Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!


INCEPTION HOSTING - DAILY DEALS - STORAGE - KVM - VZ - NVMe - SHARED - PART 2 - UPDATED - Page 2
New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

INCEPTION HOSTING - DAILY DEALS - STORAGE - KVM - VZ - NVMe - SHARED - PART 2 - UPDATED

2

Comments

  • user123user123 Member
    edited November 2018

    @AnthonySmith non-recurring deals are generally thought of as good only

  • @solaire said:

    @3606202 said:
    Is it possible to install and use OpenVPN on the OVZ plans?

    Yes, works like a charm.

    How about Pi-Hole + OpenVPN? I've seen conflicting reports whether Pi-Hole works with OVZ...

  • @AnthonySmith said:
    And the next one, had some UK none renewals from last year.

    image

    @davi

    Thanks, ordered, Order Number: 3146564056

  • @andreipoe said:
    How about Pi-Hole + OpenVPN? I've seen conflicting reports whether Pi-Hole works with OVZ...

    That would work absolutely fine, too. I'm running these myself on two OpenVZ boxes.

    Thanked by 1andreipoe
  • Thanks for releasing some 2 GB UK OVZ stock! Even though I had already ordered a US one, thinking there wasn't any left in Europe. 2 more idling vps on the wall ...

  • Does anyone have CPU benchmark like Geekbench of PURE NVME SSD KVM 1GB or 2GB?

  • AnthonySmithAnthonySmith Member, Patron Provider

    @Doutei said:
    Does anyone have CPU benchmark like Geekbench of PURE NVME SSD KVM 1GB or 2GB?

    I will run some serverpilots on a few test 2GB VM's on different nodes so you can get an idea, 1 node with customers on it 1 without.

  • AnthonySmithAnthonySmith Member, Patron Provider

    Doutei said: Does anyone have CPU benchmark like Geekbench of PURE NVME SSD KVM 1GB or 2GB

    Benchmark Run: Mon Nov 26 2018 11:48:10 - 12:18:08
    2 CPUs in system; running 2 parallel copies of tests
    
    Dhrystone 2 using register variables      103424474.7 lps   (10.0 s, 7 samples)
    Double-Precision Whetstone                     6875.9 MWIPS (21.5 s, 7 samples)
    Execl Throughput                              11841.5 lps   (30.0 s, 2 samples)
    File Copy 1024 bufsize 2000 maxblocks       1819507.2 KBps  (30.0 s, 2 samples)
    File Copy 256 bufsize 500 maxblocks          473460.1 KBps  (30.0 s, 2 samples)
    File Copy 4096 bufsize 8000 maxblocks       5140109.7 KBps  (30.0 s, 2 samples)
    Pipe Throughput                             2861696.7 lps   (10.0 s, 7 samples)
    Pipe-based Context Switching                 530626.6 lps   (10.0 s, 7 samples)
    Process Creation                              31628.8 lps   (30.0 s, 2 samples)
    Shell Scripts (1 concurrent)                  19233.5 lpm   (60.0 s, 2 samples)
    Shell Scripts (8 concurrent)                   3148.1 lpm   (60.0 s, 2 samples)
    System Call Overhead                        2039467.0 lps   (10.0 s, 7 samples)
    
    System Benchmarks Index Values               BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0  103424474.7   8862.4
    Double-Precision Whetstone                       55.0       6875.9   1250.2
    Execl Throughput                                 43.0      11841.5   2753.8
    File Copy 1024 bufsize 2000 maxblocks          3960.0    1819507.2   4594.7
    File Copy 256 bufsize 500 maxblocks            1655.0     473460.1   2860.8
    File Copy 4096 bufsize 8000 maxblocks          5800.0    5140109.7   8862.3
    Pipe Throughput                               12440.0    2861696.7   2300.4
    Pipe-based Context Switching                   4000.0     530626.6   1326.6
    Process Creation                                126.0      31628.8   2510.2
    Shell Scripts (1 concurrent)                     42.4      19233.5   4536.2
    Shell Scripts (8 concurrent)                      6.0       3148.1   5246.8
    System Call Overhead                          15000.0    2039467.0   1359.6
                                                                       ========
    System Benchmarks Index Score                                        3129.1
    
