mm: memcg: subtree stats flushing and thresholds test comparison Benchmarks by Michael Larabel of the [PATCH v2 0/5] mm: memcg: subtree stats flushing and thresholds patch series atop Linux 6.6 Git. Stock is just running the benchmarks on the system itself, "1 in cgroup" is running the benchmarks within a cgroup using "systemd-run --scope"
HTML result view exported from: https://openbenchmarking.org/result/2310173-NE-NEWTESTS925&sor&grs .
Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution Stock In 1 cgroup Stock In 1 cgroup Linux 6.6-rc5 Linux 6.6-rc5 Patched Patched 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1007B BIOS) AMD Device 14a4 1520GB 3201GB Micron_7450_MTFDKCC3T2TFS ASPEED Broadcom NetXtreme BCM5720 PCIe Ubuntu 23.10 6.6.0-rc5-phx (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 GCC 13.2.0 ext4 1920x1200 6.6.0-rc5-phx-patched (x86_64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-nEN1TP/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-nEN1TP/gcc-13-13.2.0/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 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e Python Details - Python 3.11.5 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
stress-ng: MEMFD stress-ng: Mutex stress-ng: Futex stress-ng: Poll stress-ng: MMAP nginx: 500 stress-ng: Forking ethr: TCP - Bandwidth - 256 build-linux-kernel: allmodconfig pgbench: 100 - 1000 - Read Only - Average Latency pgbench: 100 - 1000 - Read Only build-llvm: Ninja pgbench: 100 - 800 - Read Only pgbench: 100 - 1000 - Read Write - Average Latency pgbench: 100 - 1000 - Read Write ethr: UDP - Bandwidth - 256 pgbench: 100 - 800 - Read Only - Average Latency stress-ng: NUMA memcached: 1:100 stress-ng: Pthread memcached: 1:10 pgbench: 100 - 800 - Read Write pgbench: 100 - 800 - Read Write - Average Latency build-linux-kernel: defconfig svt-av1: Preset 13 - Bosphorus 4K build-godot: Time To Compile compress-7zip: Compression Rating embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer ISPC - Crown ethr: TCP - Connections/s - 256 iperf: 5201 - 60 Seconds - TCP - 128 stress-ng: Atomic stress-ng: Crypto openvkl: vklBenchmarkCPU ISPC build-nodejs: Time To Compile ethr: TCP - Connections/s - 128 stress-ng: AVL Tree compress-7zip: Decompression Rating stress-ng: Zlib stress-ng: Malloc stress-ng: Hash iperf: 5201 - 60 Seconds - UDP - 128 stress-ng: Pipe Stock In 1 cgroup Stock In 1 cgroup Linux 6.6-rc5 Linux 6.6-rc5 Patched Patched 864.80 41390907.50 2243861.84 12497817.94 4591.00 253759.29 36946.64 676.91 181.528 0.294 3397057 91.372 3399500 18.263 54902 3856640 0.235 635.13 8090072.72 58451.57 4057968.21 56790 14.087 28.565 175.838 90.642 820348 231.9349 201.5262 506 33562 174.94 428250.08 3529 91.047 504 3193.43 1200473 23273.73 267785906.75 37338441.08 134 57249607.52 842.85 48719429.36 1980878.82 14390071.72 4600.69 263642.99 39181.14 714.59 178.562 0.285 3507233 87.820 3432786 17.799 56255 3883467 0.233 640.39 8276238.33 57558.84 4013800.81 58137 13.761 28.382 176.099 89.420 821409 233.2690 198.4778 508 33798 175.78 428184.46 3530 91.173 503 3203.22 1203389 23298.26 268001048.95 37316794.24 134 66453368.09 646.05 39333593.92 2311713.80 12790984.08 4173.55 258113.05 38068.60 692.61 185.539 0.298 3360303 91.216 3429143 17.802 56200 3744427 0.233 651.94 8324029.86 59195.76 4034898.74 57951 13.805 28.969 178.782 89.175 808111 234.0837 199.5611 507 33870 174.22 424885.68 3537 91.438 502 3198.71 1201479 23292.91 268032542.49 37320648.99 134 56298303.49 651.47 48817263.17 1918073.77 14643894.67 4223.46 269764.23 38616.48 704.89 188.449 0.287 3478752 91.538 3534202 17.585 57010 3749387 0.227 630.23 8298814.64 58929.26 3949479.02 58051 13.781 28.949 176.408 89.160 810356 235.5259 201.4515 501 33956 175.41 427818.58 3546 91.121 503 3198.59 1202041 23284.67 267998007.39 37319998.44 134 61692645.82 OpenBenchmarking.org
