arrow_upward

Pages (2):
Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Virmach  VPS 9 (Atlanta) - My Dream VPS!
#1
Thumbs Up 
VPS 9 (Atlanta) - My Dream VPS!

Presented by @sohamb03 ; Directed by VirMach

Hello everyone!

This is none other than me to present a review on VPS 9 (Atlanta), belonging to the present mega-VPS group of Post4VPS, both in specifications and stock. 

THE STORY

I won this VPS on the 7th of September, 2019. I'd casually submitted a VPS request to be honest, I'd never really thought of winning this amazing VPS at the end of the Giveaway. When the Giveaway was on-going, little did I realize that this VPS, which has been an all-time favorite at Post4VPS would be mine. My spirits were really dampened when I came to know that a lot of candidates had applied, and only three of them remaining in stock with about 5 canditates already in the race, I'd assumed I wasn't going to succeed this time. 

Destiny was otherwise. On the 6th of September, 2019, @deanhills informed me (oh BTW I has initially applied for the Seattle location) that Seattle was the only location of VirMach VPSes that had a negative VPS review. He suggested that I could choose Atlanta, as Arsal has recently dropped it. I'm glad he made the suggestion that day, and today I take this opportunity to thank him a ton for the suggestion. Arsal is to be thanked too, for dropping this one, to my advantage. Wink

The very next day, came the best news. I did win the VPS and my happiness knew no bounds. Thanks to @Dynamo for organizing this forum, that brought us all together. I must say I've made great friends here, and this VPS - VPS 9, is one which I could've otherwise never afforded myself. This VPS played a great role in improving my skills in the Linux Administration, and it is through this VPS, that I learnt a lot of things. Smile

Agreed that this VPS did cause a lot of trouble during the OVZ to KVM migration, I've very little to complain about as these were very petty problems compared to the great benefit I derive out  of this VPS. (FUN FACT: I'd 6 OS re-installations on this VPS, basically I troubled Dean a lot. Tongue )

It's been 9 long months that I've been the holder of this VPS, and its time I justify the VPS and convey my regards and thanks to VirMach, through the medium of this review. Enjoy reading further!

SPECIFICATIONS


Directly from the VPS Plans page-

Disk Space 100 GB SSD

RAM: 8 GB

IP Addresses: 1x IPv4

Virtualization - KVM

Monthly Traffic: 4 TB

Location:  US

Control Panel: Ask Admin

Connection: 1Gbps

And confirming it via Post4VPS Benchmarking Script-

System Info
-----------
Processor       : QEMU Virtual CPU version (cpu64-rhel6)
CPU Cores       : 2 @ 2499.998 MHz
Memory          : 7821 MiB
Swap            : 7987 MiB
Uptime          : 46 days, 1:48,

OS              : CentOS Linux 7 (Core)
Arch            : x86_64 (64 Bit)
Kernel          : 3.10.0-1062.18.1.el7.x86_64
Hostname        : google.com


CPU BENCHMARK

Here is the Geekbench CPU benchmark on my VPS -  https://browser.geekbench.com/v5/cpu/2472702

Single-Core Score : 316
Multi-Core score   : 414

Rest of the information can be found on the page I've linked above. 

Here are the UnixBench results:

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

  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

------------------------------------------------------------------------------
  Use directories for:
     * File I/O tests (named fs***) = /root/byte-unixbench-master/UnixBench/tmp
     * Results                      = /root/byte-unixbench-master/UnixBench/results
------------------------------------------------------------------------------


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

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

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

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

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

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

2 x Process Creation  1 2 3

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

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

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

  System: sohamb03.tk: GNU/Linux
  OS: GNU/Linux -- 3.10.0-1062.18.1.el7.x86_64 -- #1 SMP Tue Mar 17 23:49:17 UTC 2020
  Machine: x86_64 (x86_64)
  Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
  CPU 0: QEMU Virtual CPU version (cpu64-rhel6) (5000.0 bogomips)
         x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  CPU 1: QEMU Virtual CPU version (cpu64-rhel6) (5000.0 bogomips)
         x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  00:19:26 up 47 days, 13:43,  1 user,  load average: 1.36, 1.47, 1.59; runlevel 2020-04-24

------------------------------------------------------------------------
Benchmark Run: Thu Jun 11 2020 00:19:26 - 00:47:41
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       21141958.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2949.7 MWIPS (9.6 s, 7 samples)
Execl Throughput                                600.6 lps   (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        104892.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           29102.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        317503.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                              160349.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  29817.7 lps   (10.0 s, 7 samples)
Process Creation                               1660.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   1318.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    245.6 lpm   (60.1 s, 2 samples)
System Call Overhead                         166583.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   21141958.6   1811.7
Double-Precision Whetstone                       55.0       2949.7    536.3
Execl Throughput                                 43.0        600.6    139.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     104892.0    264.9
File Copy 256 bufsize 500 maxblocks            1655.0      29102.0    175.8
File Copy 4096 bufsize 8000 maxblocks          5800.0     317503.1    547.4
Pipe Throughput                               12440.0     160349.3    128.9
Pipe-based Context Switching                   4000.0      29817.7     74.5
Process Creation                                126.0       1660.5    131.8
Shell Scripts (1 concurrent)                     42.4       1318.2    310.9
Shell Scripts (8 concurrent)                      6.0        245.6    409.3
System Call Overhead                          15000.0     166583.2    111.1
                                                                  ========
System Benchmarks Index Score                                         250.8

------------------------------------------------------------------------
Benchmark Run: Thu Jun 11 2020 00:47:41 - 01:16:01
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       30337697.9 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4220.3 MWIPS (9.7 s, 7 samples)
Execl Throughput                               1155.3 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        124781.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           30154.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        401904.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                              229210.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  51869.9 lps   (10.0 s, 7 samples)
Process Creation                               2479.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   1880.1 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                    284.5 lpm   (60.2 s, 2 samples)
System Call Overhead                         227504.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   30337697.9   2599.6
Double-Precision Whetstone                       55.0       4220.3    767.3
Execl Throughput                                 43.0       1155.3    268.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     124781.7    315.1
File Copy 256 bufsize 500 maxblocks            1655.0      30154.0    182.2
File Copy 4096 bufsize 8000 maxblocks          5800.0     401904.3    692.9
Pipe Throughput                               12440.0     229210.4    184.3
Pipe-based Context Switching                   4000.0      51869.9    129.7
Process Creation                                126.0       2479.1    196.8
Shell Scripts (1 concurrent)                     42.4       1880.1    443.4
Shell Scripts (8 concurrent)                      6.0        284.5    474.2
System Call Overhead                          15000.0     227504.4    151.7
                                                                  ========
System Benchmarks Index Score                                         348.4



STORAGE BENCHMARK

I've 80 GB of storage on my VPS. In VPS 9, you can choose in multiples of 5, and I didn't need much storage till now, but I'll need more soon with another OS re-installation.  XD

Filesystem               Size  Used Avail Use% Mounted on
devtmpfs                 3.9G     0  3.9G   0% /dev
tmpfs                    3.9G   64M  3.8G   2% /dev/shm
tmpfs                    3.9G  384M  3.5G  10% /run
tmpfs                    3.9G     0  3.9G   0% /sys/fs/cgroup
/dev/mapper/centos-root   47G   17G   30G  36% /
/dev/loop0               1.5G  9.0M  1.4G   1% /tmp
/dev/mapper/centos-home   23G  1.1G   22G   5% /home
/dev/vda1               1014M  228M  787M  23% /boot
tmpfs                    783M  4.0K  783M   1% /run/user/0
tmpfs                    783M     0  783M   0% /run/user/5003

For the boot time: (Actually I've a GUI - XFCE - running on the VPS; not sure why it didn't show up Thinking )

Startup finished in 861ms (kernel) + 2.761s (initrd) + 12.130s (userspace) = 15.753s


Although, the boot time is pretty cool. 