    
    ------------------------------------------------------------------------
    Benchmark Run: Mon Nov 26 2018 05:54:43 - 06:23:29
    2 CPUs in system; running 2 parallel copies of tests
    
    Dhrystone 2 using register variables       86890757.5 lps   (10.0 s, 7 samples)
    Double-Precision Whetstone                     8211.0 MWIPS (12.9 s, 7 samples)
    Execl Throughput                              13532.0 lps   (30.0 s, 2 samples)
    File Copy 1024 bufsize 2000 maxblocks       1755426.0 KBps  (30.0 s, 2 samples)
    File Copy 256 bufsize 500 maxblocks          495433.7 KBps  (30.0 s, 2 samples)
    File Copy 4096 bufsize 8000 maxblocks       4550524.3 KBps  (30.0 s, 2 samples)
    Pipe Throughput                             5337307.4 lps   (10.0 s, 7 samples)
    Pipe-based Context Switching                 782174.1 lps   (10.0 s, 7 samples)
    Process Creation                              36157.4 lps   (30.0 s, 2 samples)
    Shell Scripts (1 concurrent)                  25675.7 lpm   (60.0 s, 2 samples)
    Shell Scripts (8 concurrent)                   3367.6 lpm   (60.0 s, 2 samples)
    System Call Overhead                        6821727.3 lps   (10.0 s, 7 samples)
    
    System Benchmarks Index Values               BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0   86890757.5   7445.7
    Double-Precision Whetstone                       55.0       8211.0   1492.9
    Execl Throughput                                 43.0      13532.0   3147.0
    File Copy 1024 bufsize 2000 maxblocks          3960.0    1755426.0   4432.9
    File Copy 256 bufsize 500 maxblocks            1655.0     495433.7   2993.6
    File Copy 4096 bufsize 8000 maxblocks          5800.0    4550524.3   7845.7
    Pipe Throughput                               12440.0    5337307.4   4290.4
    Pipe-based Context Switching                   4000.0     782174.1   1955.4
    Process Creation                                126.0      36157.4   2869.6
    Shell Scripts (1 concurrent)                     42.4      25675.7   6055.6
    Shell Scripts (8 concurrent)                      6.0       3367.6   5612.6
    System Call Overhead                          15000.0    6821727.3   4547.8
                                                                       ========
    System Benchmarks Index Score                                        3929.5
    
    root@test2:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB, 1.0 GiB) copied, 0.712678 s, 1.5 GB/s
    
    root@test:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB, 1.0 GiB) copied, 0.771845 s, 1.4 GB/s
    
    Thanked by 2nhutphan Hax
  • Just got myself a UK KVM Pure NVMe SSD ( 48 euro ), seems like SSH is not working, do I need to reinstall/install something from SolusVM to get starting ?

  • MasonRMasonR Community Contributor

    @seed4u said:
    do I need to reinstall/install something from SolusVM to get starting ?

    Yes, read the email

  • @AnthonySmith @MasonR - looks like debian 9 image is broken on my node(KVM9), nothing happens when trying to install/reinstall, ubuntu works instantly though, a pitty though as I thought I could get a debian 9 box.

  • MasonRMasonR Community Contributor

    @seed4u said:
    @AnthonySmith @MasonR - looks like debian 9 image is broken on my node(KVM9), nothing happens when trying to install/reinstall, ubuntu works instantly though, a pitty though as I thought I could get a debian 9 box.

    Does Debian 8 work? Could easily upgrade that to 9 until the templates are fixed.

  • AnthonySmithAnthonySmith Member, Patron Provider
    edited November 2018

    seed4u said: @AnthonySmith @MasonR - looks like debian 9 image is broken on my node(KVM9), nothing happens when trying to install/reinstall, ubuntu works instantly though, a pitty though as I thought I could get a debian 9 box.

    checking now

    Update: my fault, template syncing now, should be good to go within about 10 minutes.

