Howdy, Stranger!

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


Storage KVM-Romania-1gbps-2tb hdd-10tb traffic/mo Only 50 in stock ! - 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.

Storage KVM-Romania-1gbps-2tb hdd-10tb traffic/mo Only 50 in stock !

2

Comments

  • Don't worry about Geekbench. It's ok without it. Thank you.

  • @ps20090 You need create swap. Than Geekbench will run ok.

    # Initialise swap file
    dd if=/dev/zero of=/swapfile count=1024 bs=1M
    # Protect it from snooping
    chown root.root /swapfile
    chmod 600 /swapfile
    # Make it into a swap file
    mkswap /swapfile
    # Mount swap file
    swapon /swapfile
    # Make it mounted at reboot
    cp -av /etc/fstab /etc/fstab.bck
    echo /swapfile swap swap defaults 0 0 >> /etc/fstab # Care!! '>>'
    
    Thanked by 2RedSox kkrajk
  • ps20090ps20090 Member
    edited October 2020

    @default said: Don't worry about Geekbench. It's ok without it. Thank you .

    curl -sL yabs.sh | bash -s -- -9
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    #              Yet-Another-Bench-Script              #
    #                     v2020-09-21                    #
    # https://github.com/masonr/yet-another-bench-script #
    # ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
    
    Sat Oct 31 23:12:14 UTC 2020
    
    Basic System Information:
    ---------------------------------
    Processor  : Common KVM processor
    CPU cores  : 1 @ 1795.672 MHz
    AES-NI     : ❌ Disabled
    VM-x/AMD-V : ❌ Disabled
    RAM        : 985M
    Swap       : 0B
    Disk       : 2.0T
    
    fio Disk Speed Tests (Mixed R/W 50/50):
    ---------------------------------
    Block Size | 4k            (IOPS) | 64k           (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 9.22 MB/s     (2.3k) | 5.40 MB/s       (84)
    Write      | 9.26 MB/s     (2.3k) | 5.71 MB/s       (89)
    Total      | 18.48 MB/s    (4.6k) | 11.11 MB/s     (173)
               |                      |                     
    Block Size | 512k          (IOPS) | 1m            (IOPS)
      ------   | ---            ----  | ----           ---- 
    Read       | 10.64 MB/s      (20) | 21.03 MB/s      (20)
    Write      | 11.75 MB/s      (22) | 23.08 MB/s      (22)
    Total      | 22.39 MB/s      (42) | 44.11 MB/s      (42)
    
    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed     
                    |                           |                 |                
    Clouvider       | London, UK (10G)          | 838 Mbits/sec   | 273 Mbits/sec  
    Online.net      | Paris, FR (10G)           | 846 Mbits/sec   | 324 Mbits/sec  
    WorldStream     | The Netherlands (10G)     | 809 Mbits/sec   | 361 Mbits/sec  
    Wifx            | Zurich, CH (10G)          | 793 Mbits/sec   | 265 Mbits/sec  
    Biznet          | Jakarta, Indonesia (1G)   | 597 Mbits/sec   | 54.6 Mbits/sec 
    Clouvider       | NYC, NY, US (10G)         | 767 Mbits/sec   | 176 Mbits/sec  
    Velocity Online | Tallahassee, FL, US (10G) | 716 Mbits/sec   | 169 Mbits/sec  
    Clouvider       | Los Angeles, CA, US (10G) | busy            | busy           
    Iveloz Telecom  | Sao Paulo, BR (2G)        | busy            | busy           
    
    Geekbench 4 Benchmark Test:
    ---------------------------------
    Test            | Value                         
                    |                               
    Single Core     | 1299                          
    Multi Core      | 1240                          
    Full Test       | https://browser.geekbench.com/v4/cpu/15848806
    
    Geekbench 5 test failed. Run manually to determine cause.
    
  • @ps20090 said: Model QEMU Standard PC (i440FX + PIIX, 1996) 🙄

  • @seenu said:

    @ps20090 said: Model QEMU Standard PC (i440FX + PIIX, 1996)

    🙄

    You could ask them to enable AES-NI

  • seenuseenu Member
    edited November 2020

    I strongly think...this is toooo old CPU.

    just running rsync from another vps and running top shows rsync, sshd commands using 90+% cpu

  • Plot twist: storage running on Pentium 1 processor.