Now for the tests, directly from the Benchmarking Script:

[sohamb03@google ~]$ ./bench.sh -io
Disk Speed
----------
I/O (1st run)   : 547 MB/s
I/O (2nd run)   : 708 MB/s
I/O (3rd run)   : 731 MB/s
Average I/O     : 662 MB/s

Which is a remarkable performance!


This is the disk-speed-beta.sh script, not yet merged into the benchmarking script but just a confirmation of the above results plus the cached mode. 

[sohamb03@google ~]$ ./disk-speed-beta.sh
Testing hard drive write speed.
Pass 1... Pass 2... Pass 3... 813 MB/s
Testing hard drive read speed with caching.
Pass 1... Pass 2... Pass 3... 2.6 GB/s
Testing hard drive read speed without caching.
Pass 1... Pass 2... Pass 3... 859 MB/s

HDPARM

Direct:

[root@google ~]# hdparm -Tt --direct /dev/vda

/dev/vda:
 Timing O_DIRECT cached reads:   1386 MB in  2.00 seconds = 693.46 MB/sec
 Timing O_DIRECT disk reads: 3600 MB in  3.00 seconds = 1199.83 MB/sec
[root@google ~]# hdparm -Tt --direct /dev/vda

/dev/vda:
 Timing O_DIRECT cached reads:   1166 MB in  2.00 seconds = 583.22 MB/sec
 Timing O_DIRECT disk reads: 2756 MB in  3.00 seconds = 918.14 MB/sec
[root@google ~]# hdparm -Tt --direct /dev/vda

/dev/vda:
 Timing O_DIRECT cached reads:   1108 MB in  2.00 seconds = 554.22 MB/sec
 Timing O_DIRECT disk reads: 2640 MB in  3.00 seconds = 879.43 MB/sec

Cached:

[root@google ~]# hdparm -Tt /dev/vda

/dev/vda:
 Timing cached reads:   7552 MB in  1.99 seconds = 3801.03 MB/sec
 Timing buffered disk reads: 3366 MB in  3.00 seconds = 1121.09 MB/sec
[root@google ~]# hdparm -Tt /dev/vda

/dev/vda:
 Timing cached reads:   7074 MB in  1.98 seconds = 3573.86 MB/sec
 Timing buffered disk reads: 3310 MB in  3.00 seconds = 1102.97 MB/sec
[root@google ~]# hdparm -Tt /dev/vda

/dev/vda:
 Timing cached reads:   8060 MB in  1.98 seconds = 4061.10 MB/sec
 Timing buffered disk reads: 3354 MB in  3.00 seconds = 1117.58 MB/sec

IOPING

Disk Seek Rate:

[root@google ~]# ioping -R /dev/vda

--- /dev/vda (block device 78 GiB) ioping statistics ---
3.34 k requests completed in 2.61 s, 13.1 MiB read, 1.28 k iops, 5.00 MiB/s
generated 3.35 k requests in 3.00 s, 13.1 MiB, 1.11 k iops, 4.35 MiB/s
min/avg/max/mdev = 176.8 us / 781.8 us / 25.6 ms / 1.41 ms

Disk Sequential Speed:

[root@google ~]# ioping -RL /dev/vda

--- /dev/vda (block device 78 GiB) ioping statistics ---
2.88 k requests completed in 2.76 s, 720.5 MiB read, 1.04 k iops, 261.5 MiB/s
generated 2.88 k requests in 3.02 s, 720.8 MiB, 953 iops, 238.3 MiB/s
min/avg/max/mdev = 329.6 us / 956.1 us / 44.1 ms / 1.65 ms

DISK I/O LATENCY:

Default Mode:

[root@google ~]# ioping -c 20 /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 2.31 ms, 76 KiB read, 8.22 k iops, 32.1 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 86.7 us / 121.6 us / 195.3 us / 31.1 us
 
Asynchronous Mode:

[root@google ~]# ioping -c 20 -A /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 6.32 ms, 76 KiB read, 3.00 k iops, 11.7 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 103.2 us / 332.7 us / 1.80 ms / 477.6 us

Direct Mode:

[root@google ~]# ioping -c 20 -D /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 7.57 ms, 76 KiB read, 2.51 k iops, 9.80 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 83.0 us / 398.5 us / 2.52 ms / 645.5 us

Cached Mode:

[root@google ~]# ioping -c 20 -C /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 493.8 us, 76 KiB read, 38.5 k iops, 150.3 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 13.3 us / 26.0 us / 177.9 us / 35.9 us

Write Mode:

[root@google ~]# ioping -c 20 -W /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 69.6 ms, 76 KiB written, 272 iops, 1.07 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 1.10 ms / 3.67 ms / 20.0 ms / 4.16 ms

Alternate Read-Write Mode:

[root@google ~]# ioping -c 20 -G /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 3.18 s, 76 KiB, 5 iops, 23.9 KiB/s
generated 20 requests in 21.2 s, 80 KiB, 0 iops, 3.78 KiB/s
min/avg/max/mdev = 110.9 us / 167.3 ms / 3.15 s / 704.1 ms


NETWORK BENCHMARK

Benchmarking Script:

Speedtest (IPv4 only)
---------------------
Your public IPv4 is 8.8.8.8

Location                Provider        Speed
--------                --------        -----
CDN                     Cachefly        47.2MB/s

Atlanta, GA, US         @sohamb03       19.3MB/s
Dallas, TX, US          Softlayer       41.5MB/s
Seattle, WA, US         Softlayer       19.4MB/s
San Jose, CA, US        Softlayer       20.0MB/s
Washington, DC, US      Leaseweb        14.9MB/s

Sao Paulo, Brazil       Softlayer       6.34MB/s

Singapore               Softlayer       5.84MB/s
Taiwan                  Hinet           3.71MB/s
Tokyo, Japan            Linode          4.20MB/s

Nuremberg, Germany      Hetzner         4.15MB/s
Rotterdam, Netherlands  id3.net         7.54MB/s
Haarlem, Netherlands    Leaseweb        17.4MB/s
Milan, Italy            Softlayer       7.54MB/s

