Subject
Re:
Hipersocket Performance Problem on SLES 9
Please respond
/2006 02:28 PM
Please respond to
Linux on 390 Port LINUX-390@VM.MARIST.EDU
To
LINUX-390@VM.MARIST.EDU
cc
Subject
Re: Hipersocket Performance Problem on SLES 9
Novell can't even find the ticket # I gave you that we filed this under?
Tom Shilson [EMAIL PROTECTED
Re:
Hipersocket Performance Problem on SLES 9
Please respond to
Linux on 390 Port LINUX-390@VM.MARIST.EDU
I don't know what they are doing. I opened the incident on-line
yesterday. They came right back and request more info. I
under z/VM
5.2 on a z9-109), with enough storage defined so the file could be
completely cached. I then FTP'd it to /dev/null on another server over a
hipersocket connection. Here's what I observed:
SLES8-to-SLES8, MTU=8184, ~75 MB/sec
SLES8-to-SLES8, MTU=32760, ~100 MB/sec (as high as 132 MB/sec
Hipersocket Performance Problem on SLES 9
Please respond to
Linux on 390 Port LINUX-390@VM.MARIST.EDU
Greetings all,
I've been using real hipersockets for a couple years now. Recently a
significant
(distribution dependent,
unfortunately) to make the change permanent.
Mark Post
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] Behalf Of
David Boyes
Sent: Wednesday, April 26, 2006 9:58 AM
To: LINUX-390@VM.MARIST.EDU
Subject: Re: simple hipersocket communication
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] Behalf Of
Fuhrmann Anna
Sent: Wednesday, April 26, 2006 7:33 AM
To: LINUX-390@VM.MARIST.EDU
Subject: AW: simple hipersocket communication between LPARS, pls help
-snip-
But how can I find out - well, just what you say
Hi List,
I simply don't know how to figure it out.
Two partitions (z/os and RHEL4) involved. want to communicate.
One interface is OSA Express, working fine, VIPA- and
omproute-configured.
The other one should be hipersocket, no need for VIPA and for dynamic
routing, as far as I see
system that has VIPA and OSPF, or both z/OS and Linux?
The other one should be hipersocket, no need for VIPA and for dynamic
routing, as far as I see.
What I don't quite see at the moment: how do I *prevent* the z/os-
LPAR
from choosing the usual way
(of being routed): is it by defining a static
of it.
What I don't quite see at the moment: how do I *prevent* the z/os-
LPAR from choosing the usual way (of being routed): is it by
defining a static route for the hipersocket interface in the
Profile-dataset? BSDROUTINGPARMS or BEGINROUTES or whatever?
Defining a static route is one
-Ursprüngliche Nachricht-
Von: Linux on 390 Port [mailto:[EMAIL PROTECTED] Im
Auftrag von Vic Cross *EXTERN*
Gesendet: Mittwoch, 26. April 2006 13:15
An: LINUX-390@VM.MARIST.EDU
Betreff: Re: simple hipersocket communication between LPARS, pls help
G'day Anna,
On 26/04/2006, at 5:43 pm
on VM and the other
an OSA card for Java apps. running on WAS servers, etc. Each access
point has a unique IP address. i.e. the OSA has it's own
ip addr and the hipersocket (hsi0) has its own unique ip addr. We then
used which ever ip addr depending on how
we needed to access the UDB.
Hope
NEED
to have the z/OS people involved also.
Lee
David Boyes wrote:
As David Boyes said, it should be simple. And it is if all is setup
right...
In a nutshell:
- turn on IP forwarding in the router
- add a route on z/OS to the guest LAN subnet via the
router IP on the hipersocket
- add
What I don't quite see at the moment: how do I *prevent* the z/os-
LPAR
from choosing the usual way
(of being routed): is it by defining a static route for the
hipersocket
interface in the Profile-dataset? BSDROUTINGPARMS or BEGINROUTES or
whatever?
