Menu
▾
▴
infiniband-general — InfiniBand General Interest List
You can subscribe to this list here.
| 2002 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
(17) |
Jul
(23) |
Aug
(4) |
Sep
(1) |
Oct
|
Nov
(4) |
Dec
(4) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2003 |
Jan
(2) |
Feb
(7) |
Mar
(7) |
Apr
|
May
(14) |
Jun
(11) |
Jul
(20) |
Aug
(7) |
Sep
(1) |
Oct
|
Nov
|
Dec
(3) |
| 2004 |
Jan
(19) |
Feb
(97) |
Mar
(4) |
Apr
(5) |
May
(4) |
Jun
|
Jul
(2) |
Aug
(2) |
Sep
(1) |
Oct
|
Nov
(3) |
Dec
|
| 2005 |
Jan
|
Feb
|
Mar
|
Apr
(1) |
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2006 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(1) |
Nov
|
Dec
|
| 2011 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(6) |
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(2) |
Nov
(2) |
Dec
|
| 2012 |
Jan
|
Feb
(1) |
Mar
(1) |
Apr
|
May
|
Jun
(1) |
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2013 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
(1) |
Sep
|
Oct
|
Nov
|
Dec
|
| 2014 |
Jan
|
Feb
|
Mar
(1) |
Apr
(1) |
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2017 |
Jan
|
Feb
|
Mar
(1) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: Miljen M. <mil...@mi...> - 2017-03-31 10:56:07
|
Hello, I went through the source code of mckey utility (available e.g. here: https://github.com/ofiwg/librdmacm/blob/master/examples/mckey.c ). There is an interesting comment at the line 524: /* * Pause to give SM chance to configure switches. We don't want to * handle reliability issue in this simple test program. */ sleep(3); If we remove sleep function call, mckey does not work properly anymore (receiver side does not get all messages that were sent). Does anyone know how long does it take for SM to "configure switches", and what is the proper way to "handle reliability issue"? Many thanks in advance. Best regards, Miljen Mikic |
Hi, A friend or colleague of yours, Winning the lottery is not a Rocket Science It is just a method to follow and implement and you could believe your eyes if you check this system out http://lottoblackbook.si6.us Click Here, whose email address is gre...@gm... thought you would like to visit http://ymcala.giftplans.org/. http://ymcala.giftplans.org/ |
Dear Make your own power generator that can power up your house for FREE http://teslasecretgenerator.com-book.me Please Click The Link Here, Check out ArtistSites.org. It is a new website and online community for visual artists and photographers. You can set up your own ArtistSites page for free, upload images of your work, post personal blogs, and network with other artists. To sign up, go to: http://www.artistsites.org/ Best regards, Make your own power generator that can power up your house for FREE http://teslasecretgenerator.com-book.me Please Click The Link Here |
|
From: Hefty, S. <sea...@in...> - 2011-05-25 16:25:23
|
> Thanks a lot. Librdmacm seems work on Linux, is there any other similar > packages > could work on Windows? Windows lacks the infrastructure to support user space multicast. The librdmacm is available on windows, but multicast does not work. (I'm subscribed to both the windows and Linux mail lists. I originally missed that this post was to the windows mail list.) - Sean |
|
From: yu.jiang <yu....@ju...> - 2011-05-25 07:17:17
|
Thanks a lot. Librdmacm seems work on Linux, is there any other similar packages could work on Windows? ------------------ yu.jiang |
|
From: Hefty, S. <sea...@in...> - 2011-05-25 05:43:15
|
> I write a program with socket interface to implement multicast, > it could work in IPoIB mode, but how to implement multicast in RDMA > mode? Thanks. You can take a look at the librdmacm example mckey. If you use the synchronous versions of the calls, it should be a little easier than that examples shows. Without using the librdmacm interfaces, it becomes quite a bit more difficult. - Sean |
|
From: yu.jiang <yu....@ju...> - 2011-05-25 04:35:59
|
Hi, I write a program with socket interface to implement multicast, it could work in IPoIB mode, but how to implement multicast in RDMA mode? Thanks. -------------- yu.jiang 2011-05-25 |
|