Melbourne, AU           Softlayer       5.85MB/s
 
Please note that the Atlanta speedtest server is my VPS itself and I'm so embarrassed inserting it here.  Tongue

And now the official SpeedTest.NET CLI :

[root@google ~]# speedtest

   Speedtest by Ookla

     Server: Sprint - Enid, OK (id = 11232)
        ISP: ColoCrossing
    Latency:    18.78 ms   (0.70 ms jitter)
   Download:   541.61 Mbps (data used: 683.7 MB)
     Upload:   920.74 Mbps (data used: 1.7 GB)
Packet Loss:     0.0%
 Result URL: https://www.speedtest.net/result/c/d0e6ac45-912f-4957-8db9-6fec1fec8e1b


Iperf3 Downstream to California, USA (Hurricane Electric):

[root@google ~]# iperf3 -c iperf.he.net -p 5201

Connecting to host iperf.he.net, port 5201
[  4] local 8.8.8.64 port 43796 connected to 216.218.207.42 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec  29.3 MBytes   245 Mbits/sec    0   6.42 MBytes
[  4]   1.00-2.00   sec  50.0 MBytes   421 Mbits/sec    0   6.42 MBytes
[  4]   2.00-3.00   sec  51.2 MBytes   429 Mbits/sec    0   6.42 MBytes
[  4]   3.00-4.00   sec  46.2 MBytes   388 Mbits/sec    0   6.42 MBytes
[  4]   4.00-5.04   sec  51.2 MBytes   415 Mbits/sec    0   6.42 MBytes
[  4]   5.04-6.01   sec  50.0 MBytes   432 Mbits/sec    0   6.42 MBytes
[  4]   6.01-7.00   sec  45.0 MBytes   381 Mbits/sec    0   6.42 MBytes
[  4]   7.00-8.00   sec  48.8 MBytes   409 Mbits/sec    0   6.42 MBytes
[  4]   8.00-9.01   sec  51.2 MBytes   428 Mbits/sec    0   6.42 MBytes
[  4]   9.01-10.00  sec  52.5 MBytes   442 Mbits/sec    0   6.42 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.00  sec   476 MBytes   399 Mbits/sec    0             sender
[  4]   0.00-10.00  sec   476 MBytes   399 Mbits/sec                  receiver

iperf Done.


Iperf3 Upstream to California, USA (Hurricane Electric):

[root@google ~]# iperf3 -c iperf.he.net -p 5201 -R

Connecting to host iperf.he.net, port 5201
Reverse mode, remote host iperf.he.net is sending
[  4] local 8.8.8.8 port 43856 connected to 216.218.207.42 port 5201
[ ID] Interval           Transfer     Bandwidth
[  4]   0.00-1.00   sec  6.60 MBytes  55.4 Mbits/sec
[  4]   1.00-2.00   sec  8.22 MBytes  69.0 Mbits/sec
[  4]   2.00-3.00   sec  7.02 MBytes  58.9 Mbits/sec
[  4]   3.00-4.01   sec  7.52 MBytes  62.8 Mbits/sec
[  4]   4.01-5.00   sec  7.61 MBytes  64.1 Mbits/sec
[  4]   5.00-6.00   sec  7.79 MBytes  65.5 Mbits/sec
[  4]   6.00-7.00   sec  7.80 MBytes  65.4 Mbits/sec
[  4]   7.00-8.00   sec  8.05 MBytes  67.5 Mbits/sec
[  4]   8.00-9.00   sec  8.13 MBytes  68.1 Mbits/sec
[  4]   9.00-10.00  sec  8.01 MBytes  67.2 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.00  sec  81.9 MBytes  68.7 Mbits/sec  319             sender
[  4]   0.00-10.00  sec  77.3 MBytes  64.8 Mbits/sec                  receiver

iperf Done.

Download speed may not be great, but good enough for my purpose.  Big Grin


USAGE

Here's the most important part - the use case of the VPS lol. 
  • I presently have CyberPanel running on he VPS - and two websites including my speedtest server being powered by the same. Also, I give free web hosting to one of my friend.
  • I've 6 Discord Bots running on that VPS (3 for me and 3 for yet another friend). All of them are coded in Python, and the server handles the load quite well. Not using much RAM and CPU honestly, except a few occasional spikes. 
  • A GUI - XFCE - is running on the VPS. It's the lightest GUI available (cuz I've previously faced problems with GNOME and MATE). 
  • Development and testing of my scripts. 
  • A private OpenVPN server for myself.
  • I'd installed Pterodactyl panel initially on the VPS; but on noticing that it consumes a lot of resources and conflicts with other applications on my VPS, I wiped it off. 
  • I always keep aside little resources (which is why the free space) for testing new stuff, panels and beta testing of other applications. 

SUMMARY

Let's sum up this review. 

1. I'm extremely satisfied with the VPS ... it's perfect for my needs and use-case. I do not regret keeping a considerable space empty cuz they get filled and wiped occasionally. 

2. As we all know, VPS 9 doesn't have a control panel, but honestly I never felt the need of having one. Dean and HR have been very active at support and my level of satisfaction knows no bounds. 

Again, a huge thanks to VirMach and Post4VPS, for this amazing VPS. Also, thanks for taking time to read this review, dear readers. Although I've tried to keep this review as descriptive as possible, any feedback, suggestions are welcome. I'll try my best to include them as soon as possible.

Regards,
Sayan Bhattacharyya,

Heartiest thanks to Post4VPS and Virmach for my wonderful VPS 9!
#2
Your KVM VPS uses virtio drivers for the disk and those disks in that case all are to be found at /dev/vdX (x = a,b,c...) and the partitions are at /dev/vdXY (y= 1,2,3...).

You have /dev/vda1 which however is just the boot partition. So maybe rather use the LVM root partition to do the tests which is "/dev/mapper/centos-root". Your OS installation uses LVM rather than classic partitions.
[Image: zHHqO5Q.png]
#3
@sohamb03

I'm afraid you'll have to repeat all the storage benchmarking section!!
(06-11-2020, 07:27 AM)sohamb03 Wrote:
STORAGE BENCHMARK

I've 70GB of storage on my VPS. In VPS 9, you can choose in multiples of 5, and I didn't need much storage till now, but I'll need more soon with another OS re-installation.  XD

Filesystem               Size  Used Avail Use% Mounted on
devtmpfs                 3.9G     0  3.9G   0% /dev
tmpfs                    3.9G   64M  3.8G   2% /dev/shm
tmpfs                    3.9G  352M  3.5G   9% /run
tmpfs                    3.9G     0  3.9G   0% /sys/fs/cgroup
/dev/mapper/centos-root   47G   17G   30G  36% /
/dev/loop0               1.5G  9.0M  1.4G   1% /tmp
/dev/mapper/centos-home   23G  1.1G   22G   5% /home
/dev/vda1               1014M  228M  787M  23% /boot
tmpfs                    783M  4.0K  783M   1% /run/user/0
tmpfs                    783M     0  783M   0% /run/user/5003

For the boot time: (Actually I've a GUI - XFCE - running on the VPS; not sure why it didn't show up Thinking )

Startup finished in 861ms (kernel) + 2.761s (initrd) + 12.130s (userspace) = 15.753s


Although, the boot time is pretty cool. 


