disk io question

[asiahost]

I have old VE1.3 with two VM using kvm ,both under Centos5 kvm os which under E3200 with good Speed.

I install a new VE1.7 and try use qmrestore,and install one new os with kvm + raw i find the speed and IO keep high loading in My E8500 CPU, is there any way to check why the io and speed drop?

when i try install the new os with directadmin cp, my VE1.7 , server down and need reboot.

Thanks.

Both using SATA HDD

vps:~# pveperf /var/lib/vz
CPU BOGOMIPS: 12651.45
REGEX/SECOND: 593763
HD SIZE: 352.64 GB (/dev/mapper/pve-data)
BUFFERED READS: 55.27 MB/sec
AVERAGE SEEK TIME: 14.07 ms
FSYNCS/SECOND: 112.51
DNS EXT: 143.92 ms
DNS INT: 1763.95 ms

vps:~# pveversion -v
pve-manager: 1.7-10 (pve-manager/1.7/5323)
running kernel: 2.6.32-4-pve
proxmox-ve-2.6.32: 1.7-28
pve-kernel-2.6.32-4-pve: 2.6.32-28
qemu-server: 1.1-25
pve-firmware: 1.0-9
libpve-storage-perl: 1.0-16
vncterm: 0.9-2
vzctl: 3.0.24-1pve4
vzdump: 1.2-9
vzprocps: 2.0.11-1dso2
vzquota: 3.0.11-1
pve-qemu-kvm: 0.13.0-2
ksm-control-daemon: 1.0-4

 

[asiahost]

dmesg message

agpgart-intel 0000:00:00.0: Intel G45/G43 Chipset
agpgart-intel 0000:00:00.0: detected 65532K stolen memory
agpgart-intel 0000:00:00.0: AGP aperture is 256M @ 0xd0000000
Serial: 8250/16550 driver, 4 ports, IRQ sharing enabled
loop: module loaded
input: Macintosh mouse button emulation as /devices/virtual/input/input0
PNP: No PS/2 controller found. Probing ports directly.
serio: i8042 KBD port at 0x60,0x64 irq 1
serio: i8042 AUX port at 0x60,0x64 irq 12
mice: PS/2 mouse device common for all mice
ahci 0000:00:1f.2: version 3.0
ahci 0000:00:1f.2: PCI INT A -> GSI 18 (level, low) -> IRQ 18
alloc irq_desc for 27 on node -1
alloc kstat_irqs on node -1
ahci 0000:00:1f.2: irq 27 for MSI/MSI-X
ahci: SSS flag set, parallel bus scan disabled
ahci 0000:00:1f.2: AHCI 0001.0200 32 slots 4 ports 3 Gbps 0xf impl SATA mode
ahci 0000:00:1f.2: flags: 64bit ncq sntf stag pm led clo pio slum part ccc ems sxs
ahci 0000:00:1f.2: setting latency timer to 64
scsi0 : ahci
scsi1 : ahci
scsi2 : ahci
scsi3 : ahci
ata1: SATA max UDMA/133 abar m2048@0xfeafb000 port 0xfeafb100 irq 27
ata2: SATA max UDMA/133 abar m2048@0xfeafb000 port 0xfeafb180 irq 27
ata3: SATA max UDMA/133 abar m2048@0xfeafb000 port 0xfeafb200 irq 27
ata4: SATA max UDMA/133 abar m2048@0xfeafb000 port 0xfeafb280 irq 27
ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
ata1.00: ATA-8: WDC WD5000AADS-00M2B0, 01.00A01, max UDMA/133
ata1.00: 976773168 sectors, multi 0: LBA48 NCQ (depth 31/32), AA
ata1.00: configured for UDMA/133
scsi 0:0:0:0: Direct-Access ATA WDC WD5000AADS-0 01.0 PQ: 0 ANSI: 5
sd 0:0:0:0: Attached scsi generic sg0 type 0
sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

 

[tom]

you have too slow FSYNCS/SECOND: 112.51. looks like the write-cache on the disk is disabled.

use a hardware raid controller with BBU and FSYNCS/SECOND can go up to 3000 or more. or enable the harddrive cache on the harddisk, but this is not safe in the case of a power loss. you can/will loose data.

 

[asiahost]

Thanks for your advice.

is it relate to "Intel G45/G43 Chipset"? my old E3200 is under G31 with Fast and stable.