Yes. See the paper I posted last night
, and not the
VIPA-Address of
z/OS? So that every conversation
from-Linux-to-z/os and back explicitly uses the HSI-Address?
Unless you defined a specific VIPA for two hipersocket interfaces, then
yes.
Another tip: PLEASE set up DNS entries for the different interfaces and
make the applications refer
Yeah, I'm just not that good of an artist...8-)(*)
I left that part out to simplify the configuration somewhat, but the
important parts are the layer 3 routing issues. The VSWITCH is a layer 2
device, so whether the connection is inside or outside the zSeries box
isn't important to the routing
On 26/04/2006, at 9:51 pm, Fuhrmann Anna wrote:
(in reply to me saying)
file called route-hsi0
to be created also in /etc/sysconfig/network-scripts ?
Yes, sorry, I distracted myself checking the answer and forgot to
give it! :)
I also forgot to mention that if you do nothing else other
on the MVS side of the
hipersocket was setup wrong. So even when the VM/Linux side was working
right, MVS never answered because of the bad routing there.
(And I apologize to all for some cut-n-paste in the original notes that
muddied the water a bit.)
Thanks again to all...
Lee
--
Lee Stewart, Senior
Lee - would you mind giving the list a (simplified) diagram of both sides,
or copies of various settings in TCP/IP and/or z/OS (minus anything too
uncomfortable for your organization to reveal of course)? might be
instructive to others to see where things have to be set, where they have
to match,
As David Boyes said, it should be simple. And it is if all is setup
right...
In a nutshell:
- turn on IP forwarding in the router
- add a route on z/OS to the guest LAN subnet via the
router IP on the hipersocket
- add a route on the Linux guests to the hipersocket subnet
via
As David Boyes said, it should be simple. And it is if all is setup
right...
I'm hacking out a short whitepaper that is a generalized version of this
setup. I'll post it later this week.
-- db
--
For LINUX-390 subscribe /
As David Boyes said, it should be simple. And it is if all is setup
right...
In a nutshell:
- turn on IP forwarding in the router
- add a route on z/OS to the guest LAN subnet via the
router IP on the hipersocket
- add a route on the Linux guests to the hipersocket subnet
OK, I went back to the device drivers book only. (Same steps as the
SHARE presentation).. I do have a layer3 QDIO guest LAN..
For a router or the Hipersocket Network Concentrator thhe book says to
issue the following to the hipersocket device:
echo primary_connector /sys/bus/ccwgroup/drivers
Keep in mind: a hipersocket and a OSA are NOT the same beast -- they
both use QDIO to deliver frames to the media, but the similarity stops
there. Some things just don't work on hipersockets -- for example,
hipersockets don't have that silly PRI/SECROUTER thing, so they *should*
return an error
On Friday, 04/14/2006 at 12:11 CST, Lee Stewart
[EMAIL PROTECTED] wrote:
OK, I went back to the device drivers book only. (Same steps as the
SHARE presentation).. I do have a layer3 QDIO guest LAN..
For a router or the Hipersocket Network Concentrator thhe book says to
issue the following
According to page 102 of the book, you use primary_connector to tell the OSA
interface you're routing between it an a HiperSocket network. You use
multicast_router to tell the HiperSockets the same thing. In the section
you're working from, they're doing the opposite. They seem to have
On Tuesday, 04/11/2006 at 05:44 CST, Lee Stewart
[EMAIL PROTECTED] wrote:
Since z/OS is more difficult to get changes made on, we went with a
definintion that's already there... It has a hipersocket defined with
IP address 192.168.11.10 and a mask of 255.255.255.0.