Now for the tests, directly from the Benchmarking Script:

Disk Speed
----------
I/O (1st run)   : 799 MB/s
I/O (2nd run)   : 781 MB/s
I/O (3rd run)   : 827 MB/s
Average I/O     : 802.333 MB/s

Which is a remarkable performance!


This is the disk-speed-beta.sh script, not yet merged into the benchmarking script but just a confirmation of the above results plus the cached mode. 

Testing hard drive write speed.
Pass 1... Pass 2... Pass 3... 693 MB/s
Testing hard drive read speed with caching.
Pass 1... Pass 2... Pass 3... 2.5 GB/s
Testing hard drive read speed without caching.
Pass 1... Pass 2... Pass 3... 859 MB/s

(PS: Here I encountered a strange problem. I'm not an expert at all this; since I don't deal with hardware at all. For some reason, my system seems to be missing "/dev/sda" and I've the least idea why, so I performed the upcoming tests on "/dev/loop0". No idea if that makes a difference but nevermind. If I were to make a wild guess, I got CentOS 7 installed from ISO since I needed the default partitions for some purpose ... maybe that's why.)

HDPARM

Direct:

/dev/loop0:
Timing O_DIRECT cached reads:   2936 MB in  1.99 seconds = 1472.22 MB/sec
Timing O_DIRECT disk reads: 1500 MB in  0.91 seconds = 1648.67 MB/sec


/dev/loop0:
 Timing O_DIRECT cached reads:   2814 MB in  1.99 seconds = 1411.65 MB/sec
 Timing O_DIRECT disk reads: 1500 MB in  1.23 seconds = 1219.07 MB/sec


/dev/loop0:
 Timing O_DIRECT cached reads:   3208 MB in  1.99 seconds = 1608.77 MB/sec
 Timing O_DIRECT disk reads: 1500 MB in  0.93 seconds = 1604.51 MB/sec

Cached:

/dev/loop0:
Timing cached reads:   6810 MB in  1.98 seconds = 3439.02 MB/sec
Timing buffered disk reads: 1426 MB in  3.00 seconds = 475.09 MB/sec


/dev/loop0:
 Timing cached reads:   5214 MB in  1.98 seconds = 2630.66 MB/sec
 Timing buffered disk reads: 1500 MB in  1.87 seconds = 800.39 MB/sec


/dev/loop0:
 Timing cached reads:   6034 MB in  1.99 seconds = 3037.79 MB/sec
 Timing buffered disk reads: 1500 MB in  1.70 seconds = 880.70 MB/sec

IOPING

Disk Seek Rate:

--- /dev/loop0 (block device 1.46 GiB) ioping statistics ---
3.95 k requests completed in 2.46 s, 15.4 MiB read, 1.60 k iops, 6.27 MiB/s
generated 3.95 k requests in 3.00 s, 15.4 MiB, 1.32 k iops, 5.14 MiB/s
min/avg/max/mdev = 17.2 us / 623.4 us / 59.9 ms / 1.60 ms

Disk Sequential Speed:

--- /dev/loop0 (block device 1.46 GiB) ioping statistics ---
2.33 k requests completed in 2.50 s, 583 MiB read, 934 iops, 233.7 MiB/s
generated 2.33 k requests in 3.00 s, 583.2 MiB, 777 iops, 194.4 MiB/s
min/avg/max/mdev = 245.1 us / 1.07 ms / 21.4 ms / 1.57 ms

DISK I/O LATENCY:

Default Mode:


--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 2.31 ms, 76 KiB read, 8.22 k iops, 32.1 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 86.7 us / 121.6 us / 195.3 us / 31.1 us
 
Asynchronous Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 6.32 ms, 76 KiB read, 3.00 k iops, 11.7 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 103.2 us / 332.7 us / 1.80 ms / 477.6 us

Direct Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 7.57 ms, 76 KiB read, 2.51 k iops, 9.80 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 83.0 us / 398.5 us / 2.52 ms / 645.5 us

Cached Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 493.8 us, 76 KiB read, 38.5 k iops, 150.3 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 13.3 us / 26.0 us / 177.9 us / 35.9 us

Write Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 69.6 ms, 76 KiB written, 272 iops, 1.07 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 1.10 ms / 3.67 ms / 20.0 ms / 4.16 ms

Alternate Read-Write Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 3.18 s, 76 KiB, 5 iops, 23.9 KiB/s
generated 20 requests in 21.2 s, 80 KiB, 0 iops, 3.78 KiB/s
min/avg/max/mdev = 110.9 us / 167.3 ms / 3.15 s / 704.1 ms

Why?!.. you may ask!... Simply --and correct me if I'm work-- because you were benchmarking inside the /tmp folder, which is a loop-mounted folder (as /dev/loop0). Thus the rates you got ain't really those of your virtual disk (/dev/vda), but just a loop-mounted folder/device.
Filesystem               Size  Used Avail Use% Mounted on
.....
/dev/mapper/centos-root   47G   17G   30G  36% /
/dev/loop0               1.5G  9.0M  1.4G   1% /tmp
/dev/mapper/centos-home   23G  1.1G   22G   5% /home
/dev/vda1               1014M  228M  787M  23% /boot
....

Those, who did have OVZ editions of VPS-9 will be familiar with the 600/700 MB/s sequential write... But shouldn't be the case for KVM editions.

As to why your storage device
(06-11-2020, 07:27 AM)sohamb03 Wrote: (PS: Here I encountered a strange problem. I'm not an expert at all this; since I don't deal with hardware at all. For some reason, my system seems to be missing "/dev/sda" and I've the least idea why, so I performed the upcoming tests on "/dev/loop0". No idea if that makes a difference but nevermind. If I were to make a wild guess, I got CentOS 7 installed from ISO since I needed the default partitions for some purpose ... maybe that's why.)
It's not a hardware issue!.. Your running in a virtual environment!.. It's a device driver issue, and it's because you're using the virtio_blk device driver; just run this command to attest for that:
lsmod | grep virt

If you happened to be used the virtio_scsi version, your virtual disk would have the 'S' prefix instead of 'V'. But it's the deploy-er decision not ours.

Anyway, I think you're onto something here, and I'll comment further one you update the miss-hap.
VirMach's Buffalo_VPS-9 Holder (Dec. 20 - July 21)
microLXC's Container Holder (july 20 - ?)
VirMach's Phoenix_VPS-9 Holder (Apr. 20 - June 20)
NanoKVM's NAT-VPS Holder (jan. 20 - ?)
#4
Thanks for the information HR and fChk. I've updated the OP with the results with the LVM root partition "/dev/mapper/centos-root" and I think it should be fine now.  