Stress-NG Test: MEMFD Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MEMFD Linux 6.6-rc5 Patched 200 400 600 800 1000 SE +/- 0.55, N = 3 SE +/- 1.19, N = 3 SE +/- 12.01, N = 3 SE +/- 8.06, N = 3 864.80 646.05 842.85 651.47 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Mutex In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex Patched Linux 6.6-rc5 10M 20M 30M 40M 50M SE +/- 468525.09, N = 3 SE +/- 354571.11, N = 3 SE +/- 568394.95, N = 3 SE +/- 340872.62, N = 13 48817263.17 48719429.36 41390907.50 39333593.92 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Futex Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Futex Patched Linux 6.6-rc5 500K 1000K 1500K 2000K 2500K SE +/- 21836.06, N = 3 SE +/- 20656.01, N = 15 SE +/- 13105.85, N = 15 SE +/- 25886.82, N = 3 2311713.80 2243861.84 1980878.82 1918073.77 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Poll In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Poll Patched Linux 6.6-rc5 3M 6M 9M 12M 15M SE +/- 3745.07, N = 3 SE +/- 185125.61, N = 3 SE +/- 6083.73, N = 3 SE +/- 42614.36, N = 3 14643894.67 14390071.72 12790984.08 12497817.94 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: MMAP In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MMAP Linux 6.6-rc5 Patched 1000 2000 3000 4000 5000 SE +/- 4.68, N = 3 SE +/- 4.20, N = 3 SE +/- 3.11, N = 3 SE +/- 4.22, N = 3 4600.69 4223.46 4591.00 4173.55 1. (CXX) g++ options: -O2 -std=gnu99 -lc
nginx Connections: 500 In 1 cgroup Stock OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 Patched Linux 6.6-rc5 60K 120K 180K 240K 300K SE +/- 1189.39, N = 3 SE +/- 2579.49, N = 5 SE +/- 1406.24, N = 3 SE +/- 372.10, N = 3 269764.23 263642.99 258113.05 253759.29 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Stress-NG Test: Forking In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking Linux 6.6-rc5 Patched 8K 16K 24K 32K 40K SE +/- 401.52, N = 5 SE +/- 152.24, N = 3 SE +/- 286.38, N = 3 SE +/- 32.03, N = 3 39181.14 38616.48 38068.60 36946.64 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Ethr Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 256 In 1 cgroup Stock OpenBenchmarking.org Gbits/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 256 Linux 6.6-rc5 Patched 150 300 450 600 750 SE +/- 4.92, N = 13 SE +/- 8.60, N = 4 SE +/- 6.44, N = 3 SE +/- 8.16, N = 15 714.59 704.89 692.61 676.91
Timed Linux Kernel Compilation Build: allmodconfig In 1 cgroup Stock OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: allmodconfig Linux 6.6-rc5 Patched 40 80 120 160 200 SE +/- 0.66, N = 3 SE +/- 0.84, N = 3 SE +/- 1.28, N = 3 SE +/- 0.59, N = 3 178.56 188.45 181.53 185.54
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency In 1 cgroup Stock OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency Linux 6.6-rc5 Patched 0.0671 0.1342 0.2013 0.2684 0.3355 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.003, N = 3 0.285 0.287 0.294 0.298 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only In 1 cgroup Stock OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only Linux 6.6-rc5 Patched 800K 1600K 2400K 3200K 4000K SE +/- 9155.47, N = 3 SE +/- 40909.46, N = 3 SE +/- 24087.02, N = 3 SE +/- 32249.83, N = 3 3507233 3478752 3397057 3360303 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Timed LLVM Compilation Build System: Ninja In 1 cgroup Stock OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja Linux 6.6-rc5 Patched 20 40 60 80 100 SE +/- 0.84, N = 3 SE +/- 0.75, N = 3 SE +/- 0.19, N = 3 SE +/- 1.17, N = 3 87.82 91.54 91.22 91.37
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only In 1 cgroup Stock OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Only Patched Linux 6.6-rc5 800K 1600K 2400K 3200K 4000K SE +/- 18828.10, N = 3 SE +/- 27914.12, N = 9 SE +/- 27956.11, N = 9 SE +/- 38417.67, N = 3 3534202 3432786 3429143 3399500 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency In 1 cgroup Stock OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency Patched Linux 6.6-rc5 4 8 12 16 20 SE +/- 0.25, N = 12 SE +/- 0.18, N = 12 SE +/- 0.19, N = 5 SE +/- 0.26, N = 12 17.59 17.80 17.80 18.26 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write In 1 cgroup Stock OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write Patched Linux 6.6-rc5 12K 24K 36K 48K 60K SE +/- 921.56, N = 12 SE +/- 644.74, N = 12 SE +/- 592.28, N = 5 SE +/- 924.69, N = 12 57010 56255 56200 54902 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Ethr Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 256 In 1 cgroup Stock OpenBenchmarking.org Packets/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 256 Linux 6.6-rc5 Patched 800K 1600K 2400K 3200K 4000K SE +/- 51188.71, N = 3 SE +/- 33305.28, N = 15 SE +/- 29992.45, N = 15 SE +/- 29877.45, N = 15 3883467 3749387 3856640 3744427