    Thanked by 1yoursunny
  • To help people install custom isos:

    As noted earlier in this thread CTRL B at the ipxe prompt:

    dhcp doesn't work @hostsolutions ipxe prompt so you need to set a static ip:

    set net0/ip 1.2.3.4
    set net0/netmask 255.255.252.0
    set net0/gateway 5.6.7.8
    set dns 9.9.9.9
    ifopen net0
    chain --autofree http://boot.netboot.xyz
    
  • @itoffshore said: To help people install custom isos:

    As noted earlier in this thread CTRL B at the ipxe prompt:

    dhcp doesn't work @hostsolutions ipxe prompt so you need to set a static ip:

    set net0/ip 1.2.3.4

    set net0/netmask 255.255.252.0
    set net0/gateway 5.6.7.8
    set dns 9.9.9.9
    ifopen net0
    chain --autofree http://boot.netboot.xyz

    We are agree with such practice but i want to advert some "windows" users/aplication , this package was not created to have huge cpu consumition/usage so to prevent suspend ora any discution better to know before use it.

  • @cociu - they make great Alpine Linux boxes ;o)

  • I dunno what Cociu did with network, but I can playback ISOs via Plex (sort of Virtual Mount Drive to playback ISOs remotely, doesn't take a lot of CPU when Direct Play) at 1080p without transcoding and it plays smoothly, without stutters or anything.

  • PilzbaumPilzbaum Member
    edited November 2020

    Thanks for the mention however

    @itoffshore said:

    dhcp doesn't work @hostsolutions ipxe prompt so you need to set a static ip:

    was certainly not the case for my nvme kvm in Romania. For me, dhcp worked just fine. Interesting that it appers to be different across nodes.. Weird

  • itoffshoreitoffshore Member
    edited November 2020

    @Pilzbaum the dhcp issue was on a kvm that was recently created (converted after OpenVZ was phased out).

    Overall it's been fine.

    I now have iPXE set as a boot option for a Rescue ISO

  • @ps20090 said:
    I dunno what Cociu did with network, but I can playback ISOs via Plex (sort of Virtual Mount Drive to playback ISOs remotely, doesn't take a lot of CPU when Direct Play) at 1080p without transcoding and it plays smoothly, without stutters or anything.

    probably you are lucky!

    for me just rsync is enough for cpu to reach 100%

  • @seenu said:

    @ps20090 said:
    I dunno what Cociu did with network, but I can playback ISOs via Plex (sort of Virtual Mount Drive to playback ISOs remotely, doesn't take a lot of CPU when Direct Play) at 1080p without transcoding and it plays smoothly, without stutters or anything.

    probably you are lucky!

    for me just rsync is enough for cpu to reach 100%

    Are you running rsync inside cociu VPS? Or running it from other VPS?

  • @chocolateshirt said:

    @seenu said:

    @ps20090 said:
    I dunno what Cociu did with network, but I can playback ISOs via Plex (sort of Virtual Mount Drive to playback ISOs remotely, doesn't take a lot of CPU when Direct Play) at 1080p without transcoding and it plays smoothly, without stutters or anything.

    probably you are lucky!

    for me just rsync is enough for cpu to reach 100%

    Are you running rsync inside cociu VPS? Or running it from other VPS?

    running rsync from other vps
    i.e. copying from other vps to cociu's vps.

  • I see.. you could try to reduce the transfer to 2 files at a time, by default rsync transfer 4 files at a time..

  • I found it strange that AES-NI is disabled since the E5-2450L does support it. I went digging around a bit and found this page which explains how you can force AES-NI usage. I had to set the env variable to OPENSSL_ia32cap=0x200000000000400 instead though (notice the lack of a + character). The kernel module also works.

