How to test vps performance?

[Medow7]

Hi:

There is an issue which we all face, which is how to test vps performance and how to know if the server is oversold. Espicialy these days with 128 GB ram server sharing the same processor and hard drives.

I have a vps with xxxxxxx provider, and the network is fast and amazing but i am more concern about processor stress and harddrive performance which i guess is a way lower.

Usually it take about an hour or hour and a half to install cpanel, but when i test it on this vps it took almost 6 hours to complete installation of cpanel, also when i apt-get install any packages it took to much time to complete install these packages.

Here is some test:

Processor test:

root@server:~# cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 45
model name      : Intel(R) Xeon(R) CPU E5-1650 0 @ 3.20GHz
stepping        : 7
cpu MHz         : 3200.143
cache size      : 12288 KB
physical id     : 0
siblings        : 12
core id         : 0
cpu cores       : 6
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid
bogomips        : 6400.28
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 45
model name      : Intel(R) Xeon(R) CPU E5-1650 0 @ 3.20GHz
stepping        : 7
cpu MHz         : 3200.143
cache size      : 12288 KB
physical id     : 0
siblings        : 12
core id         : 1
cpu cores       : 6
apicid          : 2
initial apicid  : 2
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid
bogomips        : 6400.28
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:

processor       : 2
vendor_id       : GenuineIntel
cpu family      : 6
model           : 45
model name      : Intel(R) Xeon(R) CPU E5-1650 0 @ 3.20GHz
stepping        : 7
cpu MHz         : 3200.143
cache size      : 12288 KB
physical id     : 0
siblings        : 12
core id         : 2
cpu cores       : 6
apicid          : 4
initial apicid  : 4
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid
bogomips        : 6400.28
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:

processor       : 3
vendor_id       : GenuineIntel
cpu family      : 6
model           : 45
model name      : Intel(R) Xeon(R) CPU E5-1650 0 @ 3.20GHz
stepping        : 7
cpu MHz         : 3200.143
cache size      : 12288 KB
physical id     : 0
siblings        : 12
core id         : 3
cpu cores       : 6
apicid          : 6
initial apicid  : 6
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid
bogomips        : 6400.28
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:

Network test:

root@server:~# wget cachefly.cachefly.net/100mb.test
--2013-03-02 16:19:08--  http://cachefly.cachefly.net/100mb.test
Resolving cachefly.cachefly.net (cachefly.cachefly.net)... 178.33.235.161
Connecting to cachefly.cachefly.net (cachefly.cachefly.net)|178.33.235.161|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 104857600 (100M) [application/octet-stream]
Saving to: `100mb.test'

100%[======================================>] 104,857,600 76.6M/s   in 1.3s

2013-03-02 16:19:10 (76.6 MB/s) - `100mb.test' saved [104857600/104857600]

Usually above 80M.

I/O test:

root@server:~# 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) copied, 23.7552 s, 45.2 MB/s

How about these tests?

Thanks.

 

[REAK]

6 hours to install cpanel ?, even with the network being fast enough there is something seriously wrong with the server.

Even the I/O seems slow (is it a raid config ?) , on an average the I/O is usually 60-120 MB/s.

For CPU and Memory stressing you can use UnixBench and can compare result.

 

[Cometolearn]

oversold server , i have same condition when i buy the vps from cheap provider :D

 

[cvrle77]

dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync

to get adequate results, you need to run this command multiple times and check the average.

 

[Medow7]

6 hours to install cpanel ?, even with the network being fast enough there is something seriously wrong with the server.

Even the I/O seems slow (is it a raid config ?) , on an average the I/O is usually 60-120 MB/s.

For CPU and Memory stressing you can use UnixBench and can compare result.

This the strange thing , when ever i wget something it was transfered very fast. I mean packages was downloaded very fast but it take too much time to installed.

And it was raid 0.

to get adequate results, you need to run this command multiple times and check the average.

This is a new result:

root@server:# 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) copied, 23.4877 s, 45.7 MB/s

I test it multiple times and it was never exceed 50MB/s

 

[cvrle77]

Simply contact your provider, submit proof to him, and tell him to move you on less crowded server. If he refuses, you know what to do.

 

[Loonycgb2]

Your vps "bean counters" are not adjusted correctly for the server.

Your host needs to configure it correctly and also giving every user 4 cpus will definitely cause a huge slow down since everyone will be sharing atleast one cpu all together and useing up to 80% of allowed cpu.

 

[Kruno]

CPU and network are great, but disk I/O is below average nowadays.

Your disk I/O is definitely effecting cPanel's installation and overall performance. I/O is most important when it comes to VPS Nodes.

 

[Loonycgb2]

CPU and network are great, but disk I/O is below average nowadays.

Your disk I/O is definitely effecting cPanel's installation and overall performance. I/O is most important when it comes to VPS Nodes.

Well said Krun!x..

 

[concerto49]

Try serverbear.com for tests. Nice comparison with other providers too.

 

[Medow7]

CPU and network are great, but disk I/O is below average nowadays.

Your disk I/O is definitely effecting cPanel's installation and overall performance. I/O is most important when it comes to VPS Nodes.

My provider telling me they are aware of some problems on that node, and he transfer my vps to other node.
Here is my I/O test:

root@server:# 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) copied, 5.19567 s, 207 MB/s

 

[Kruno]

My provider telling me they are aware of some problems on that node, and he transfer my vps to other node.
Here is my I/O test:

root@server:# 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) copied, 5.19567 s, 207 MB/s

Right now it is great! What provider is it btw?

 

[Cheetah]

@Kruno, looks like the vps node is hosted at ovh.

 

[Medow7]

Right now it is great! What provider is it btw?

Sorry Kruno, i have to respect his privacy, any way he is a provider here in wjunction.

@Kruno, looks like the vps node is hosted at ovh.

No, it is ECATEL NL.