(06-11-2020, 08:47 AM)fChk Wrote: Why?!.. you may ask!... Simply --and correct me if I'm work-- because you were benchmarking inside the /tmp folder, which is a loop-mounted folder (as /dev/loop0). Thus the rates you got ain't really those of your virtual disk (/dev/vda), but just a loop-mounted folder/device.
 
I wasn't inside the /tmp folder while doing the tests though; it's just that I used "/dev/loop0" to do the tests when I din't find "/dev/sda". Smile
Sayan Bhattacharyya,

Heartiest thanks to Post4VPS and Virmach for my wonderful VPS 9!
#5
(06-11-2020, 11:13 AM)sohamb03 Wrote: Thanks for the information HR and fChk. I've updated the OP with the results with the LVM root partition "/dev/mapper/centos-root" and I think it should be fine now.  

Sorry!.. but I still can't get my head around those results!

I would have preferred that you also post the commands corresponding to those output. It's always an uncomfortable guessing game when we want to interpret outputs of missing commands.

What's needed is the benchmarking of the virtual disk as a whole (ie /dev/vda); bypassing the file-system entirely:
# Disk seq.read Speed (Cached)
hdparm -Tt /dev/vda

# Disk seq.read Speed (Direct)
hdparm -Tt --direct /dev/vda

# Disk Seek Rate:
ioping -R /dev/vda

# Disk Sequential Speed:
ioping -RL /dev/vda

As for dd, please run the io section of your script inside your sudoer home directory.

The values in the OP are too high to be credible for a Virmach KVM VPS. If the results of the commands I posted above proved otherwise, then you'll have won the JACKPOT indeed, storage performance-wise !..

What makes me believe that's not the case is this:
--- /dev/mapper/centos-root: (block device 78 GiB) ioping statistics ---
3.53 k requests completed in 2.76 s, 882.8 MiB read, 1.28 k iops, 320.1 MiB/s
generated 3.53 k requests in 3.00 s, 883 MiB, 1.18 k iops, 294.3 MiB/s
min/avg/max/mdev = 311.7 us / 780.9 us / 16.3 ms / 963.3 us

A rate of 294.3 MiB/s in disk sequential read is much more credible frankly!
VirMach's Buffalo_VPS-9 Holder (Dec. 20 - July 21)
microLXC's Container Holder (july 20 - ?)
VirMach's Phoenix_VPS-9 Holder (Apr. 20 - June 20)
NanoKVM's NAT-VPS Holder (jan. 20 - ?)
#6
(06-11-2020, 07:27 AM)sohamb03 Wrote:
VPS 9 (Atlanta) - My Dream VPS!

Presented by @sohamb03 ; Directed by VirMach

Hello everyone!

This is none other than me to present a review on VPS 9 (Atlanta), belonging to the present mega-VPS group of Post4VPS, both in specifications and stock. 

THE STORY

I won this VPS on the 7th of September, 2019. I'd casually submitted a VPS request to be honest, I'd never really thought of winning this amazing VPS at the end of the Giveaway. When the Giveaway was on-going, little did I realize that this VPS, which has been an all-time favorite at Post4VPS would be mine. My spirits were really dampened when I came to know that a lot of candidates had applied, and only three of them remaining in stock with about 5 canditates already in the race, I'd assumed I wasn't going to succeed this time. 

Destiny was otherwise. On the 6th of September, 2019, @deanhills informed me (oh BTW I has initially applied for the Seattle location) that Seattle was the only location of VirMach VPSes that had a negative VPS review. He suggested that I could choose Atlanta, as Arsal has recently dropped it. I'm glad he made the suggestion that day, and today I take this opportunity to thank him a ton for the suggestion. Arsal is to be thanked too, for dropping this one, to my advantage. Wink

The very next day, came the best news. I did win the VPS and my happiness knew no bounds. Thanks to @Dynamo for organizing this forum, that brought us all together. I must say I've made great friends here, and this VPS - VPS 9, is one which I could've otherwise never afforded myself. This VPS played a great role in improving my skills in the Linux Administration, and it is through this VPS, that I learnt a lot of things. Smile

Agreed that this VPS did cause a lot of trouble during the OVZ to KVM migration, I've very little to complain about as these were very petty problems compared to the great benefit I derive out  of this VPS. (FUN FACT: I'd 6 OS re-installations on this VPS, basically I troubled Dean a lot. Tongue )

It's been 9 long months that I've been the holder of this VPS, and its time I justify the VPS and convey my regards and thanks to VirMach, through the medium of this review. Enjoy reading further!

SPECIFICATIONS


Directly from the VPS Plans page-

Disk Space 100 GB SSD

RAM: 8 GB

IP Addresses: 1x IPv4

Virtualization - KVM

Monthly Traffic: 4 TB

Location:  US

Control Panel: Ask Admin

Connection: 1Gbps

And confirming it via Post4VPS Benchmarking Script-

System Info
-----------
Processor       : QEMU Virtual CPU version (cpu64-rhel6)
CPU Cores       : 2 @ 2499.998 MHz
Memory          : 7821 MiB
Swap            : 7987 MiB
Uptime          : 46 days, 1:48,

OS              : CentOS Linux 7 (Core)
Arch            : x86_64 (64 Bit)
Kernel          : 3.10.0-1062.18.1.el7.x86_64
Hostname        : google.com


CPU BENCHMARK

Here is the Geekbench CPU benchmark on my VPS -  https://browser.geekbench.com/v5/cpu/2472702

Single-Core Score : 316
Multi-Core score   : 414

Rest of the information can be found on the page I've linked above. 

Here are the UnixBench results:

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

  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

------------------------------------------------------------------------------
  Use directories for:
     * File I/O tests (named fs***) = /root/byte-unixbench-master/UnixBench/tmp
     * Results                      = /root/byte-unixbench-master/UnixBench/results
------------------------------------------------------------------------------


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

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

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

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

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

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

2 x Process Creation  1 2 3

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

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

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

  System: sohamb03.tk: GNU/Linux
  OS: GNU/Linux -- 3.10.0-1062.18.1.el7.x86_64 -- #1 SMP Tue Mar 17 23:49:17 UTC 2020
  Machine: x86_64 (x86_64)
  Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
  CPU 0: QEMU Virtual CPU version (cpu64-rhel6) (5000.0 bogomips)
         x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  CPU 1: QEMU Virtual CPU version (cpu64-rhel6) (5000.0 bogomips)
         x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
  00:19:26 up 47 days, 13:43,  1 user,  load average: 1.36, 1.47, 1.59; runlevel 2020-04-24