    Benchmark before forcing AES-NI:

    root@vm1:~/aes_ni_force# openssl speed -elapsed -evp aes-128-cbc
    You have chosen to measure elapsed time instead of user CPU time.
    Doing aes-128-cbc for 3s on 16 size blocks: 7694123 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 64 size blocks: 1685387 aes-128-cbc's in 3.01s
    Doing aes-128-cbc for 3s on 256 size blocks: 552983 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 1024 size blocks: 307286 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 8192 size blocks: 38000 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 16384 size blocks: 20698 aes-128-cbc's in 3.00s
    OpenSSL 1.1.1  11 Sep 2018
    built on: Wed May 27 19:15:54 2020 UTC
    options:bn(64,64) rc4(8x,int) des(int) aes(partial) blowfish(ptr) 
    compiler: gcc -fPIC -pthread -m64 -Wa,--noexecstack -Wall -Wa,--noexecstack -g -O2 -fdebug-prefix-map=/build/openssl-dyPhHZ/openssl-1.1.1=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPADLOCK_ASM -DPOLY1305_ASM -DNDEBUG -Wdate-time -D_FORTIFY_SOURCE=2
    The 'numbers' are in 1000s of bytes per second processed.
    type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes  16384 bytes
    aes-128-cbc      41035.32k    35835.47k    47187.88k   104886.95k   103765.33k   113038.68k
    
    root@vm1:~# cryptsetup benchmark
    # Tests are approximate using memory only (no storage IO).
    PBKDF2-sha1       226768 iterations per second for 256-bit key
    PBKDF2-sha256     286809 iterations per second for 256-bit key
    PBKDF2-sha512     216647 iterations per second for 256-bit key
    PBKDF2-ripemd160  200109 iterations per second for 256-bit key
    PBKDF2-whirlpool  168256 iterations per second for 256-bit key
    argon2i       4 iterations, 147985 memory, 4 parallel threads (CPUs) for 256-bit key (requested 2000 ms time)
    argon2id      4 iterations, 143659 memory, 4 parallel threads (CPUs) for 256-bit key (requested 2000 ms time)
    #     Algorithm | Key |  Encryption |  Decryption
            aes-cbc   128b    67.1 MiB/s    67.8 MiB/s
        serpent-cbc   128b    22.7 MiB/s   100.1 MiB/s
        twofish-cbc   128b    52.3 MiB/s    53.7 MiB/s
            aes-cbc   256b    61.4 MiB/s    61.8 MiB/s
        serpent-cbc   256b    27.4 MiB/s    99.2 MiB/s
        twofish-cbc   256b    53.1 MiB/s    57.2 MiB/s
            aes-xts   256b    32.8 MiB/s    72.5 MiB/s
        serpent-xts   256b    79.7 MiB/s    83.1 MiB/s
        twofish-xts   256b    52.4 MiB/s    54.8 MiB/s
            aes-xts   512b    57.7 MiB/s    30.5 MiB/s
        serpent-xts   512b    82.4 MiB/s    98.2 MiB/s
        twofish-xts   512b    49.3 MiB/s    53.5 MiB/s
    

    Benchmark after forcing AES-NI:

    root@vm1:~/aes_ni_force# env OPENSSL_ia32cap=0x200000200000000 openssl speed -elapsed -evp aes-128-cbc
    You have chosen to measure elapsed time instead of user CPU time.
    Doing aes-128-cbc for 3s on 16 size blocks: 43118080 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 64 size blocks: 13080886 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 256 size blocks: 2908108 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 1024 size blocks: 854302 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 8192 size blocks: 95311 aes-128-cbc's in 3.00s
    Doing aes-128-cbc for 3s on 16384 size blocks: 46607 aes-128-cbc's in 3.00s
    OpenSSL 1.1.1  11 Sep 2018
    built on: Wed May 27 19:15:54 2020 UTC
    options:bn(64,64) rc4(8x,int) des(int) aes(partial) blowfish(ptr) 
    compiler: gcc -fPIC -pthread -m64 -Wa,--noexecstack -Wall -Wa,--noexecstack -g -O2 -fdebug-prefix-map=/build/openssl-dyPhHZ/openssl-1.1.1=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPADLOCK_ASM -DPOLY1305_ASM -DNDEBUG -Wdate-time -D_FORTIFY_SOURCE=2
    The 'numbers' are in 1000s of bytes per second processed.
    type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes  16384 bytes
    aes-128-cbc     229963.09k   279058.90k   248158.55k   291601.75k   260262.57k   254536.36k
    