We have the 192.168.11.0
Shouldn't you just be able to create a guest LAN/vswitch that uses a
hipersocket device group on VM as the interface and then present that to each
linux guest as device 9200 or somesuch? That way all the traffic on the
hipersocket is handled by VM, and all the linux guests can talk
On 4/12/06, James Melin [EMAIL PROTECTED] wrote:
Shouldn't you just be able to create a guest LAN/vswitch that uses a
hipersocket device group on VM as the interface and then present that to each
No, VSWITCH requires an OSA Express interface to go out, not
hipersockets. But I do agree
On Wednesday, 04/12/2006 at 09:10 EST, James Melin
[EMAIL PROTECTED] wrote:
Shouldn't you just be able to create a guest LAN/vswitch that uses a
hipersocket device group on VM as the interface and then present that to
each
linux guest as device 9200 or somesuch? That way all the traffic
Shouldn't you just be able to create a guest LAN/vswitch that uses a
hipersocket device group on VM as the interface and then present that
to
each
linux guest as device 9200 or somesuch? That way all the traffic on
the
hipersocket is handled by VM, and all the linux guests can talk
Hi all... Sorry if this is kind of long winded... Also forgive me,
I'm sometimes lost (pun intended) when it comes to IP routing...
I have a client with a fair number of Linux guests that we want to
connect each via hipersocket to a z/OS LPAR... For flexibility (and
other reasons), we don't
And from the router I can ping both z/OS and the Linux guest, so the
basic connection and routing seems to be there...
And following the instructions in the device drivers manual and in a
SHARE pitch, I turned on IP forwarding.
That should be sufficient. If you enable IP forwarding, you
seen this problem? Has it been fixed? I've been running my
hipersocket (and CTC) interfaces with MTU=32760. Should I start
reconfiguring them all back to 8K? (8184?)
Most of our servers are SLES8, just starting to roll out SLES9.
Mark Wheeler, 3M Company
We have a Hipersocket defined between two guests. It has stopped
working on one of the guests. I have deleted the configuration and
recreated it and ran mkinitrd. We have also rebooted the guest. Below
is the config file for the failing interface:
BOOTPROTO='static'
BROADCAST='10.14.1.255
What are the addresses of the hipersockets in the failing machine?
Being QDIO I believe that the hipersocket low order address needs to be
even. It should be a triplet of
even (read) even+1(write) available address(date transfer)
David
Kenneth Libutti wrote:
We have a Hipersocket defined
Also you describe hipersockets between two guests. Are these guests on
the same LPAR? Is the hipersocket being used by different LPARs?
David
Kenneth Libutti wrote:
We have a Hipersocket defined between two guests. It has stopped
working on one of the guests. I have deleted the configuration
The guests are on the same LPAR but we do have the Hipersocket connected
to a third vse machine in another LPAR and that connection is
functioning. The addresses for the failing hipersocket are F509 F50A
F50B.
Ken Libutti CNE, CNI, SCSA, RHCT
Asst. Director of Systems Services
Broward Community
Just out of curiosity, what is the MTU size?
Thanks,
tom
- - - - - - - - - - - -
Toto, I have a feeling we're not in the mainframe world any more.
_/) Tom Shilson
~Unix Team / IT Server Services
Aloha Tel: 651-733-7591 tshilson at mmm dot
ifconfig -a from non-working interface:
hsi0 Link encap:Ethernet HWaddr 00:00:00:00:00:00
inet addr:10.14.1.4 Bcast:10.14.1.255 Mask:255.255.255.0
inet6 addr: fe80::200:ff:fe00:0/64 Scope:Link
UP BROADCAST RUNNING NOARP MULTICAST MTU:57344 Metric:1
@VM.MARIST.EDU
Subject: z/OS tcp/ip stack definitions for hipersocket
The results of a netstat on z/os showed me that while the actMtu is 8192
while under BSD Routing Parameters it shows an MTU Size of 00576.
Question: Does this mean z/OS tcp/ip is breaking 8 K packets into 576
byte units each
the hipersocket definitions ?
I appreciate any suggestions.
Thanks,
Mark Vandale
--
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http
could ATTACH the 3 hipersocket devices to the
virtual machine while it is running (which happens automatically when
you logon the virtual machine because of the dedicate statements in
the directory). In that case you don't even have to reboot Linux to
see it pick up the new devices.
Rob
--
Rob van der
Hi, Rob
(B
(BThank you for your answer.
