[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-users] Windows 2008 - slow upload

James Harper schrieb:

Just to get this info in one spot (sorry if I'm asking you to repeat
yourselves), please tell me the versions of:

Xen (hypervisor)
Dom0 Kernel

host                   : greatmama-n2
release                : 2.6.26-2-xen-amd64
version                : #1 SMP Sun Jul 26 22:39:03 UTC 2009
machine                : x86_64
nr_cpus                : 4
nr_nodes               : 1
cores_per_socket       : 4
threads_per_core       : 1
cpu_mhz                : 2333
hw_caps : bfebfbff:20000800:00000000:00000140:000ce3bd:00000000:00000001
total_memory           : 4093
free_memory            : 2083
node_to_cpu            : node0:0-3
xen_major              : 3
xen_minor              : 2
xen_extra              : -1
xen_caps : xen-3.0-x86_64 xen-3.0-x86_32p hvm-3.0-x86_32 hvm-3.0-x86_32p hvm-3.0-x86_64
xen_scheduler          : credit
xen_pagesize           : 4096
platform_params        : virt_start=0xffff800000000000
xen_changeset          : unavailable
cc_compiler            : gcc version 4.3.1 (Debian 4.3.1-2)
cc_compile_by          : waldi
cc_compile_domain      : debian.org
cc_compile_date        : Sat Jun 28 09:32:18 UTC 2008
xend_config_format     : 4

Dom0 kernel patch source if you aren't running the standard 2.6.18
kernel that ships with Xen, eg a distro kernel perhaps?

all plain debian lenny

Dom0 network module (eg e1000e)

e1000e on eth0
bnx2 on eth2

Dom0 network card (just the make and chipset should be fine)


0e:00.0 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet Controller (rev 06) Subsystem: Hewlett-Packard Company NC360T PCI Express Dual Port Gigabit Server Adapter
        Flags: bus master, fast devsel, latency 0, IRQ 17
        Memory at fdfe0000 (32-bit, non-prefetchable) [size=128K]
        Memory at fdfc0000 (32-bit, non-prefetchable) [size=128K]
        I/O ports at 6000 [size=32]
        [virtual] Expansion ROM at d1100000 [disabled] [size=128K]
        Capabilities: [c8] Power Management version 2
Capabilities: [d0] Message Signalled Interrupts: Mask- 64bit+ Queue=0/0 Enable-
        Capabilities: [e0] Express Endpoint, MSI 00
        Capabilities: [100] Advanced Error Reporting <?>
        Capabilities: [140] Device Serial Number 5c-f0-55-ff-ff-29-1f-00
        Kernel driver in use: e1000e
        Kernel modules: e1000e


03:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5708 Gigabit Ethernet (rev 12) Subsystem: Hewlett-Packard Company NC373i Integrated Multifunction Gigabit Server Adapter Flags: bus master, 66MHz, medium devsel, latency 64, IRQ 16 Memory at f8000000 (64-bit, non-prefetchable) [size=32M] [virtual] Expansion ROM at d1300000 [disabled] [size=2K] Capabilities: [40] PCI-X non-bridge device Capabilities: [48] Power Management version 2 Capabilities: [50] Vital Product Data <?> Capabilities: [58] Message Signalled Interrupts: Mask- 64bit+ Queue=0/0 Enable- Kernel driver in use: bnx2
        Kernel modules: bnx2

TX speed from DomU to Dom0 as measured with 'iperf -w1m' (approx will be

For now I only have output/speed of some (bacula) backup runs. Receiving bacula storage daemon resides in Dom0, the sending file-daemon in domU. I get a rate about 1.3 MB/s. Whithout GPLPV now I get rates about 6-7 MB/s.

TX speed from DomU to a physical machine on the other side of a 1GBit
interface from Dom0

At the moment I don't have any phy machine in the same subnet. But I've measured filetransfer (smb) speed between the GPLPV server (TX) and another WinHVM on the same subnet: About poorly 65 kB/s. In the other direction I get rates about 2.5-3 MB/s (smb traffic). But the other HVM didn't have GPLPV installed so the bottleneck here was quemu on the peer.

Maybe I also should  play around with offloading.


Xen-users mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.