  • seed4useed4u Member
    edited November 2018

    @AnthonySmith said:

    seed4u said: @AnthonySmith @MasonR - looks like debian 9 image is broken on my node(KVM9), nothing happens when trying to install/reinstall, ubuntu works instantly though, a pitty though as I thought I could get a debian 9 box.

    checking now

    Update: my fault, template syncing now, should be good to go within about 10 minutes.

    Thanks

  • hello Anthony
    how much RAM in the shared web hosting?

  • @AnthonySmith Hello! Any chance for the "UK 4GB OpenVZ" to come back in stock soon? ^^

  • AnthonySmithAnthonySmith Member, Patron Provider
    edited November 2018

    awan said: hello Anthony
    how much RAM in the shared web hosting?

    You mean the sever total or package limits? generally I think when people ask this they already should be buying a VPS to begin with :) the server has 16GB the CL limits are set to defaults which have always worked well, more info here: https://docs.cloudlinux.com/limits.html

    shadow24 said: @AnthonySmith Hello! Any chance for the "UK 4GB OpenVZ" to come back in stock soon? ^^

    More chance that the 2GB plan goes out of stock first :) (like very soon)

  • AnthonySmith said: More chance that the 2GB plan goes out of stock first :) (like very soon)

    Nailed it! Out of stock now.

  • @solaire said:

    AnthonySmith said: More chance that the 2GB plan goes out of stock first :) (like very soon)

    Nailed it! Out of stock now.

    Oh forking fudge. I wasn't paying attention and hadn't seen the 2GB plan. ARGH.

  • AnthonySmithAnthonySmith Member, Patron Provider
    edited November 2018

    tarasis said: Oh forking fudge. I wasn't paying attention and hadn't seen the 2GB plan. ARGH.

    May be back at the end of the month or start of December, I tend to run these promotions until the end of November each year so still some scope for none renewals from last year to become available.

  • Just leaving this here for anyone who's planning to pick one up later if they become available:

    Benchmark started on Mon Nov 26 18:09:35 CET 2018
    Full benchmark log: /root/bench.log
    
    System Info
    -----------
    Processor       : Intel(R) Xeon(R) CPU E3-1270 v5 @ 3.60GHz
    CPU Cores       : 2
    Frequency       : 3611.272 MHz
    Memory          : 2048 MB
    Swap            : 1024 MB
    Uptime          : 19:48,
    
    OS              : Debian GNU/Linux 9
    Arch            : i686 (32 Bit)
    Kernel          : 2.6.32-042stab134.3
    Hostname        : seath
    
    
    Speedtest (IPv4 only)
    ---------------------
    Your public IPv4 is xx.xx.xx.xx
    
    Location                Provider        Speed
    CDN                     Cachefly        86.2MB/s
    
    Atlanta, GA, US         Coloat          21.1MB/s
    Dallas, TX, US          Softlayer       30.3MB/s
    Seattle, WA, US         Softlayer       23.2MB/s
    San Jose, CA, US        Softlayer       23.5MB/s
    Washington, DC, US      Softlayer       40.4MB/s
    
    Tokyo, Japan            Linode          2.14MB/s
    Singapore               Softlayer       15.1MB/s
    
    Rotterdam, Netherlands  id3.net         96.2MB/s
    Haarlem, Netherlands    Leaseweb        98.2MB/s
    
    
    Disk Speed
    ----------
    I/O (1st run)   : 1.4 GB/s
    I/O (2nd run)   : 1.4 GB/s
    I/O (3rd run)   : 1.4 GB/s
    Average I/O     : 1.4 MB/s
    
    Thanked by 1AnthonySmith
  • AnthonySmithAnthonySmith Member, Patron Provider

    thanks @solaire :)

  • @AnthonySmith you sure the KVM9 node is NVMe? IO seems very bad. Should I raise a ticket ?