------------------------------------------------------------------------
Benchmark Run: Thu Jun 11 2020 00:19:26 - 00:47:41
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       21141958.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2949.7 MWIPS (9.6 s, 7 samples)
Execl Throughput                                600.6 lps   (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        104892.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           29102.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        317503.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                              160349.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  29817.7 lps   (10.0 s, 7 samples)
Process Creation                               1660.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   1318.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    245.6 lpm   (60.1 s, 2 samples)
System Call Overhead                         166583.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   21141958.6   1811.7
Double-Precision Whetstone                       55.0       2949.7    536.3
Execl Throughput                                 43.0        600.6    139.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     104892.0    264.9
File Copy 256 bufsize 500 maxblocks            1655.0      29102.0    175.8
File Copy 4096 bufsize 8000 maxblocks          5800.0     317503.1    547.4
Pipe Throughput                               12440.0     160349.3    128.9
Pipe-based Context Switching                   4000.0      29817.7     74.5
Process Creation                                126.0       1660.5    131.8
Shell Scripts (1 concurrent)                     42.4       1318.2    310.9
Shell Scripts (8 concurrent)                      6.0        245.6    409.3
System Call Overhead                          15000.0     166583.2    111.1
                                                                  ========
System Benchmarks Index Score                                         250.8

------------------------------------------------------------------------
Benchmark Run: Thu Jun 11 2020 00:47:41 - 01:16:01
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       30337697.9 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4220.3 MWIPS (9.7 s, 7 samples)
Execl Throughput                               1155.3 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        124781.7 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           30154.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        401904.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                              229210.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  51869.9 lps   (10.0 s, 7 samples)
Process Creation                               2479.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   1880.1 lpm   (60.1 s, 2 samples)
Shell Scripts (8 concurrent)                    284.5 lpm   (60.2 s, 2 samples)
System Call Overhead                         227504.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   30337697.9   2599.6
Double-Precision Whetstone                       55.0       4220.3    767.3
Execl Throughput                                 43.0       1155.3    268.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     124781.7    315.1
File Copy 256 bufsize 500 maxblocks            1655.0      30154.0    182.2
File Copy 4096 bufsize 8000 maxblocks          5800.0     401904.3    692.9
Pipe Throughput                               12440.0     229210.4    184.3
Pipe-based Context Switching                   4000.0      51869.9    129.7
Process Creation                                126.0       2479.1    196.8
Shell Scripts (1 concurrent)                     42.4       1880.1    443.4
Shell Scripts (8 concurrent)                      6.0        284.5    474.2
System Call Overhead                          15000.0     227504.4    151.7
                                                                  ========
System Benchmarks Index Score                                         348.4



STORAGE BENCHMARK

I've 70GB of storage on my VPS. In VPS 9, you can choose in multiples of 5, and I didn't need much storage till now, but I'll need more soon with another OS re-installation.  XD

Filesystem               Size  Used Avail Use% Mounted on
devtmpfs                 3.9G     0  3.9G   0% /dev
tmpfs                    3.9G   64M  3.8G   2% /dev/shm
tmpfs                    3.9G  384M  3.5G  10% /run
tmpfs                    3.9G     0  3.9G   0% /sys/fs/cgroup
/dev/mapper/centos-root   47G   17G   30G  36% /
/dev/loop0               1.5G  9.0M  1.4G   1% /tmp
/dev/mapper/centos-home   23G  1.1G   22G   5% /home
/dev/vda1               1014M  228M  787M  23% /boot
tmpfs                    783M  4.0K  783M   1% /run/user/0
tmpfs                    783M     0  783M   0% /run/user/5003

For the boot time: (Actually I've a GUI - XFCE - running on the VPS; not sure why it didn't show up Thinking )

Startup finished in 861ms (kernel) + 2.761s (initrd) + 12.130s (userspace) = 15.753s


Although, the boot time is pretty cool. 


Now for the tests, directly from the Benchmarking Script:

Disk Speed
----------
I/O (1st run)   : 799 MB/s
I/O (2nd run)   : 781 MB/s
I/O (3rd run)   : 827 MB/s
Average I/O     : 802.333 MB/s

Which is a remarkable performance!


This is the disk-speed-beta.sh script, not yet merged into the benchmarking script but just a confirmation of the above results plus the cached mode. 

Testing hard drive write speed.
Pass 1... Pass 2... Pass 3... 693 MB/s
Testing hard drive read speed with caching.
Pass 1... Pass 2... Pass 3... 2.5 GB/s
Testing hard drive read speed without caching.
Pass 1... Pass 2... Pass 3... 859 MB/s

(PS: Here I encountered a strange problem. I'm not an expert at all this; since I don't deal with hardware at all. For some reason, my system seems to be missing "/dev/sda" and I've the least idea why, so I performed the upcoming tests on "/dev/loop0". No idea if that makes a difference but nevermind. If I were to make a wild guess, I got CentOS 7 installed from ISO since I needed the default partitions for some purpose ... maybe that's why.)

HDPARM

Direct:

/dev/mapper/centos-root:
 Timing O_DIRECT cached reads:   1570 MB in  2.00 seconds = 786.52 MB/sec
 Timing O_DIRECT disk reads: 3374 MB in  3.00 seconds = 1124.29 MB/sec

/dev/mapper/centos-root:
 Timing O_DIRECT cached reads:   1196 MB in  2.00 seconds = 598.63 MB/sec
 Timing O_DIRECT disk reads: 3204 MB in  3.00 seconds = 1067.33 MB/sec

/dev/mapper/centos-root:
 Timing O_DIRECT cached reads:   1252 MB in  2.00 seconds = 626.79 MB/sec
 Timing O_DIRECT disk reads: 2826 MB in  3.00 seconds = 941.83 MB/sec

Cached:

/dev/mapper/centos-root:
 Timing cached reads:   6780 MB in  1.99 seconds = 3408.66 MB/sec
 Timing buffered disk reads: 3198 MB in  3.00 seconds = 1065.62 MB/sec

/dev/mapper/centos-root:
 Timing cached reads:   7404 MB in  1.99 seconds = 3724.59 MB/sec
 Timing buffered disk reads: 3406 MB in  3.00 seconds = 1134.39 MB/sec

/dev/mapper/centos-root:
 Timing cached reads:   7968 MB in  1.99 seconds = 4009.13 MB/sec
 Timing buffered disk reads: 3190 MB in  3.15 seconds = 1013.77 MB/sec

IOPING

Disk Seek Rate:

--- /dev/mapper/centos-root: (block device 78 GiB) ioping statistics ---
5.11 k requests completed in 2.78 s, 19.9 MiB read, 1.84 k iops, 7.18 MiB/s
generated 5.11 k requests in 3.00 s, 19.9 MiB, 1.70 k iops, 6.65 MiB/s
min/avg/max/mdev = 185.0 us / 544.1 us / 17.0 ms / 792.0 us

Disk Sequential Speed:

--- /dev/mapper/centos-root: (block device 78 GiB) ioping statistics ---
3.53 k requests completed in 2.76 s, 882.8 MiB read, 1.28 k iops, 320.1 MiB/s
generated 3.53 k requests in 3.00 s, 883 MiB, 1.18 k iops, 294.3 MiB/s
min/avg/max/mdev = 311.7 us / 780.9 us / 16.3 ms / 963.3 us

