What do people do with the cheap Kimsufi servers? KS1 & KS-LE-1?

plumberg

@Sanjue007 said:

@plumberg said:

@Sanjue007 said:
Wait..what.. I just got my 1 year old KS-1 1Gbps download speed..how weird is that?

Not weird. Enjoy

iperf3 Network Speed Tests (IPv4):
---------------------------------
Provider        | Location (Link)           | Send Speed      | Recv Speed      | Ping
-----           | -----                     | ----            | ----            | ----
Clouvider       | London, UK (10G)          | 90.8 Mbits/sec  | 559 Mbits/sec   | 3.34 ms
Scaleway        | Paris, FR (10G)           | 86.5 Mbits/sec  | 858 Mbits/sec   | 4.99 ms
NovoServe       | North Holland, NL (40G)   | 79.4 Mbits/sec  | 857 Mbits/sec   | 13.9 ms
Uztelecom       | Tashkent, UZ (10G)        | 20.9 Mbits/sec  | 168 Mbits/sec   | 104 ms
Clouvider       | NYC, NY, US (10G)         | 26.5 Mbits/sec  | 197 Mbits/sec   | 80.4 ms
Clouvider       | Dallas, TX, US (10G)      | 17.1 Mbits/sec  | 72.9 Mbits/sec  | 115 ms
Clouvider       | Los Angeles, CA, US (10G) | 15.9 Mbits/sec  | 55.9 Mbits/sec  | 133 ms

ethtool -S eno0 | grep error
     rx_errors: 1
     tx_errors: 0
     rx_length_errors: 1
     rx_over_errors: 0
     rx_crc_errors: 0
     rx_frame_errors: 0
     **rx_missed_errors: 772189**
     tx_aborted_errors: 0
     tx_carrier_errors: 0
     tx_fifo_errors: 0
     tx_heartbeat_errors: 0
     tx_window_errors: 0
     rx_long_length_errors: 0
     rx_short_length_errors: 1
     rx_align_errors: 0
     **rx_csum_offload_errors: 44**
     uncorr_ecc_errors: 0
     corr_ecc_errors: 0

Definetely something weired is going on.

M not qualified enough to see through these notes.

I know that once I enabled bbr things were pretty smooth and I was able to hit the designated speeds

rm_

@Sanjue007 said: Definetely something weired is going on.

Did you check for the whole story? E.g. on my server:

     rx_packets: 10202685590
     rx_missed_errors: 33600
     rx_csum_offload_good: 10034622014
     rx_csum_offload_errors: 8589

Surely I should run to complain in tiket about 8 thousand checksum errors? Out of 10 billion good ones?

Sanjue007

What is the customer care calling number for OVH france or Ireland
(for a person who is outside europian region)

Val

@Sanjue007 said:
What is the customer care calling number for OVH france or Ireland
(for a person who is outside europian region)

OVH does not support phone support for Kimsufi customers. Open a ticket if it's a hardware issue.

mbug

My KS-1 is in GRA and "We are sorry but we cannot replace your disk with a new one because your server is a KIMSUFI range." My HDD is over 70k+ hours.

darkimmortal

@mbug said:
My KS-1 is in GRA and "We are sorry but we cannot replace your disk with a new one because your server is a KIMSUFI range." My HDD is over 70k+ hours.

What’s wrong with that? They are all good quality disks, not consumer garbage that will die at 50k

plumberg

I think many ppl are hurt in the ass to see some folks getting quick replacements with new and / or higher size diks.... and their requests being straight out denied...

mbug

My disk read/write is very slow.

plumberg

@mbug said:
My disk read/write is very slow.

Based on what? Yabs?

mbug

yabs and fio

plumberg

@mbug said:
yabs and fio

How bad and slow is it?

stoned

I had both KS-1's disks replaced.

Just paste the SMART line for 70k hours, and provide server location, ask them, hey, the disk is old, it could die anytime, I'd like to keep the server for a few years without issues. What can be done about this?

