hbase0001 ARMv8 Neoverse-N1 testing with a GIGABYTE MP32-AR1-00 v01010101 (F18w16 SCP: 1.08.20211002 BIOS) and ASPEED on Debian unstable via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2209283-NE-HBASE000193&grr .
hbase0001 Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 ARMv8 Neoverse-N1 @ 3.00GHz (80 Cores) GIGABYTE MP32-AR1-00 v01010101 (F18w16 SCP: 1.08.20211002 BIOS) Ampere Computing LLC Altra PCI Root Complex A 256GB 2 x 3841GB SAMSUNG MZQL23T8HCLS-00A07 ASPEED 2 x Intel I350 Debian unstable 5.19.0-2-arm64 (aarch64) GCC 12.2.0 ext4 800x600 OpenBenchmarking.org - Transparent Huge Pages: always - Scaling Governor: cppc_cpufreq performance (Boost: Disabled) - OpenJDK Runtime Environment (build 11.0.16+8-post-Debian-1) - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected
hbase0001 hbase: Seq Read - 128 hbase: Seq Read - 128 hbase: Rand Write - 128 hbase: Rand Write - 128 hbase: Async Rand Write - 128 hbase: Async Rand Write - 128 hbase: Seq Write - 128 hbase: Seq Write - 128 hbase: Async Rand Read - 128 hbase: Async Rand Read - 128 hbase: Increment - 128 hbase: Increment - 128 hbase: Rand Read - 128 hbase: Rand Read - 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 509 250238 770 230324 2492 51279 314 490788 785 162121 1515 84214 472 268762 OpenBenchmarking.org
Apache HBase Test: Sequential Read - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Sequential Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 110 220 330 440 550 SE +/- 4.22, N = 15 509
Apache HBase Test: Sequential Read - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Sequential Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 50K 100K 150K 200K 250K SE +/- 1887.74, N = 15 250238
Apache HBase Test: Random Write - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 170 340 510 680 850 SE +/- 145.51, N = 9 770
Apache HBase Test: Random Write - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 50K 100K 150K 200K 250K SE +/- 46852.92, N = 9 230324
Apache HBase Test: Async Random Write - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Async Random Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 500 1000 1500 2000 2500 SE +/- 10.02, N = 3 2492
Apache HBase Test: Async Random Write - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Async Random Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 11K 22K 33K 44K 55K SE +/- 213.12, N = 3 51279
Apache HBase Test: Sequential Write - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Sequential Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 70 140 210 280 350 SE +/- 16.71, N = 10 314
Apache HBase Test: Sequential Write - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Sequential Write - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 110K 220K 330K 440K 550K SE +/- 10644.79, N = 10 490788
Apache HBase Test: Async Random Read - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Async Random Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 200 400 600 800 1000 SE +/- 7.43, N = 7 785
Apache HBase Test: Async Random Read - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Async Random Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 30K 60K 90K 120K 150K SE +/- 1499.68, N = 7 162121
Apache HBase Test: Increment - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Increment - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 300 600 900 1200 1500 SE +/- 12.17, N = 3 1515
Apache HBase Test: Increment - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Increment - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 20K 40K 60K 80K 100K SE +/- 721.36, N = 3 84214
Apache HBase Test: Random Read - Clients: 128 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 100 200 300 400 500 SE +/- 3.61, N = 3 472
Apache HBase Test: Random Read - Clients: 128 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Random Read - Clients: 128 ARMv8 Neoverse-N1 - ASPEED - GIGABYTE MP32-AR1-00 60K 120K 180K 240K 300K SE +/- 2004.15, N = 3 268762
Phoronix Test Suite v10.8.5