    root@vm1:~/aes_ni_force# cryptsetup benchmark
    # Tests are approximate using memory only (no storage IO).
    PBKDF2-sha1       231167 iterations per second for 256-bit key
    PBKDF2-sha256     222344 iterations per second for 256-bit key
    PBKDF2-sha512     224054 iterations per second for 256-bit key
    PBKDF2-ripemd160  195922 iterations per second for 256-bit key
    PBKDF2-whirlpool  151879 iterations per second for 256-bit key
    argon2i       4 iterations, 126612 memory, 4 parallel threads (CPUs) for 256-bit key (requested 2000 ms time)
    argon2id      4 iterations, 143037 memory, 4 parallel threads (CPUs) for 256-bit key (requested 2000 ms time)
    #     Algorithm | Key |  Encryption |  Decryption
            aes-cbc   128b   216.5 MiB/s   499.4 MiB/s
        serpent-cbc   128b    19.2 MiB/s    67.6 MiB/s
        twofish-cbc   128b    50.9 MiB/s    41.0 MiB/s
            aes-cbc   256b   162.5 MiB/s   511.7 MiB/s
        serpent-cbc   256b    30.8 MiB/s    99.1 MiB/s
        twofish-cbc   256b    38.5 MiB/s    52.9 MiB/s
            aes-xts   256b   347.2 MiB/s   368.6 MiB/s
        serpent-xts   256b    68.7 MiB/s   102.8 MiB/s
        twofish-xts   256b    54.6 MiB/s    59.8 MiB/s
            aes-xts   512b   357.4 MiB/s   374.6 MiB/s
        serpent-xts   512b   105.4 MiB/s    88.6 MiB/s
        twofish-xts   512b    30.6 MiB/s    41.7 MiB/s
    

    To compile the kernel module, make a directory aes_ni_force and add the following files (all based on these instructions):

    aes_ni_force.c

    #include <linux/init.h>
    #include <linux/module.h>
    #include <linux/kernel.h>
    #include <linux/bitops.h>
    
    
    MODULE_LICENSE("GPL");
    MODULE_AUTHOR("David Hoppenbrouwers");
    MODULE_DESCRIPTION("Force usage of AES-NI in kernel");
    MODULE_VERSION("0.0.1");
    
    
    static int __init lkm_example_init(void) {
        printk(KERN_INFO "Forcing AES-NI\n");
        set_bit(153, (unsigned long *)(boot_cpu_data.x86_capability));
        return 0;
    }
    
    static void __exit lkm_example_exit(void) {
        printk(KERN_INFO "Un-forcing AES-NI\n");
    }
    
    
    module_init(lkm_example_init);
    module_exit(lkm_example_exit);
    

    Makefile

    obj-m += aes_ni_force.o
    
    
    all:
        make -C /lib/modules/$(shell uname -r)/build M=$(PWD) modules
    
    clean:
        make -C /lib/modules/$(shell uname -r)/build M=$(PWD) clean
    

    Then run these commands:

    $ apt install build-essential linux-headers-`uname -r`
    $ make
    $ insmod aes_ni_force.ko
    $ modprobe aesni_intel
    

    As for the magic constant in OPENSSL_ia32cap: I've derived it by checking how
    CPUID works, reading the manpage and after finding a random StackOverflow
    answer I came up with this:

    extern unsigned int OPENSSL_ia32cap_P[];
    
    
    void main() {
        printf("0: %x\n", OPENSSL_ia32cap_P[0]);
        printf("1: %x\n", OPENSSL_ia32cap_P[1]);
        printf("2: %x\n", OPENSSL_ia32cap_P[2]);
        printf("3: %x\n", OPENSSL_ia32cap_P[3]);
    }
    
    • Put the above in `main.c´
    • Compile with gcc main.c -lcrypto -static
    • Run with ./a.out
    • Launch python3 (or whatever really) and type this:

      • Put the first number in a = 0x<value>
      • Put the second number in ´b = 0x`
      • Execute this: hex(a | (b << 32) | (1 << 57))
      • Pass the value you got to OPENSSL_ia32cap
    • Run OPENSSL_ia32cap=<value> ./a.out and make sure the output is the
      same (aside from the (1 << 57) that got added). If it is not, then
      don't use the value, otherwise your day may get ruined.