DISK I/O LATENCY:

Default Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 2.31 ms, 76 KiB read, 8.22 k iops, 32.1 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 86.7 us / 121.6 us / 195.3 us / 31.1 us
 
Asynchronous Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 6.32 ms, 76 KiB read, 3.00 k iops, 11.7 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 103.2 us / 332.7 us / 1.80 ms / 477.6 us

Direct Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 7.57 ms, 76 KiB read, 2.51 k iops, 9.80 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 83.0 us / 398.5 us / 2.52 ms / 645.5 us

Cached Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 493.8 us, 76 KiB read, 38.5 k iops, 150.3 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 13.3 us / 26.0 us / 177.9 us / 35.9 us

Write Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 69.6 ms, 76 KiB written, 272 iops, 1.07 MiB/s
generated 20 requests in 19.0 s, 80 KiB, 1 iops, 4.21 KiB/s
min/avg/max/mdev = 1.10 ms / 3.67 ms / 20.0 ms / 4.16 ms

Alternate Read-Write Mode:

--- /tmp (ext4 /dev/loop0) ioping statistics ---
19 requests completed in 3.18 s, 76 KiB, 5 iops, 23.9 KiB/s
generated 20 requests in 21.2 s, 80 KiB, 0 iops, 3.78 KiB/s
min/avg/max/mdev = 110.9 us / 167.3 ms / 3.15 s / 704.1 ms


NETWORK BENCHMARK

Benchmarking Script:

Speedtest (IPv4 only)
---------------------
Your public IPv4 is 8.8.8.8

Location                Provider        Speed
--------                --------        -----
CDN                     Cachefly        47.2MB/s

Atlanta, GA, US         @sohamb03       19.3MB/s
Dallas, TX, US          Softlayer       41.5MB/s
Seattle, WA, US         Softlayer       19.4MB/s
San Jose, CA, US        Softlayer       20.0MB/s
Washington, DC, US      Leaseweb        14.9MB/s

Sao Paulo, Brazil       Softlayer       6.34MB/s

Singapore               Softlayer       5.84MB/s
Taiwan                  Hinet           3.71MB/s
Tokyo, Japan            Linode          4.20MB/s

Nuremberg, Germany      Hetzner         4.15MB/s
Rotterdam, Netherlands  id3.net         7.54MB/s
Haarlem, Netherlands    Leaseweb        17.4MB/s
Milan, Italy            Softlayer       7.54MB/s

Melbourne, AU           Softlayer       5.85MB/s
 
Please note that the Atlanta speedtest server is my VPS itself and I'm so embarrassed inserting it here.  Tongue

And now the official SpeedTest.NET CLI :

  Speedtest by Ookla

    Server: Sprint - Enid, OK (id = 11232)
       ISP: ColoCrossing
   Latency:    18.54 ms   (0.34 ms jitter)
  Download:   531.59 Mbps (data used: 846.4 MB)
    Upload:   917.35 Mbps (data used: 914.9 MB)
Packet Loss:     0.0%


Iperf3 Downstream to California, USA (Hurricane Electric):

Connecting to host iperf.he.net, port 5201
[  4] local 8.8.8.64 port 43796 connected to 216.218.207.42 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec  29.3 MBytes   245 Mbits/sec    0   6.42 MBytes
[  4]   1.00-2.00   sec  50.0 MBytes   421 Mbits/sec    0   6.42 MBytes
[  4]   2.00-3.00   sec  51.2 MBytes   429 Mbits/sec    0   6.42 MBytes
[  4]   3.00-4.00   sec  46.2 MBytes   388 Mbits/sec    0   6.42 MBytes
[  4]   4.00-5.04   sec  51.2 MBytes   415 Mbits/sec    0   6.42 MBytes
[  4]   5.04-6.01   sec  50.0 MBytes   432 Mbits/sec    0   6.42 MBytes
[  4]   6.01-7.00   sec  45.0 MBytes   381 Mbits/sec    0   6.42 MBytes
[  4]   7.00-8.00   sec  48.8 MBytes   409 Mbits/sec    0   6.42 MBytes
[  4]   8.00-9.01   sec  51.2 MBytes   428 Mbits/sec    0   6.42 MBytes
[  4]   9.01-10.00  sec  52.5 MBytes   442 Mbits/sec    0   6.42 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.00  sec   476 MBytes   399 Mbits/sec    0             sender
[  4]   0.00-10.00  sec   476 MBytes   399 Mbits/sec                  receiver

iperf Done.


Iperf3 Upstream to California, USA (Hurricane Electric):

Connecting to host iperf.he.net, port 5201
Reverse mode, remote host iperf.he.net is sending
[  4] local 8.8.8.8 port 43856 connected to 216.218.207.42 port 5201
[ ID] Interval           Transfer     Bandwidth
[  4]   0.00-1.00   sec  6.60 MBytes  55.4 Mbits/sec
[  4]   1.00-2.00   sec  8.22 MBytes  69.0 Mbits/sec
[  4]   2.00-3.00   sec  7.02 MBytes  58.9 Mbits/sec
[  4]   3.00-4.01   sec  7.52 MBytes  62.8 Mbits/sec
[  4]   4.01-5.00   sec  7.61 MBytes  64.1 Mbits/sec
[  4]   5.00-6.00   sec  7.79 MBytes  65.5 Mbits/sec
[  4]   6.00-7.00   sec  7.80 MBytes  65.4 Mbits/sec
[  4]   7.00-8.00   sec  8.05 MBytes  67.5 Mbits/sec
[  4]   8.00-9.00   sec  8.13 MBytes  68.1 Mbits/sec
[  4]   9.00-10.00  sec  8.01 MBytes  67.2 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.00  sec  81.9 MBytes  68.7 Mbits/sec  319             sender
[  4]   0.00-10.00  sec  77.3 MBytes  64.8 Mbits/sec                  receiver

iperf Done.

Download speed may not be great, but good enough for my purpose.  Big Grin


USAGE

Here's the most important part - the use case of the VPS lol. 
  • I presently have CyberPanel running on he VPS - and two websites including my speedtest server being powered by the same. Also, I give free web hosting to one of my friend.
  • I've 6 Discord Bots running on that VPS (3 for me and 3 for yet another friend). All of them are coded in Python, and the server handles the load quite well. Not using much RAM and CPU honestly, except a few occasional spikes. 
  • A GUI - XFCE - is running on the VPS. It's the lightest GUI available (cuz I've previously faced problems with GNOME and MATE). 
  • Development and testing of my scripts. 
  • A private OpenVPN server for myself.
  • I'd installed Pterodactyl panel initially on the VPS; but on noticing that it consumes a lot of resources and conflicts with other applications on my VPS, I wiped it off. 
  • I always keep aside little resources (which is why the free space) for testing new stuff, panels and beta testing of other applications. 

SUMMARY

Let's sum up this review. 