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency In 1 cgroup Stock OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency Patched Linux 6.6-rc5 0.0529 0.1058 0.1587 0.2116 0.2645 SE +/- 0.001, N = 3 SE +/- 0.002, N = 9 SE +/- 0.002, N = 9 SE +/- 0.003, N = 3 0.227 0.233 0.233 0.235 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: NUMA Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: NUMA Patched Linux 6.6-rc5 140 280 420 560 700 SE +/- 5.33, N = 9 SE +/- 3.01, N = 3 SE +/- 0.79, N = 3 SE +/- 4.07, N = 3 651.94 635.13 640.39 630.23 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Memcached Set To Get Ratio: 1:100 Stock In 1 cgroup OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 Patched Linux 6.6-rc5 2M 4M 6M 8M 10M SE +/- 39215.21, N = 3 SE +/- 89498.30, N = 3 SE +/- 51343.89, N = 3 SE +/- 20736.09, N = 3 8324029.86 8090072.72 8298814.64 8276238.33 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stress-NG Test: Pthread Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pthread Patched Linux 6.6-rc5 13K 26K 39K 52K 65K SE +/- 546.77, N = 3 SE +/- 121.73, N = 3 SE +/- 42.00, N = 3 SE +/- 415.45, N = 2 59195.76 58451.57 58929.26 57558.84 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Memcached Set To Get Ratio: 1:10 Stock In 1 cgroup OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 Linux 6.6-rc5 Patched 900K 1800K 2700K 3600K 4500K SE +/- 6269.50, N = 3 SE +/- 12460.08, N = 3 SE +/- 5607.83, N = 3 SE +/- 44333.51, N = 3 4057968.21 4034898.74 4013800.81 3949479.02 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write In 1 cgroup Stock OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Write Linux 6.6-rc5 Patched 12K 24K 36K 48K 60K SE +/- 117.12, N = 3 SE +/- 136.15, N = 3 SE +/- 345.06, N = 3 SE +/- 130.86, N = 3 58137 58051 57951 56790 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency In 1 cgroup Stock OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency Linux 6.6-rc5 Patched 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 13.76 13.78 13.81 14.09 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Timed Linux Kernel Compilation Build: defconfig In 1 cgroup Stock OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: defconfig Linux 6.6-rc5 Patched 7 14 21 28 35 SE +/- 0.23, N = 9 SE +/- 0.24, N = 9 SE +/- 0.25, N = 8 SE +/- 0.23, N = 9 28.38 28.95 28.57 28.97
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K Stock In 1 cgroup OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K Patched Linux 6.6-rc5 40 80 120 160 200 SE +/- 0.69, N = 3 SE +/- 1.65, N = 3 SE +/- 0.99, N = 3 SE +/- 2.05, N = 3 178.78 175.84 176.41 176.10 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Timed Godot Game Engine Compilation Time To Compile In 1 cgroup Stock OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile Patched Linux 6.6-rc5 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 SE +/- 0.86, N = 3 89.16 89.42 89.18 90.64
7-Zip Compression Test: Compression Rating In 1 cgroup Stock OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating Linux 6.6-rc5 Patched 200K 400K 600K 800K 1000K SE +/- 2286.58, N = 3 SE +/- 3125.48, N = 3 SE +/- 2611.68, N = 3 SE +/- 2732.90, N = 3 821409 810356 820348 808111 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Embree Binary: Pathtracer ISPC - Model: Asian Dragon In 1 cgroup Stock OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Patched Linux 6.6-rc5 50 100 150 200 250 SE +/- 0.55, N = 3 SE +/- 1.41, N = 3 SE +/- 0.14, N = 3 SE +/- 0.60, N = 3 235.53 233.27 234.08 231.93
Embree Binary: Pathtracer ISPC - Model: Crown Stock In 1 cgroup OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Linux 6.6-rc5 Patched 40 80 120 160 200 SE +/- 0.63, N = 3 SE +/- 0.54, N = 3 SE +/- 0.26, N = 3 SE +/- 0.78, N = 3 201.53 199.56 201.45 198.48
Ethr Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 256 In 1 cgroup Stock OpenBenchmarking.org Connections/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 256 Linux 6.6-rc5 Patched 110 220 330 440 550 SE +/- 0.58, N = 3 SE +/- 2.73, N = 3 SE +/- 0.33, N = 3 SE +/- 2.00, N = 3 508 501 507 506