(BI'm successful to add the new NIC.
(B
(BThank you.
(B-
(BK.M.
(B
(B__
(BDo You Yahoo!?
(BUpgrade Your Life
(Bhttp://bb.yahoo.co.jp/
(B
Hi, all
(B
(BI want to add a new NIC for HiperSocket.
(BNow, my environment is below.
(B
(Bz890 has 2LAPRs.
(BLPAR-A has lpar linux SLES9(Linux-A).
(BLPAR-B has z/VM V5.1.
(Bz/VM has two Guest SLES9s. (Linux-B, Linux-C)
(B
(BI want to add a NIC for HiperSocket on Linux-B.
(BI tried
How did you add it to the directory? In this case you are using a real
hipersocket so you will need DEDICATE statements in your directory or ATTACH
commands from a class B need to be issued. While you can consider the virtual
addresses as NICs, they ar more like a set of devices
Hi, David
(B
(B1)
(BI added to USER DIRECT as below
(BDEDICATE 2000 2000
(BDEDICATE 2001 2001
(BDEDICATE 2002 2002
(B
(B2)
(BDevice Address 2000-200F is assigned to HiperSocket.
(BOf cause I added to definition for HiperSocket to IOCDS.
(B
(B3)
(BAnd SLES9 was rebooted.(to reload
PROTECTED]
IST.EDU Subject
Change IP address for Hipersocket
01/23/2005 12
On Sunday, 01/23/2005 at 11:39 PST, Ranga Nathan [EMAIL PROTECTED]
wrote:
I need to change the IP address for a hipersocket interface for z/VM
itself.
ifconfig hiperlec newip
does not work.
I tried it from MAINT and from TCPMAINT.
When I issue
ifconfig HIPERLEC down
ifconfig HIPERLEC
IP address for Hipersocket
You don't need to bounce TCPIP. Logon to TCPMAINT, create a temporary file
on TCPMAINT's A=disk with filetype TCPIP (for example, file CHGHOME TCPIP
A) enter ALL of the HOME statements from PROFILE.TCPIP (starting with the
HOME keyword) then issue the command
I need to change the IP address for a hipersocket interface for z/VM
itself.
ifconfig hiperlec newip
does not work.
I tried it from MAINT and from TCPMAINT.
When I issue
ifconfig HIPERLEC down
ifconfig HIPERLEC 192.168.1.250
ifconfig HIPERLEC up
all commands are accepted but the change
Hugo,
If you're talking to a _real_ HiperSocket, and not a virtual one, then z/VM
TCP/IP doesn't have anything to do with it. You should just be able to set
up your IP addresses and routes and it should all just work.
Mark Post
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL
, January 05, 2005 3:29 PM
To: LINUX-390@VM.MARIST.EDU
Subject: Hipersocket - qdio error messages
Hello list -
I'm trying to connect a Linux (z/VM guest) server with a z/OS LPAR via
HiprSockets and I'm getting the following error messages when I reboot
the Linux server. I can't ping from Linux to z/OS
Greetings,
I am getting an error when starting my hipersocket up.
SIOCSIFMTU: Invalid argument
Why am i getting this error, shouldn't it take '65535' as a valid mtu size?
I never had this problem on SLES 8, did something change?
I'm also noticeing that my mtu is being dropped to 57344
on 390 Port [EMAIL PROTECTED]
11/01/2004 08:56 AM
Please respond to
Linux on 390 Port
To
[EMAIL PROTECTED]
cc
Subject
Hipersocket MTU invalid argument SLES 9
Greetings,
I am getting an error when starting my hipersocket up.
SIOCSIFMTU: Invalid argument
Why am i getting this error
ok, now i understand thank you for the info.