1. I'm extremely satisfied with the VPS ... it's perfect for my needs and use-case. I do not regret keeping a considerable space empty cuz they get filled and wiped occasionally. 

2. As we all know, VPS 9 doesn't have a control panel, but honestly I never felt the need of having one. Dean and HR have been very active at support and my level of satisfaction knows no bounds. 

Again, a huge thanks to VirMach and Post4VPS, for this amazing VPS. Also, thanks for taking time to read this review, dear readers. Although I've tried to keep this review as descriptive as possible, any feedback, suggestions are welcome. I'll try my best to include them as soon as possible.

Regards,

Amazing and insanely detailed review you got there! Looks beautiful too with the way you formatted it! I enjoyed reading every little character on your review, so kudos for that!

Since we both have VPS 9, just different locations, the specs a vert identical! However performance wise, something just isn’t right on my end (more on that below).

It specially caught my attention that you mentioned that Deanhills informed you that the previous holder of VPS 9 Seattle had negative feedback on it (never knew that to be honest). That, if anyone here doesn’t already know, is the same VPS i had currently. And apart from a ton of miscommunication that went on almost every time i tried to ask the staff to do me something for it (not really the VPSs fault)... I haven’t had much negative to say about it except for ONE thing that I haven’t mentioned before (simply because I don’t want to trouble the admins more than I already have... so I learned to live with it):

And that one thing is that it tends to be quite slow in tasks such as establishing the SSH connection and logging in, along with running tasks as such updating dependencies and upgrading the packages. At first (for several months for a matter of fact) I thought that was normal... however, based on feedback i got from several VPS 9 holders, I’m the only one experiencing this. I couldn’t narrow the issue dowm however... network speeds are at a comfortable 800-900Mbps, and disk I/O speeds have been very inconsistent, but the max I’ve seen was around 500MBps, which is quite good (interesting to see that your VPS has almost double that... but I doubt that this could be the issue since ~500MBps I/O speeds is still blazing fast). But anyways, it’s not that huge of a deal as I’ve, just like I’ve mentioned previously, learned to live with it.
Thank you Post4VPS and VirMach for providing me with VPS9! But now it’s time to say farewell due to my studies.
#7
Thanks @ikk157. Well, it turns out that what Dean had warned me against Seattle is correct. Why don't you open a support ticket in the private VPS support section? I'm sure Dean can contact VirMach regarding the performance of the VPS and get it sorted. 


@fChk Done updated the thread again with the new results and also, I included the commands I used for every test. At first I skipped it cuz I thought it'd be making the thread unnecessarily longer but nevertheless. I've taken care of the following:
  • Benchmarking of the virtual disk has been done as a whole. 
  • dd outputs have been run the sudoers home directory. 
Also, it seems only the sequential rate dropped by a bit, but it's still good as far as I understand. Smile

BTW, here's something I wanted to ask. As I said, I'm more into software than hardware, hence, I can't make out why the sequential rate is so high on /tmp. Can you please explain to me?

[root@google ~]# ioping -RL /tmp

--- /tmp (ext4 /dev/loop0) ioping statistics ---
7.31 k requests completed in 2.52 s, 1.79 GiB read, 2.90 k iops, 725.9 MiB/s
generated 7.32 k requests in 3.00 s, 1.79 GiB, 2.44 k iops, 609.6 MiB/s
min/avg/max/mdev = 203.7 us / 344.4 us / 26.5 ms / 506.1 us

Thanks and regards,
Sayan Bhattacharyya,

Heartiest thanks to Post4VPS and Virmach for my wonderful VPS 9!
#8
(06-11-2020, 04:11 PM)sohamb03 Wrote: Thanks @ikk157. Well, it turns out that what Dean had warned me against Seattle is correct. Why don't you open a support ticket in the private VPS support section? I'm sure Dean can contact VirMach regarding the performance of the VPS and get it sorted. 

The reason why I haven’t already done that is because I’ve already bothered him enough. I feel like I’m the most troubling VPS holder over here considering that no one else is as demanding as I am. 

That’s exactly why I don’t want to trouble him any more regarding anything. Even I wouldn’t appreciate someone constantly asking me to look into stuff.

Not to mention that, just like what Dynamo has told me when I contacted him about something completely different, VirMach already does so much for post4vps. We don’t want to trouble them with anything. And I absolutely agree with what Dynamo said!

Also, complaining about something that’s completely free is just bad. VirMach is after all providing this VPS completely free of cost. And the post4vps staff members are voluntarily dedicating some of their precious time into into making all of this possible! The last thing I’d want is to be a pain in the butt for any of them.
Thank you Post4VPS and VirMach for providing me with VPS9! But now it’s time to say farewell due to my studies.
#9
(06-11-2020, 01:53 PM)ikk157 Wrote: It specially caught my attention that you mentioned that Deanhills informed you that the previous holder of VPS 9 Seattle had negative feedback on it (never knew that to be honest).

@ikk157  The VPS 9 Seattle review was dated 2018 when we still were on OpenVZ.  Seattle and Chicago VPS got upgraded to KVM towards end of 2019 (think it was October) as the first VPSs to be upgraded to KVM and the upgrades were very high quality, much higher quality than the other locations whose upgrades possibly got automated.  At any rate, possibly due to expert network configuration with the KVM upgrade Seattle VPS turned into a much more powerful VPS.  

Would be interesting if you could make a comparison of the stats quoted in the 2018 review and your experience with the KVM version of the same VPS.
Terminal
Thank you to Post4VPS and VirMach for my awesome VPS 9!  
#10
(06-11-2020, 09:38 PM)deanhills Wrote: @ikk157  The VPS 9 Seattle review was dated 2018 when we still were on OpenVZ.  Seattle and Chicago VPS got upgraded to KVM towards end of 2019 (think it was October) as the first VPSs to be upgraded to KVM and the upgrades were very high quality, much higher quality than the other locations whose upgrades possibly got automated.  At any rate, possibly due to expert network configuration with the KVM upgrade Seattle VPS turned into a much more powerful VPS.  

Would be interesting if you could make a comparison of the stats quoted in the 2018 review and your experience with the KVM version of the same VPS.

I absolutely agree, just looking at that older review you linked (thanks for the link!), I can already see a lot of improvements CPU-wise and disk speeds as well!

My existing review serves as a great source of KVM benchmarks which will allow people to compare it to the previous OVZ review you linked. I’ll go ahead and post an update on my existing review with my overall experience now that I’ve been the proud holder of VPS 9 Seattle for almost 8 months!
Thank you Post4VPS and VirMach for providing me with VPS9! But now it’s time to say farewell due to my studies.
Pages (2):


Possibly Related Threads…
Thread
Author
Replies
Views
Last Post

person_pin_circle Users browsing this thread: 2 Guest(s)
Sponsors: VirMach - Host4Fun - CubeData - Evolution-Host - HostDare - Hyper Expert - Shadow Hosting - Bladenode - Hostlease - RackNerd - ReadyDedis - Limitless Hosting