    If you want to set the env variable for any systemd services execute systemctl edit <service>
    and add the following:

    [Service]
    Environment=OPENSSL_ia32cap=<value>
    
    Thanked by 1jugganuts
  • Also this CloudFlare Captcha bullshit does not work properly and is driving me nuts

    Thanked by 1Devil
  • What is the average download/upload speed?

  • edited November 2020

    @thammy321 said:
    What is the average download/upload speed?

    This:

    @ps20090 said:

    @default said: Don't worry about Geekbench. It's ok without it. Thank you.

    iperf3 Network Speed Tests (IPv4):
    ---------------------------------
    Provider        | Location (Link)           | Send Speed      | Recv Speed     
                    |                           |                 |                
    Clouvider       | London, UK (10G)          | 838 Mbits/sec   | 273 Mbits/sec  
    Online.net      | Paris, FR (10G)           | 846 Mbits/sec   | 324 Mbits/sec  
    WorldStream     | The Netherlands (10G)     | 809 Mbits/sec   | 361 Mbits/sec  
    Wifx            | Zurich, CH (10G)          | 793 Mbits/sec   | 265 Mbits/sec  
    Biznet          | Jakarta, Indonesia (1G)   | 597 Mbits/sec   | 54.6 Mbits/sec 
    Clouvider       | NYC, NY, US (10G)         | 767 Mbits/sec   | 176 Mbits/sec  
    Velocity Online | Tallahassee, FL, US (10G) | 716 Mbits/sec   | 169 Mbits/sec  
    Clouvider       | Los Angeles, CA, US (10G) | busy            | busy           
    Iveloz Telecom  | Sao Paulo, BR (2G)        | busy            | busy           
    
    
    Thanked by 1thammy321
  • Butine25Butine25 Member
    edited November 2020

    Hi cociu !
    Thanks for this offer

    Do you know when the last VPS will be deliver ?
    Thanks

  • @Butine25 said: Do you know when the last VPS will be deliver ?

    Thanks

    we are focused with some norway problems but definetly will be today lather.

    Thanked by 3Butine25 bdl msallak1
  • @cociu said:

    @Butine25 said: Do you know when the last VPS will be deliver ?

    Thanks

    we are focused with some norway problems but definetly will be today lather.

    well, I'm waitin' in my bath ;)

    Thanked by 1xaoc
  • @cociu said:

    @Butine25 said: Do you know when the last VPS will be deliver ?

    Thanks

    we are focused with some norway problems but definetly will be today lather.

    Hello !

    My bath is cold :'(
    But good luck in Norway, we're patient ;)

  • @cociu said: Thanks

    How many internet providers/internet route options do you have in Romania? Do you know how I can find which internet provider/internet route my VPS in Romania is using? This new 2TB VPS works so much better network wise to me in computer in US, like it feels much more stable and speed is quite consistent compared to my other old VPS from you.

  • lentrolentro Member, Host Rep

    @ps20090 said: Do you know how I can find which internet provider/internet route my VPS in Romania is using

    Traceroute?

    Doesn't seem to be many peering providers: https://bgp.he.net/AS44220

    Thanked by 1ps20090
  • Butine25Butine25 Member
    edited November 2020

    Hello Houston

    Do you hear me?
    Seems to have a problem this morning
    No connection at all

    Am I alone?

  • You're not alone, just lost my ssh connection.

    Thanked by 1Butine25
  • dfroedfroe Member, Host Rep

    No need to call Houston.
    This is just a temporary network outage which comes for free with your service.
    As soon as we are leaving the 'dark' side of the moon, connectivity should be established again.
    Hope you feel better knowing you are not alone out there at all. :)

Sign In or Register to comment.