iPerf Server Address: localhost - Server Port: 5201 - Duration: 60 Seconds - Test: TCP - Parallel: 128 In 1 cgroup Stock OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.14 Server Address: localhost - Server Port: 5201 - Duration: 60 Seconds - Test: TCP - Parallel: 128 Patched Linux 6.6-rc5 7K 14K 21K 28K 35K SE +/- 164.73, N = 3 SE +/- 72.07, N = 3 SE +/- 25.67, N = 3 SE +/- 69.21, N = 3 33956 33798 33870 33562 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lsctp -lm
Stress-NG Test: Atomic In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Atomic Linux 6.6-rc5 Patched 40 80 120 160 200 SE +/- 0.93, N = 3 SE +/- 0.53, N = 3 SE +/- 0.96, N = 3 SE +/- 0.80, N = 3 175.78 175.41 174.94 174.22 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Crypto Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Crypto Linux 6.6-rc5 Patched 90K 180K 270K 360K 450K SE +/- 50.51, N = 3 SE +/- 2977.99, N = 3 SE +/- 127.17, N = 3 SE +/- 194.59, N = 3 428250.08 424885.68 428184.46 427818.58 1. (CXX) g++ options: -O2 -std=gnu99 -lc
OpenVKL Benchmark: vklBenchmarkCPU ISPC In 1 cgroup Stock OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Patched Linux 6.6-rc5 800 1600 2400 3200 4000 SE +/- 2.73, N = 3 SE +/- 3.06, N = 3 SE +/- 2.60, N = 3 SE +/- 6.23, N = 3 3546 3530 3537 3529
Timed Node.js Compilation Time To Compile Stock In 1 cgroup OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 19.8.1 Time To Compile Linux 6.6-rc5 Patched 20 40 60 80 100 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.32, N = 3 91.05 91.44 91.12 91.17
Ethr Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 128 Stock In 1 cgroup OpenBenchmarking.org Connections/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 128 Linux 6.6-rc5 Patched 110 220 330 440 550 SE +/- 1.76, N = 3 SE +/- 1.76, N = 3 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 504 502 503 503
Stress-NG Test: AVL Tree In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVL Tree Linux 6.6-rc5 Patched 700 1400 2100 2800 3500 SE +/- 0.55, N = 3 SE +/- 2.01, N = 3 SE +/- 0.45, N = 3 SE +/- 0.73, N = 3 3203.22 3198.59 3198.71 3193.43 1. (CXX) g++ options: -O2 -std=gnu99 -lc
7-Zip Compression Test: Decompression Rating In 1 cgroup Stock OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Linux 6.6-rc5 Patched 300K 600K 900K 1200K 1500K SE +/- 2891.50, N = 3 SE +/- 2994.32, N = 3 SE +/- 3534.64, N = 3 SE +/- 6233.30, N = 3 1203389 1202041 1201479 1200473 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Stress-NG Test: Zlib In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Zlib Linux 6.6-rc5 Patched 5K 10K 15K 20K 25K SE +/- 10.95, N = 3 SE +/- 3.45, N = 3 SE +/- 7.17, N = 3 SE +/- 4.80, N = 3 23298.26 23284.67 23292.91 23273.73 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Malloc Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc Patched Linux 6.6-rc5 60M 120M 180M 240M 300M SE +/- 362591.01, N = 3 SE +/- 552523.39, N = 3 SE +/- 167541.58, N = 3 SE +/- 135784.62, N = 3 268032542.49 267785906.75 268001048.95 267998007.39 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Hash Stock In 1 cgroup OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Hash Linux 6.6-rc5 Patched 8M 16M 24M 32M 40M SE +/- 3140.46, N = 3 SE +/- 22001.89, N = 3 SE +/- 8015.53, N = 3 SE +/- 7856.31, N = 3 37338441.08 37320648.99 37319998.44 37316794.24 1. (CXX) g++ options: -O2 -std=gnu99 -lc
iPerf Server Address: localhost - Server Port: 5201 - Duration: 60 Seconds - Test: UDP - Parallel: 128 In 1 cgroup Stock OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.14 Server Address: localhost - Server Port: 5201 - Duration: 60 Seconds - Test: UDP - Parallel: 128 Patched Linux 6.6-rc5 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 134 134 134 134 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lsctp -lm
Stress-NG Test: Pipe In 1 cgroup Stock OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pipe Linux 6.6-rc5 Patched 14M 28M 42M 56M 70M SE +/- 1447716.85, N = 15 SE +/- 1087490.60, N = 15 SE +/- 577983.22, N = 15 SE +/- 777538.46, N = 15 66453368.09 61692645.82 57249607.52 56298303.49 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Phoronix Test Suite v10.8.5