无神通 大佬有话说 :
Netcup四核Unixbench测试，多核分数有点低啊，附带YABS结果
Unixbench Version 5.1.3
单核 1650.2
四核 3347.7
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 35621720.4 lps (10.0 s, 7 samples)
Double-Precision Whetstone 6595.0 MWIPS (9.9 s, 7 samples)
Execl Throughput 4154.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 994704.2 KBps(30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 290029.3 KBps(30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2645061.6 KBps(30.0 s, 2 samples)
Pipe Throughput 1805685.5 lps (10.0 s, 7 samples)
Pipe-based Context Switching 104561.3 lps (10.0 s, 7 samples)
Process Creation 9568.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 10599.2 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2861.1 lpm (60.0 s, 2 samples)
System Call Overhead 2509209.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 35621720.4 3052.4
Double-Precision Whetstone 55.0 6595.0 1199.1
Execl Throughput 43.0 4154.6 966.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 994704.2 2511.9
File Copy 256 bufsize 500 maxblocks 1655.0 290029.3 1752.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 2645061.6 4560.5
Pipe Throughput 12440.0 1805685.5 1451.5
Pipe-based Context Switching 4000.0 104561.3 261.4
Process Creation 126.0 9568.5 759.4
Shell Scripts (1 concurrent) 42.4 10599.2 2499.8
Shell Scripts (8 concurrent) 6.0 2861.1 4768.5
System Call Overhead 15000.0 2509209.0 1672.8
========
System Benchmarks Index Score 1650.2
————————————————————————
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 137645974.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 25921.7 MWIPS (9.9 s, 7 samples)
Execl Throughput 11498.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 676129.3 KBps(30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 206838.5 KBps(30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2019425.9 KBps(30.0 s, 2 samples)
Pipe Throughput 7129829.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 638789.9 lps (10.0 s, 7 samples)
Process Creation 24852.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 22807.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 3389.6 lpm (60.0 s, 2 samples)
System Call Overhead 4905364.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0137645974.111794.9
Double-Precision Whetstone 55.0 25921.7 4713.0
Execl Throughput 43.0 11498.8 2674.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 676129.3 1707.4
File Copy 256 bufsize 500 maxblocks 1655.0 206838.5 1249.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 2019425.9 3481.8
Pipe Throughput 12440.0 7129829.8 5731.4
Pipe-based Context Switching 4000.0 638789.9 1597.0
Process Creation 126.0 24852.2 1972.4
Shell Scripts (1 concurrent) 42.4 22807.6 5379.1
Shell Scripts (8 concurrent) 6.0 3389.6 5649.4
System Call Overhead 15000.0 4905364.0 3270.2
========
System Benchmarks Index Score 3347.7
======= Script description and score comparison completed! =======
YABS测试
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
# Yet-Another-Bench-Script #
# v2021-06-05 #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
Basic System Information:
———————————
Processor: AMD EPYC 7702P 64-Core Processor
CPU cores: 4 @ 1996.249 MHz
AES-NI : ✔ Enabled
VM-x/AMD-V : ❌ Disabled
RAM : 15.6 GiB
Swap : 0.0 KiB
Disk : 314.9 GiB
fio Disk Speed Tests (Mixed R/W 50/50):
———————————
Block Size | 4k (IOPS) | 64k (IOPS)
—— | — —-| —- —-
Read | 73.32 MB/s (18.3k) | 1.07 GB/s (16.7k)
Write | 73.51 MB/s (18.3k) | 1.07 GB/s (16.8k)
Total | 146.83 MB/s(36.7k) | 2.15 GB/s (33.6k)
| |
Block Size | 512k (IOPS) | 1m (IOPS)
—— | — —-| —- —-
Read | 1.60 GB/s (3.1k) | 1.55 GB/s (1.5k)
Write | 1.69 GB/s (3.3k) | 1.66 GB/s (1.6k)
Total | 3.30 GB/s (6.4k) | 3.21 GB/s (3.1k)
iperf3 Network Speed Tests (IPv4):
———————————
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Clouvider | London, UK (10G) | 1.83 Gbits/sec| 2.37 Gbits/sec
Online.net | Paris, FR (10G) | busy | busy
WorldStream | The Netherlands (10G) | 1.96 Gbits/sec| 2.38 Gbits/sec
Biznet | Jakarta, Indonesia (1G) | 429 Mbits/sec | 82.8 Mbits/sec
Clouvider | NYC, NY, US (10G) | 390 Mbits/sec | 1.68 Gbits/sec
Velocity Online | Tallahassee, FL, US (10G) | 519 Mbits/sec | 1.99 Gbits/sec
Clouvider | Los Angeles, CA, US (10G) | 388 Mbits/sec | 993 Mbits/sec
Iveloz Telecom| Sao Paulo, BR (2G) | 177 Mbits/sec | 880 Mbits/sec
iperf3 Network Speed Tests (IPv6):
———————————
Provider | Location (Link) | Send Speed | Recv Speed
| | |
Clouvider | London, UK (10G) | 1.42 Gbits/sec| 2.33 Gbits/sec
Online.net | Paris, FR (10G) | 1.50 Gbits/sec| 1.86 Gbits/sec
WorldStream | The Netherlands (10G) | 1.46 Gbits/sec| 2.34 Gbits/sec
Clouvider | NYC, NY, US (10G) | 574 Mbits/sec | 1.67 Gbits/sec
Clouvider | Los Angeles, CA, US (10G) | 443 Mbits/sec | 1.11 Gbits/sec
Geekbench 5 Benchmark Test:
———————————
Test | Value
|
Single Core | 890
Multi Core | 2762
ApkB 大佬有话说 :
没想法，这东西会动态变化
无神通 大佬有话说 :
ApkB 大佬有话说 : 2021-6-21 20:12
没想法，这东西会动态变化
RS系列是独享CPU，不应该啊yc022t
ApkB 大佬有话说 :
无神通 大佬有话说 : 2021-6-21 20:16
RS系列是独享CPU，不应该啊
独享？太天真了，你以为杜甫啊
你算算如果实现真正意义上的独享，
那么每核心的成本会有多高，
算力在虚拟化中是共享得最彻底的
3333 大佬有话说 :
挺高了