    Jobs: 1 (f=1): [m(1)] [10.0% done] [0KB/0KB/0KB /s] [0/0/0 iops] [eta 11m:53s]

    test: (groupid=0, jobs=1): err= 0: pid=756: Mon Nov 26 12:14:13 2018
    read : io=392300KB, bw=5013.2KB/s, iops=1253, runt= 78241msec
    write: io=130596KB, bw=1669.2KB/s, iops=417, runt= 78241msec
    cpu : usr=0.34%, sys=0.96%, ctx=6441, majf=0, minf=8
    IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
    submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
    complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
    issued : total=r=98075/w=32649/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
    latency : target=0, window=0, percentile=100.00%, depth=64

    Run status group 0 (all jobs):
    READ: io=392300KB, aggrb=5013KB/s, minb=5013KB/s, maxb=5013KB/s, mint=78241msec, maxt=78241msec
    WRITE: io=130596KB, aggrb=1669KB/s, minb=1669KB/s, maxb=1669KB/s, mint=78241msec, maxt=78241msec

    Disk stats (read/write):
    vda: ios=98064/32646, merge=0/15, ticks=2522744/2222708, in_queue=4819140, util=100.00%

  • AnthonySmithAnthonySmith Member, Patron Provider

    As you are seeing 0 IOPS but also a rete I suspect you have a problem with your script as both simply cannot be true, yes I am quite sure it is NVMe :)

  • @AnthonySmith said:
    As you are seeing 0 IOPS but also a rete I suspect you have a problem with your script as both simply cannot be true, yes I am quite sure it is NVMe :)

    The command I run is:

    fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 --name=test --filename=test --bs=4k --iodepth=64 --size=5G --readwrite=randrw --rwmixread=75

    Test results from my new debian 9 box ( canceled it in the middle, as too slow to finish, showing 40 minutes remanning ), as you can see something is definitely wrong with the node.

    fio-3.1
    Starting 1 process
    test: Laying out IO file (1 file / 5120MiB)
    bs: 1 (f=1): [m(1)][12.1%][r=1332KiB/s,w=512KiB/s][r=333,w=128 IOPS][eta 33m:31s]
    fio: terminating on signal 2
    Jobs: 1 (f=1): [m(1)][12.1%][r=0KiB/s,w=0KiB/s][r=0,w=0 IOPS][eta 33m:45s]
    test: (groupid=0, jobs=1): err= 0: pid=703: Mon Nov 26 18:24:39 2018
    read: IOPS=427, BW=1710KiB/s (1751kB/s)(464MiB/277748msec)
    bw ( KiB/s): min= 7, max=191808, per=100.00%, avg=2166.29, stdev=14524.17, samples=438
    iops : min= 1, max=47952, avg=541.51, stdev=3631.05, samples=438
    write: IOPS=142, BW=569KiB/s (583kB/s)(154MiB/277748msec)
    bw ( KiB/s): min= 7, max=63904, per=100.00%, avg=2357.04, stdev=8541.75, >samples=134
    iops : min= 1, max=15976, avg=589.22, stdev=2135.45, samples=134
    cpu : usr=0.12%, sys=0.39%, ctx=15183, majf=0, minf=8
    IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
    submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
    complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
    issued rwt: total=118707,39536,0, short=0,0,0, dropped=0,0,0
    latency : target=0, window=0, percentile=100.00%, depth=64

    Run status group 0 (all jobs):
    READ: bw=1710KiB/s (1751kB/s), 1710KiB/s-1710KiB/s (1751kB/s-1751kB/s), io=464MiB (486MB), run=277748-277748msec
    WRITE: bw=569KiB/s (583kB/s), 569KiB/s-569KiB/s (583kB/s-583kB/s), io=154MiB (162MB), run=277748-277748msec

    Disk stats (read/write):
    vda: ios=118748/39654, merge=0/60, ticks=9385816/7847792, in_queue=9093416, util=54.68%

