WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-users

Re: [Xen-users] Release 0.8.9 of GPL PV drivers for Windows

To: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: Re: [Xen-users] Release 0.8.9 of GPL PV drivers for Windows
From: jim burns <jim_burn@xxxxxxxxxxxxx>
Date: Sun, 27 Apr 2008 12:10:35 -0400
Delivery-date: Sun, 27 Apr 2008 09:11:14 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <AEC6C66638C05B468B556EA548C1A77D013DC584@trantor>
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
References: <AEC6C66638C05B468B556EA548C1A77D013DC578@trantor> <200804270316.09691.jim_burn@xxxxxxxxxxxxx> <AEC6C66638C05B468B556EA548C1A77D013DC584@trantor> (sfid-20080427_075031_654691_A26268B0)
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: KMail/1.9.9
On Sunday April 27 2008 07:36:46 am James Harper wrote:
> Ouch. I was confident I'd fixed all of those hanging problems. I can
> enable and disable those settings all I like and it never misses a beat
> - the driver shuts itself down and restarts without a problem. Can you
> tell me more about your test system?

From a previous benchmark post, 'Release 0.8.0 of GPL PV Drivers for Windows':

Equipment: core duo 2300, 1.66ghz each, 2M, sata drive configured for UDMA/100
System: fc8 32bit pae, xen 3.1.2, xen.gz 3.1.3 [updated from 3.1.0-rc7], dom0 
2.6.21
Tested hvm: XP Pro SP2, 2002 w/512M

Method:

The version tested was 1.7.0, to avoid having to apply the kernel patch that 
comes with 2.0.2. The binaries downloaded were from the project homepage 
http://dast.nlanr.net/Projects/Iperf/#download. For linux, I chose the 'Linux 
libc 2.3 binary and (on fc8 at least) I still had to install the 
compat-libstdc++-33 package to get it to run.

> Scatter/Gather disabled isn't really a tested configuration, but the
> others should work, although LSO disabled when Dom0 has it enabled could
> be problematic...

It isn't:
[822] > ethtool -k peth0
Offload parameters for peth0:
Cannot get device rx csum settings: Operation not supported
Cannot get device tx csum settings: Operation not supported
Cannot get device scatter-gather settings: Operation not supported
Cannot get device tcp segmentation offload settings: Operation not supported
Cannot get device udp large send offload settings: Operation not supported
rx-checksumming: off
tx-checksumming: off
scatter-gather: off
tcp segmentation offload: off
udp fragmentation offload: off
generic segmentation offload: off
jimb@Insp6400 04/27/08 11:15AM:~
[823] > lspci|grep Broad
03:00.0 Ethernet controller: Broadcom Corporation BCM4401-B0 100Base-TX (rev 
02)

 and thus the b44 driver.

>> Doing 'iperf -c dom0-name -l 1M -w 1M' gives 28.8 Mb/s, and reversing
the
>> direction (winxp as iperf server) gives 30.2 Mb/s.

> You can achieve the same results with -r to do a TX test followed by an
> RX (eg client/server roles reverse) or -d to do the TX and RX tests
> concurrently.

Ok:
iperf -c dom0-name -l 1M -w 1M -r gave me a BSOD:
DRIVER_IRQL_NOT_LESS_OR_EQUAL
[...]
*** STOP: 0x000000D1 (0x8945365C,0x00000002,0x00000001,0xF87EE6B4)

***    xennet.sys - Address F87EE6B4 base at F87EA000, DateStamp 4812c73b

Rebooting and trying again gave me minor variations in the STOP line:
*** STOP: 0x000000D1 (0x895D973C,0x00000002,0x00000001,0xF87FE6B4)

The dom0 output was:
[501] > iperf -s
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
[  4] local 192.168.1.100 port 5001 connected with 192.168.1.102 port 1038
[ ID] Interval       Transfer     Bandwidth
[  4]  0.0-10.2 sec  30.7 MBytes  25.3 Mbits/sec
------------------------------------------------------------
Client connecting to 192.168.1.102, TCP port 5001
TCP window size:  256 KByte (WARNING: requested 1.00 MByte)
------------------------------------------------------------
[  4] local 192.168.1.100 port 33125 connected with 192.168.1.102 port 5001
Waiting for server threads to complete. Interrupt again to force quit.

Running higher window size on the server also gave:
[502] > iperf -s -l 1M -w 1M
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size:  256 KByte (WARNING: requested 1.00 MByte)
------------------------------------------------------------

and so was not pursued further, 'iperf -c dom0-name -l 256k -w 256k -r' gave 
on dom0:
[505] > iperf -s
------------------------------------------------------------
Server listening on TCP port 5001
TCP window size: 85.3 KByte (default)
------------------------------------------------------------
[  4] local 192.168.1.100 port 5001 connected with 192.168.1.102 port 1037
[ ID] Interval       Transfer     Bandwidth
[  4]  0.0-10.1 sec  41.5 MBytes  34.6 Mbits/sec
------------------------------------------------------------
Client connecting to 192.168.1.102, TCP port 5001
TCP window size:  256 KByte (WARNING: requested  256 KByte)
------------------------------------------------------------
[  4] local 192.168.1.100 port 53348 connected with 192.168.1.102 port 5001
[ ID] Interval       Transfer     Bandwidth
[  4]  0.0-10.1 sec  38.8 MBytes  32.3 Mbits/sec

Isn't debugging fun :-)

>> Going down to vcpu=1, dom0 as server gives 27.1 Mb/s, and domu as
server
>> gives
>> 35.7 Mb/s, so there is not a lot of difference between 1 and 2 vcpus
for
>> me.

> With all features enabled?

Yes, I left all features enabled after getting them where a new install would 
put them.

>> Nice improvements. I will test disk i/o w/ iometer later.

> I'll be interested in the results, but the disk stuff hasn't changed in
a while.

I kind of thought so, since you haven't mentioned it, but I'll post the 
results later anyway.

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users

<Prev in Thread] Current Thread [Next in Thread>