Sorry other then install the raid card, any other thing can do?

 

[tom]

Thanks for your advice.

is it relate to "Intel G45/G43 Chipset"? my old E3200 is under G31 with Fast and stable.

Sorry other then install the raid card, any other thing can do?

read above.

 

[asiahost]

Thanks , problem fixed.

 

[snowman66]

How much should i expect with 2x SAS 10k in Raid 0? Buff. reads gets only 40-45MB/s.

CPU BOGOMIPS: 24000.20
REGEX/SECOND: 948996
HD SIZE: 92.69 GB (/dev/mapper/pve-data)
BUFFERED READS: 40.90 MB/sec
AVERAGE SEEK TIME: 7.52 ms
FSYNCS/SECOND: 2422.51

Raid controller:

Smart Array P400 in Slot 1
Bus Interface: PCI
Slot: 1
Serial Number: PA2240J9SU66IR
RAID 6 (ADG) Status: Enabled
Controller Status: OK
Chassis Slot:
Hardware Revision: Rev B
Firmware Version: 1.18
Rebuild Priority: Low
Expand Priority: Low
Surface Scan Delay: 15 secs
Surface Scan Mode: Idle
Post Prompt Timeout: 0 secs
Cache Board Present: True
Cache Status: OK
Accelerator Ratio: 50% Read / 50% Write
Drive Write Cache: Enabled
Total Cache Size: 512 MB
No-Battery Write Cache: Disabled
Cache Backup Power Source: Batteries
Battery/Capacitor Count: 1
Battery/Capacitor Status: OK

 

[udo]

How much should i expect with 2x SAS 10k in Raid 0? Buff. reads gets only 40-45MB/s...:

Much more!
On my ( little bit old) test notebook with 5400 rpm drive i got faster read-values:

BUFFERED READS: 57.36 MB/sec

OK; seektime (16.57 ms) and fsyncs (448.56) are not so good - but with this disks...

With an good raid-controller i expected 180-240MB/s on a raid-0 with two fast sas-drives (i had only 15k 4ms sas-drives).

Udo

 

[snowman66]

I'm considering to buy two more disks to try with Raid 10 and see what happens but i think that will be better if i get new raid controller.
Thanks for the answer.

 

[ashes]

Hi Tom,

How can I run on a different partition pveperf? This is by default:

pveperf
CPU BOGOMIPS: 140804.83
REGEX/SECOND: 1205754
HD SIZE: 45.83 GB (/dev/mapper/system-root)
BUFFERED READS: 133.13 MB/sec
AVERAGE SEEK TIME: 8.66 ms
FSYNCS/SECOND: 1517.47
DNS EXT: 6.36 ms
DNS INT: 0.58 ms (domain.local)

but my virtual machines are on another raid controler with bbu

pveperf /dev/mapper/STORAGE-test
CPU BOGOMIPS: 140804.83
REGEX/SECOND: 1169296
HD SIZE: 9.84 GB (/dev/mapper/STORAGE-test)
BUFFERED READS: 262.56 MB/sec
AVERAGE SEEK TIME: 6.87 ms
open failed at /usr/bin/pveperf line 82.

 

[udo]

Hi Tom,

How can I run on a different partition pveperf? This is by default:

pveperf
CPU BOGOMIPS: 140804.83
REGEX/SECOND: 1205754
HD SIZE: 45.83 GB (/dev/mapper/system-root)
BUFFERED READS: 133.13 MB/sec
AVERAGE SEEK TIME: 8.66 ms
FSYNCS/SECOND: 1517.47
DNS EXT: 6.36 ms
DNS INT: 0.58 ms (domain.local)

but my virtual machines are on another raid controler with bbu

pveperf /dev/mapper/STORAGE-test
CPU BOGOMIPS: 140804.83
REGEX/SECOND: 1169296
HD SIZE: 9.84 GB (/dev/mapper/STORAGE-test)
BUFFERED READS: 262.56 MB/sec
AVERAGE SEEK TIME: 6.87 ms
open failed at /usr/bin/pveperf line 82.

Hi,
you need an mounted filesystem.
Create a lv (what you have allready done), format, mount and test:

lvcreate -L 10G -n test STORAGE
mkfs.ext3 /dev/STORAGE/test
mount /dev/STORAGE/test /mnt
pveperf /mnt

Udo

 

[ashes]

thank's udo!