    Test results from my home regular ssd drive:

    test: (g=0): rw=randrw, bs=4K-4K/4K-4K/4K-4K, ioengine=libaio, iodepth=64
    fio-2.16
    Starting 1 process
    test: Laying out IO file(s) (1 file(s) / 5120MB)
    Jobs: 1 (f=1): [m(1)] [100.0% done] [193.7MB/65016KB/0KB /s] [49.6K/16.3K/0 iops] [eta 00m:00s]
    test: (groupid=0, jobs=1): err= 0: pid=26692: Mon Nov 26 12:20:32 2018
    read : io=3838.9MB, bw=194180KB/s, iops=48544, runt= 20244msec
    write: io=1281.2MB, bw=64805KB/s, iops=16201, runt= 20244msec
    cpu : usr=12.96%, sys=39.93%, ctx=907262, majf=0, minf=9
    IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.1%, 32=0.1%, >=64=100.0%
    submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
    complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.1%, >=64=0.0%
    issued : total=r=982744/w=327976/d=0, short=r=0/w=0/d=0, drop=r=0/w=0/d=0
    latency : target=0, window=0, percentile=100.00%, depth=64

    Run status group 0 (all jobs):
    READ: io=3838.9MB, aggrb=194179KB/s, minb=194179KB/s, maxb=194179KB/s, mint=20244msec, maxt=20244msec
    WRITE: io=1281.2MB, aggrb=64804KB/s, minb=64804KB/s, maxb=64804KB/s, mint=20244msec, maxt=20244msec

    Disk stats (read/write):
    sda: ios=975704/327661, merge=2535/1872, ticks=862976/290464, in_queue=1153724, util=92.80%

  • AnthonySmithAnthonySmith Member, Patron Provider

    @seed4u I need to look further in to this, what I can say so far.

    I get the same results as you, I have tested this on 3 nodes now, 1 of them was just provisioned today and has 0 customers on it, I get the same issue.

    However when testing the backend storage on the node directly, no issues and it completes incredibly fast with great results.

    Right now I do not know the answer except to say I believe it is more a problem with the way that specific test works with NVMe backed KVM Virtual servers rather than an actual problem, all other IO tests complete exactly as expected.

    I don't expect to resolve this over night I am going to have to put some research in to it.

  • @AnthonySmith said:
    New shared hosting deal up, click the image to order:

    image

    Hey @AnthonySmith , I'm just teasing here but is there a chance you can bump up the number of add-on domains for this? I have a bunch of domains I use solely for email (hosted in another email provider) and host names for internal projects that needs single static "Page Intentionally Left Blank" placeholders. :smiley:

    Thanked by 1kiwidave
  • AnthonySmithAnthonySmith Member, Patron Provider

    just for the sake of updating the thread, I tracked this fio test not starting issue down to a kernel version, very odd, more research needed and customer moved to another node.

    @pullangcubo you get 20 add-ons

    Thanked by 1pullangcubo
  • seed4useed4u Member
    edited November 2018

    @AnthonySmith Thank you very much for solving the issue for me. Performance is spectacular now both on IO and the CPU, and makes me want to grab another one :smile:

    read : io=785812KB, bw=452396KB/s, iops=113099, runt= 1737msec
    write: io=262764KB, bw=151275KB/s, iops=37818, runt= 1737msec

    sysbench --num-threads=2 --test=cpu --cpu-max-prime=20000 run
    sysbench 0.4.12: multi-threaded system evaluation benchmark

    Running the test with following options:
    Number of threads: 2

    Doing CPU performance benchmark

    Threads started!
    Done.

    Maximum prime number checked in CPU test: 20000

    Test execution summary:
    total time: 9.9067s
    total number of events: 10000
    total time taken by event execution: 19.8089
    per-request statistics:
    min: 1.86ms
    avg: 1.98ms
    max: 5.14ms
    approx. 95 percentile: 2.20ms

    Threads fairness:
    events (avg/stddev): 5000.0000/15.00
    execution time (avg/stddev): 9.9044/0.00

  • @AnthonySmith Can you add stock? for UK 4GB OpenVZ or UK 2GB OpenVZ

Sign In or Register to comment.