Hi,
This afternoon without any change :
- No PVE configuration change
- No hardware change
- No new VM and nothing was delete as well ( most VMs are Windows 10 )
VMs become very slow and I noticed that CPU usage was very high like 35 for the last minute in an 8 core CPU ( 16 threads ).
This slow behaviour change overtime. I mean during a period of time it is OK then become slow again.
I run pveperf twice and as you can see the time it takes to run varys.
PVEPERF stops at FSYNCS/SECOND after that is runs fast again.
root@pve:~# time pveperf
CPU BOGOMIPS: 118162.56
REGEX/SECOND: 2394824
HD SIZE: 2770.98 GB (rpool/ROOT/pve-1)
FSYNCS/SECOND: 314.22
DNS EXT: 201.24 ms
DNS INT: 53.31 ms (universo.local)
real 1m18.396s
user 0m3.124s
sys 1m6.352s
root@pve:~#
root@pve:~# time pveperf
CPU BOGOMIPS: 118162.56
REGEX/SECOND: 2460989
HD SIZE: 2770.82 GB (rpool/ROOT/pve-1)
FSYNCS/SECOND: 316.33
DNS EXT: 199.34 ms
DNS INT: 78.34 ms (universo.local)
real 39m47.886s
user 0m3.109s
sys 39m35.217s
root@pve:~#
System configuration is :
CPU(s)
16 x AMD Ryzen 7 2700X Eight-Core Processor (1 Socket)
Kernel Version
Linux 4.15.17-1-pve #1 SMP PVE 4.15.17-9 (Wed, 9 May 2018 13:31:43 +0200)
PVE Manager Version
pve-manager/5.2-1/0fcd7879
I'm using ZFS and Pool health looks good.
==========
root@pve:~# zpool status -v
pool: rpool
state: ONLINE
scan: scrub repaired 0B in 7h27m with 0 errors on Sun Mar 10 07:51:25 2019
config:
NAME STATE READ WRITE CKSUM
rpool ONLINE 0 0 0
mirror-0 ONLINE 0 0 0
sda2 ONLINE 0 0 0
sdb2 ONLINE 0 0 0
logs
nvme0n1p1 ONLINE 0 0 0
cache
nvme0n1p2 ONLINE 0 0 0
errors: No known data errors
root@pve:~#
==========
I hope someone can help / give some directions.
Best Regards,
Ricardo Jorge
This afternoon without any change :
- No PVE configuration change
- No hardware change
- No new VM and nothing was delete as well ( most VMs are Windows 10 )
VMs become very slow and I noticed that CPU usage was very high like 35 for the last minute in an 8 core CPU ( 16 threads ).
This slow behaviour change overtime. I mean during a period of time it is OK then become slow again.
I run pveperf twice and as you can see the time it takes to run varys.
PVEPERF stops at FSYNCS/SECOND after that is runs fast again.
root@pve:~# time pveperf
CPU BOGOMIPS: 118162.56
REGEX/SECOND: 2394824
HD SIZE: 2770.98 GB (rpool/ROOT/pve-1)
FSYNCS/SECOND: 314.22
DNS EXT: 201.24 ms
DNS INT: 53.31 ms (universo.local)
real 1m18.396s
user 0m3.124s
sys 1m6.352s
root@pve:~#
root@pve:~# time pveperf
CPU BOGOMIPS: 118162.56
REGEX/SECOND: 2460989
HD SIZE: 2770.82 GB (rpool/ROOT/pve-1)
FSYNCS/SECOND: 316.33
DNS EXT: 199.34 ms
DNS INT: 78.34 ms (universo.local)
real 39m47.886s
user 0m3.109s
sys 39m35.217s
root@pve:~#
System configuration is :
CPU(s)
16 x AMD Ryzen 7 2700X Eight-Core Processor (1 Socket)
Kernel Version
Linux 4.15.17-1-pve #1 SMP PVE 4.15.17-9 (Wed, 9 May 2018 13:31:43 +0200)
PVE Manager Version
pve-manager/5.2-1/0fcd7879
I'm using ZFS and Pool health looks good.
==========
root@pve:~# zpool status -v
pool: rpool
state: ONLINE
scan: scrub repaired 0B in 7h27m with 0 errors on Sun Mar 10 07:51:25 2019
config:
NAME STATE READ WRITE CKSUM
rpool ONLINE 0 0 0
mirror-0 ONLINE 0 0 0
sda2 ONLINE 0 0 0
sdb2 ONLINE 0 0 0
logs
nvme0n1p1 ONLINE 0 0 0
cache
nvme0n1p2 ONLINE 0 0 0
errors: No known data errors
root@pve:~#
==========
I hope someone can help / give some directions.
Best Regards,
Ricardo Jorge