-Cameron
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] Behalf Of
Dennis Musselwhite
Sent: Monday, November 01, 2004 08:55
To: [EMAIL PROTECTED]
Subject: Re: Hipersocket MTU invalid argument SLES 9
From Cameron Seader
On Monday, 11/01/2004 at 08:42 MST, Seader, Cameron
[EMAIL PROTECTED] wrote:
Why is that? i was able to do 64k on SLES 8
Actually, Cameron, you were not. HiperSockets are physically incapable of
handling an MTU larger than 56K. You may have *specified* 64K, but you
didn't *get* 64K.
Alan
yeah i think you are right.
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] Behalf Of
Alan Altmark
Sent: Monday, November 01, 2004 09:08
To: [EMAIL PROTECTED]
Subject: Re: Hipersocket MTU invalid argument SLES 9
On Monday, 11/01/2004 at 08:42 MST, Seader, Cameron
I have configured my Linux running on my IBM Z800 to use HiperSocket to my z/VM
machine. The VM machine apears to be configured correctly and the hardward
configuration apears to be configured correctly. When I boot my Linux system I get the
following messages on the console --
qeth: Trying
Does the divice show up in your chandev
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] Behalf Of
Mike Lovins
Sent: Tuesday, October 05, 2004 09:10
To: [EMAIL PROTECTED]
Subject: HiperSocket setup
I have configured my Linux running on my IBM Z800 to use HiperSocket
, October 05, 2004 11:10 AM
To: [EMAIL PROTECTED]
Subject: HiperSocket setup
I have configured my Linux running on my IBM Z800 to use HiperSocket to my
z/VM machine. The VM machine apears to be configured correctly and the
hardward configuration apears to be configured correctly. When I boot my
Linux
I presume you have defined the hipersocket interface to your Linux?
When you issue an ifconfig command do you get something like this back?
hsi1 Link encap:Ethernet HWaddr 00:00:00:00:00:00
inet addr:192.168.252.12 Mask:255.255.255.0
inet6 addr: fe80::200:ff:fe00:0/64
Alan Cox wrote:
The disk to disk aspect is distorting but he's using similar tests for
each case. In many case disk to disk is the right way to test anyway,
its what you actually do in the real world. ttcp can do similar testing
without the disk layer being involved if that matters.
The closer a
hipersocket
testing/benchmarking need help interpreting results.
Do a short transfer and tcpdump it. Look at the window size
offered by
the server in the syn frame, that is a good guide to the
buffering.
Got a window of 32767 from Linux to z/OS and 65535 from z/OS
to Linux using lukemftp
On Gwe, 2004-05-28 at 18:13, Lucius, Leland wrote:
Yepper, it does. I'm currently running with a 56KB MTU (on z/OS side) and have
tried lower. Never could get the FTP up very high. I even transferred files
between a TFS under z/OS and an ram disk under Linux. Thought it might be I/O
Specifically ftp ? The reason I ask is that the old BSD ftp client
always set 8K buffer limits and many vendors who reused the BSD
client code in other products never got around to fixing that.
Linux has it fixed, I'd have assumed z/Os did but you never know..
Hmmm, good point. Let me
On Gwe, 2004-05-28 at 20:43, Janek Jakubek wrote:
We had a TCPIP performance issue when we upgraded from
OS/390 2.7 to 2.10. The conclusion of that the problem is attached
below (from an IBM ETR record).
This could be another lead to follow
Except that the problem occurs with an 8K MTU
- Original Message -
From: Alan Cox [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, June 03, 2004 12:04 PM
Subject: Re: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
On Gwe, 2004-05-28 at 20:04, James Tison wrote:
FTP is a __TERRIBLE__
Hmmm, good point. Let me see if I can play with the buffer size under
z/OS.
Well, I can set the default TCP buffer size to different values for the z/OS
stack and we have it set to 65535, so I'd say it's on the largish size.
But, I don't know if the FTP server issues a setsockopt() to set a
On Iau, 2004-06-03 at 22:26, Lucius, Leland wrote:
Well, I can set the default TCP buffer size to different values for the z/OS
stack and we have it set to 65535, so I'd say it's on the largish size.
But, I don't know if the FTP server issues a setsockopt() to set a different
value or not.
