04:14 by user phoronix.