80k and 70k disks were replaced with 33k and 40k. YMMV. I was hoping they might stick some 4TB in but nope.

stoned

@mbug said:
My disk read/write is very slow.

Post numbers for us to usee.

stoned

@plumberg said:
I think many ppl are hurt in the ass to see some folks getting quick replacements with new and / or higher size diks.... and their requests being straight out denied...

It also depends on how you ask. I had no luck when I just plain asked them about it. I had good luck when I pasted the smart log of 70k hours, and plainly stated that the disks need replacement, without asking, and what can be done about this.

Without the smart log in the initial ticket, they will refuse you giving you the reason that it's Kimsufi and you just get old drives.

Good luck.

plumberg

@stoned said:

@plumberg said:
I think many ppl are hurt in the ass to see some folks getting quick replacements with new and / or higher size diks.... and their requests being straight out denied...

It also depends on how you ask.

Without the smart log in the initial ticket,

Both valid points!!

ps20090

@stoned said:
Post numbers for us to usee.

curl -sL yabs.sh | bash
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #
#              Yet-Another-Bench-Script              #
#                     v2022-12-04                    #
# https://github.com/masonr/yet-another-bench-script #
# ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## #

Thu Dec  8 02:56:30 UTC 2022

Basic System Information:
---------------------------------
Uptime     : 71 days, 19 hours, 10 minutes
Processor  : Intel(R) Atom(TM) CPU N2800   @ 1.86GHz
CPU cores  : 4 @ 959.044 MHz
AES-NI     : ❌ Disabled
VM-x/AMD-V : ❌ Disabled
RAM        : 3.8 GiB
Swap       : 512.0 MiB
Disk       : 1.8 TiB
Distro     : Ubuntu 20.04.3 LTS
Kernel     : 5.4.0-126-generic

fio Disk Speed Tests (Mixed R/W 50/50):
---------------------------------
Block Size | 4k            (IOPS) | 64k           (IOPS)
  ------   | ---            ----  | ----           ---- 
Read       | 550.00 KB/s    (137) | 7.98 MB/s      (124)
Write      | 582.00 KB/s    (145) | 8.35 MB/s      (130)
Total      | 1.13 MB/s      (282) | 16.33 MB/s     (254)
           |                      |                     
Block Size | 512k          (IOPS) | 1m            (IOPS)
  ------   | ---            ----  | ----           ---- 
Read       | 31.04 MB/s      (60) | 36.73 MB/s      (35)
Write      | 33.32 MB/s      (65) | 40.07 MB/s      (39)
Total      | 64.37 MB/s     (125) | 76.80 MB/s      (74)

smartctl

SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   016    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   137   137   054    Pre-fail  Offline      -       79
  3 Spin_Up_Time            0x0007   100   100   024    Pre-fail  Always       -       372
  4 Start_Stop_Count        0x0012   100   100   000    Old_age   Always       -       139
  5 Reallocated_Sector_Ct   0x0033   100   100   005    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   067    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   142   142   020    Pre-fail  Offline      -       25
  9 Power_On_Hours          0x0012   092   092   000    Old_age   Always       -       59625
 10 Spin_Retry_Count        0x0013   100   100   060    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       136
192 Power-Off_Retract_Count 0x0032   099   099   000    Old_age   Always       -       1888
193 Load_Cycle_Count        0x0012   099   099   000    Old_age   Always       -       1888
194 Temperature_Celsius     0x0002   214   214   000    Old_age   Always       -       28 (Min/Max 15/51)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0022   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0008   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x000a   200   200   000    Old_age   Always       -       0

SMART Error Log Version: 1
No Errors Logged

I think I had it for around 1 year though cause I remember it was close to 50k hours when I first got it

plumberg

Seems ok for ks1

wii747

I use my KS1 as a proxmox backup server. As I have a 2TB HDD installed on my server.