Do a short transfer and tcpdump it. Look at the window size offered by
the server in the syn frame, that is a good guide to the buffering.
Got a window of 32767 from Linux to z/OS and 65535 from z/OS to Linux
using lukemftp. Must dash right now, but it appears that changing the
sndbuf size in
To preface this, this all started when our z/OS tcp/ip person tested z/OS
to z/OS hipersocket performance and found it nearly the same as using GBE
osa connection. I immediately went 'huh' and went on to get hipersockets
configured in the z/VM Linux guests.
I then ran some testing after doing so
125 Storing data set /it/public/Su810_001.iso
100% |*| 595 MB2.68
MB/s--:--
ETA
250 Transfer completed successfully.
624885855 bytes sent in 03:41 (2.68 MB/s)
Depressing isn't it? I've never been able to get much (or any) better than
what you
Just a thought.
Do you have to change the MTU size at all? I think it
defaults on linux to 1500.
Just a thought. Does the MTU size even play into the
hipersockets at all?
Yepper, it does. I'm currently running with a 56KB MTU (on z/OS side) and have tried
lower. Never could get the
On Friday, 05/28/2004 at 12:13 EST, Lucius, Leland
[EMAIL PROTECTED] wrote:
Yepper, it does. I'm currently running with a 56KB MTU (on z/OS side)
and have
tried lower. Never could get the FTP up very high. I even transferred
files
between a TFS under z/OS and an ram disk under Linux.
cc
[EMAIL PROTECTED]
IST.EDU Subject
Re: Did some extensive hipersocket
testing/benchmarking need help
05/28/2004 11:46
I wonder if for some reason the 192.x address is NOT being used during
FTP. Is there a confirmation that the transfer is actually going through
the hipersocket?
Alan Altmark [EMAIL PROTECTED]
Sent by: Linux on 390 Port [EMAIL PROTECTED]
05/28/2004 10:41 AM
Please respond to Linux on 390 Port
hipersocket
testing/benchmarking need help
05/28/2004 12:56 interpreting results.
PM
Please respond to
Linux on 390 Port
[EMAIL PROTECTED]
IST.EDU
I wonder
Ummm...you have to have the same MTU on both sides. Make
sure you have
MFS (OS= in IOCDS) at 64K.
Oops, I did mislead with that didn't I? Sorry, 'bout that.
Here's the interface:
hsi0 Link encap:Ethernet HWaddr 00:00:00:00:00:00
inet addr:10.2.32.30 Mask:255.255.255.0
Of
Lucius, Leland
Sent: Friday, May 28, 2004 12:41 PM
To: [EMAIL PROTECTED]
Subject: Re: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
-snip-
Depressing isn't it? I've never been able to get much (or any) better than
what you have. I don't know why either
PM
To: [EMAIL PROTECTED]
Subject: Re: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
Well to check THAT particular item (on the z/linux to z/linux transfers
anyway) I ipl'ed both guests to set the hsi1 tx/rx numbers back to 0, and
then ran the test. When I
]
Subject: Re: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
So, what you're saying is that the problem isn't with Linux, or
HiperSockets, or TCP/IP (as such) on z/OS, it is the z/OS implementation of
FTP. Perhaps we just need a different/better tool to test
Maybe someone could try with NFS instead of FTP
Is anyone running NFS over HiperSockets to z/OS???
I tried that as well. Unfortunately, I can't remember (and didn't write
it down) the throughput. Let me see if I can get some #s real quick.
Leland
: Re: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
FYI the MTU size being used was 8192
--
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED
Maybe someone could try with NFS instead of FTP
Is anyone running NFS over HiperSockets to z/OS???
I tried that as well. Unfortunately, I can't remember (and
didn't write
it down) the throughput. Let me see if I can get some #s real quick.
Okay, I NFS mounted an HFS directory
The reason I say that is because the message I got from the FTP connect.
