Review Scaleway: Dedicated Server murah meriah

By | January 27, 2019

Entah kerasukan apa saya beberapa hari lalu. 😀 Iseng saja coba – coba Scaleway yang menyediakan produk Dedicated Server dengan harga yang terjangkau. Dengan catatan, arsitektur CPUnya ialah ARM. Ya yang dimanfaatkan di handphone itu. Oh ya, Scaleway ini besutan Online.net, jadi telah ada latar belakang yang lumayan kuat.

Sesungguhnya Scaleway pun ada Cloud/VPS lazimnya dan dedicated yang arsitektur x86, tapi khusus yang saya review ini ialah yang ARM dan sangat murah. Ini spesifikasinya Scaleway C1:

  • 4 Dedicated ARMv7 Cores
  • 2GB Memory
  • 50GB SSD Disk
  • 1 Flexible public IPv4
  • 200Mbit/s Unmetered bandwidth
  • €2.99/bulan

Yang saya pilih lokasi Perancis (PARIS/FR), alternatifnya di Belanda (AMSTERDAM/NL). Ya kurang lebih bayar Rp 50.000 sebulan. Waktu itu asumsi saya dengan 4 core mestinya tak parah – parah amat. akan tetapi apakah benar seperti itu?

Apa yang kita dapatkan?

Secara prosesor berikut informasinya:

lscpu
Architecture: armv7l
Byte Order: Little Endian
CPU(s): 4
On-line CPU(s) list: 0-3
Thread(s) per core: 1
Core(s) per socket: 4
Socket(s): 1
Model name: ARMv7 Processor rev 2 (v7l)
CPU max MHz: 1333.0000
CPU min MHz: 666.5000

Kemudian struktur storage servernya:

df -h
Filesystem Size Used Avail Use% Mounted on
udev 1009M 0 1009M 0% /dev
tmpfs 203M 12M 191M 6% /run
/dev/nbd0 46G 604M 43G 2% /
tmpfs 1011M 0 1011M 0% /dev/shm
tmpfs 5.0M 0 5.0M 0% /run/lock
tmpfs 1011M 0 1011M 0% /sys/fs/cgroup

Dan kondisi RAM ketika default:

free -m
total used free shared buff/cache available
Mem: 2020 24 1519 12 476 1744
Swap: 0 0 0

Semuanya masih sesuai spesifikasi produknya, mungkin pemakaian RAM saja yang termasuk besar.

Bagaimana kemampuannya?

Baru sekarang ini kita masuk ke benchmark dedicated servernya. Jujur ini dedicated server ARM pertama-tama saya, jadi tak ada rujukan seharusnya seperti apa performanya. Jadi sekalian bikin sahabat yang terdapat minat dapat minimal dapat mengira – ngira bagaimana kerjanya.

Diawali secara umum lewat bench.sh:

----------------------------------------------------------------------
CPU model : ARMv7 Processor rev 2 (v7l)
Number of cores : 4
CPU frequency : MHz
Total size of Disk : 47.0 GB (0.6 GB Used)
Total amount of Mem : 2020 MB (25 MB Used)
Total amount of Swap : 0 MB (0 MB Used)
System uptime : 0 days, 0 hour 10 min
Load average : 0.10, 0.53, 0.35
OS : Ubuntu 16.04.1 LTS
Arch : armv7l (32 Bit)
Kernel : 4.4.112-mainline-rev1
----------------------------------------------------------------------
I/O speed(1st run) : 116 MB/s
I/O speed(2nd run) : 113 MB/s
I/O speed(3rd run) : 110 MB/s
Average I/O speed : 113.0 MB/s
----------------------------------------------------------------------
Node Name IPv4 address Unduh Speed
CacheFly 62.210.187.96 109MB/s
Linode, Tokyo, JP 106.187.96.148 1.47MB/s
Linode, Singapore, SG 139.162.23.4 1.10MB/s
Linode, London, UK 176.58.107.39 16.9MB/s
Linode, Frankfurt, DE 139.162.130.8 28.3MB/s
Linode, Fremont, CA 50.116.14.9 2.20MB/s
Softlayer, Dallas, TX 173.192.68.18 2.19MB/s
Softlayer, Seattle, WA 67.228.112.250 1.80MB/s
Softlayer, Frankfurt, DE 159.122.69.4 19.0MB/s
Softlayer, Singapore, SG 119.81.28.170 1.57MB/s
Softlayer, HongKong, CN 119.81.130.170 1.42MB/s
----------------------------------------------------------------------

Yang saya komentari cuma bandwidthnya kerena yang lainnya itu termasuk normal angkanya. Jadi secara bandwidth ini bakal betul-betul – betul-betul lambat kalau dari Indonesia.