Specifically: FTPD1 IBM FTP CS V1R4 at OWL0.CO.HENNEPIN.MN.US, 13:46:49 on
2004-05-28
I don't know if the FTP daemon is programmed to spit out the machine name,
but the hipersocket address does NOT resolve to a DNS entry
[EMAIL PROTECTED]
05/28/2004 12:40
Please respond to
Linux on 390 Port
To
[EMAIL PROTECTED]
cc
Subject
Re: Did some extensive hipersocket testing/benchmarking need help
interpreting results.
125 Storing data set /it/public/Su810_001.iso
100
: Did some extensive hipersocket testing/benchmarking need
help interpreting results.
The 8192 MTU was used on ALL tests in my original post. So I cant see how it
is the deciding issue.
Post, Mark K
[EMAIL PROTECTED]
m
a time of close to zero other activity with the
hipersocket subnets and the GBe subnets. Unfortunately, most of the results are gone,
but I was not very impressed with either GBe or hipersockets.
I tried many tests with different hipersocket chpids and found that the best
hipersocket ftp
Consider that a single TCP/IP instance can have many IP addresses.
Mark Post
-Original Message-
From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of James
Melin
Sent: Friday, May 28, 2004 2:49 PM
To: [EMAIL PROTECTED]
Subject: Re: Did some extensive hipersocket testing
3.82KB/s??? Is that supposed to be MB/s
Uh, can we all say...oops! ;-) Yes, that was supposed to be MB/s.
Leland
CONFIDENTIALITY NOTICE: This e-mail communication and any attachments may
contain proprietary and privileged information for the use of the designated
recipients named
)
for the hipersocket interface too.
--
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390
Subject
Re: Did some extensive hipersocket
testing/benchmarking need help
05/28/2004 02:07 interpreting results.
PM
Please
On Friday, 05/28/2004 at 03:19 EST, Lucius, Leland
[EMAIL PROTECTED] wrote:
I can live with that. What is the theoritical maximum for a
hipersocket?
It's a function of microcode. The faster the processor, the faster it
runs. Theoretically, of course.
Alan Altmark
Sr. Software Engineer
IBM z
What is the theoritical maximum for a hipersocket?
To be honest (and embarassed), I have no clue. Maybe someone else
does. Alan?
--Jim--
James S. Tison
Senior Software Engineer
TPF Laboratory / Architecture
IBM Corporation
If dogs don't go to heaven, then, when I die, I want to go where they
do
Alan,
It's a function of microcode. The faster the processor, the faster it
runs. Theoretically, of course.
That sounds a lot like an 'It depends' answer.
Hummm ... Maybe Bill is rubbing off on you ...
;
Regards,
Jeff
--
Jeffrey C Barnard
Barnard Software, Inc. http://www.bsiopti.com
Phone
SLES8A -- ZOS1 = ~56KB/sec!!
If anyone is interested, I was able to increase this to around 55MB/sec by
changing SLES8A's MTU to 20480. Anything higher and it drops back down to
K/sec. I haven't had a chance to change the ZOS side yet.
Leland
CONFIDENTIALITY NOTICE:
On Sun, 2003-10-19 at 20:18, Lucius, Leland wrote:
SLES8A -- ZOS1 = ~56KB/sec!!
If anyone is interested, I was able to increase this to around 55MB/sec by
changing SLES8A's MTU to 20480. Anything higher and it drops back down to
K/sec. I haven't had a chance to
On Sunday, 10/19/2003 at 10:01 EST, Adam Thornton
[EMAIL PROTECTED] wrote:
How much does a large MTU actually help, even when everyone supports it?
I usually leave mine at either 1492 or 1500, regardless of the allowable
interface maximum, because there's often something in the path that
On Sun, 19 Oct 2003, Adam Thornton wrote:
How much does a large MTU actually help, even when everyone supports it?
I think it has more to do with reducing processing overhead in your host
systems than wringing the last bit out of your network. Increasing the
MTU from 1500 to 2 (say) will
101 - 200 of 236 matches
Mail list logo