Kemudian kita uji performa sistemnya dengan UnixBench:

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #

Version 5.1.3 Based on the Byte Magazine Unix Benchmark

Multi-CPU version Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011 johantheghost at yahoo period com

1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput 1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3

1 x File Copy 256 bufsize 500 maxblocks 1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3

1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10

1 x Process Creation 1 2 3

1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent) 1 2 3

1 x Shell Scripts (8 concurrent) 1 2 3

4 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10

4 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10

4 x Execl Throughput 1 2 3

4 x File Copy 1024 bufsize 2000 maxblocks 1 2 3

4 x File Copy 256 bufsize 500 maxblocks 1 2 3

4 x File Copy 4096 bufsize 8000 maxblocks 1 2 3

4 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10

4 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10

4 x Process Creation 1 2 3

4 x System Call Overhead 1 2 3 4 5 6 7 8 9 10

4 x Shell Scripts (1 concurrent) 1 2 3

4 x Shell Scripts (8 concurrent) 1 2 3

========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)

System: servernesia.scaleway: GNU/Linux
OS: GNU/Linux -- 4.4.112-mainline-rev1 -- #1 SMP Wed Jan 17 10:34:56 UTC 2018
Machine: armv7l (armv7l)
Language: en_US.utf8 (charmap=UTF-8, collate=UTF-8)
CPU 0: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

CPU 1: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

CPU 2: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

CPU 3: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

11:35:54 up 23 min, 2 users, load average: 0.52, 0.49, 0.40; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Mon Jan 22 2018 11:35:54 - 12:04:03
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 4467368.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 778.6 MWIPS (9.9 s, 7 samples)
Execl Throughput 891.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 135154.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 39803.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 320990.3 KBps (30.0 s, 2 samples)
Pipe Throughput 215581.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 51742.0 lps (10.0 s, 7 samples)
Process Creation 1692.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 1531.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 511.9 lpm (60.0 s, 2 samples)
System Call Overhead 718610.7 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 4467368.2 382.8
Double-Precision Whetstone 55.0 778.6 141.6
Execl Throughput 43.0 891.6 207.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 135154.2 341.3
File Copy 256 bufsize 500 maxblocks 1655.0 39803.4 240.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 320990.3 553.4
Pipe Throughput 12440.0 215581.3 173.3
Pipe-based Context Switching 4000.0 51742.0 129.4
Process Creation 126.0 1692.8 134.4
Shell Scripts (1 concurrent) 42.4 1531.8 361.3
Shell Scripts (8 concurrent) 6.0 511.9 853.1
System Call Overhead 15000.0 718610.7 479.1
========
System Benchmarks Index Score 279.5

------------------------------------------------------------------------
Benchmark Run: Mon Jan 22 2018 12:04:03 - 12:32:16
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 17834383.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3117.8 MWIPS (9.9 s, 7 samples)
Execl Throughput 2555.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 201836.4 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 52361.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 617314.8 KBps (30.0 s, 2 samples)
Pipe Throughput 878432.4 lps (10.0 s, 7 samples)
Pipe-based Context Switching 179073.0 lps (10.0 s, 7 samples)
Process Creation 3940.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4163.0 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 582.8 lpm (60.2 s, 2 samples)
System Call Overhead 2552962.6 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 17834383.5 1528.2
Double-Precision Whetstone 55.0 3117.8 566.9
Execl Throughput 43.0 2555.6 594.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 201836.4 509.7
File Copy 256 bufsize 500 maxblocks 1655.0 52361.3 316.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 617314.8 1064.3
Pipe Throughput 12440.0 878432.4 706.1
Pipe-based Context Switching 4000.0 179073.0 447.7
Process Creation 126.0 3940.8 312.8
Shell Scripts (1 concurrent) 42.4 4163.0 981.8
Shell Scripts (8 concurrent) 6.0 582.8 971.3
System Call Overhead 15000.0 2552962.6 1702.0
========
System Benchmarks Index Score 701.4

Singkat cerita, secara skor single core ini cuma 25-30% dari DigitalOcean/Vultr dan secara multicore pun sama rasionya. Keunggulannya kita dapat maksimalkan pemakaian 4 corenya dalam rentang waktu 24 jam 7 hari seminggu tanpa takut disuspend provider. Telah saya coba soalnya.

Tak ada benchmark dari GeekBench karena softwarenya belum mendukung prosesor ARM, padahal Android dapat. 😀

Kesimpulan

Jadi cocoknya Scaleway C1 dibangun apa? Mungkin kalau dipaksa bikin web hosting, pakailah CloudFlare/Incapsula biar pengunjung koneknya ke server mereka yang jelas lebih optimal kecepatannya. Atau dijadikan backup server karena kapasitasnya lumayan besar dan pastinya koneksi antar server lebih bagus daripada ke rumah. Yang pasti jangan dibangun mining coin, jangan berharap ada hasilnya. Telah saya coba soalnya. 😛

Oh ya, saya belum coba yang x86_64 tapi baca – baca katanya ini bukan CPU Intel yang jenis desktop (i3-i7)maupun server (Xeon) tapi seri Atom. Jadi performanya sendiri saya tebak kurang bagus pun. Mungkin lain kesempatan akan saya coba.


Sumber https://servernesia.com