From: Sean H. <sea...@in...> - 2004-11-09 19:34:33
|
>Is this list a good place to keep track of the Linux InfiniBand efforts? The best place to track Infiniband development on Linux is www.openib.org. All major Infiniband developers are part of that project, with active work going into providing an Infiniband software stack for the Linux kernel. >How alive is this project? I noticed not much traffic in the last month >or two. This project has minimal ongoing maintenance to fix critical bugs and is in use, but will eventually be replaced by the openib stack mentioned above. >How alive is even InfiniBand itself? Google'ing reveals lots trade >brochures and such, but that's hard to get a feel. One of the other >guys in the office looking at this had gotten the indication that >InfiniBand had lost some steam in the last year. Infiniband itself is alive, and doing okay. The market for Infiniband products is limited to the HPC market, so is not as widespread as hoped a couple of years ago (e.g. as a replacement for PCI). I don't think that there's a compelling alternative for high bandwidth, low-latency applications. Again, you may get a better feel after joining the mail lists on openib. >One thing I don't get a feel for, is what services InfiniBand offers to >me the software developer. Obviously there'll be a TCP/IP thing on top >of it. Are there other APIs I can use? We make heavy use of ieee1394's >isochronous streams for our real time data stuff, does InfiniBand >provide anything like this? Infiniband will provide its own interfaces, plus there will be ports of MPI and DAPL. (Note that these are just my opinions.) |
|
From: Roland D. <ro...@to...> - 2004-11-09 19:32:19
|
Travis> Is this list a good place to keep track of the Linux
Travis> InfiniBand efforts?
No, the sourceforge lists are obsolete now. Development has moved to
the OpenIB project (www.openib.org) and in particular the
openib-general mailing list.
Travis> How alive is this project? I noticed not much traffic in
Travis> the last month or two.
The sourceforge project is not very active, but OpenIB is extremely
active right now.
Travis> How alive is even InfiniBand itself? Google'ing reveals
Travis> lots trade brochures and such, but that's hard to get a
Travis> feel. One of the other guys in the office looking at this
Travis> had gotten the indication that InfiniBand had lost some
Travis> steam in the last year.
IB has had its ups and downs but actually if anything it has gained
momentum in the past year. The number of IB press releases coming out
of SuperComputing '04 this week is pretty large.
Travis> One thing I don't get a feel for, is what services
Travis> InfiniBand offers to me the software developer. Obviously
Travis> there'll be a TCP/IP thing on top of it. Are there other
Travis> APIs I can use? We make heavy use of ieee1394's
Travis> isochronous streams for our real time data stuff, does
Travis> InfiniBand provide anything like this?
IB does not have an isochronous mode, but it does have a rich set of
transport services.
- Roland
|
|
From: Travis G. <tg...@ke...> - 2004-11-09 19:25:58
|
I am trying to learn more about InfiniBand. Especially as it pertains to Linux. I see InfiniBand often mentioned w.r.t. clusters. My company does NOT build clusters per se, but we do produce food processing machines with between 7 and 11 processors running Linux or uClinux. Currently we link them together via both ethernet and ieee1394. I'm always trying to keep my eyes open for new ways of linking these processors efficiently together. Is this list a good place to keep track of the Linux InfiniBand efforts? How alive is this project? I noticed not much traffic in the last month or two. How alive is even InfiniBand itself? Google'ing reveals lots trade brochures and such, but that's hard to get a feel. One of the other guys in the office looking at this had gotten the indication that InfiniBand had lost some steam in the last year. One thing I don't get a feel for, is what services InfiniBand offers to me the software developer. Obviously there'll be a TCP/IP thing on top of it. Are there other APIs I can use? We make heavy use of ieee1394's isochronous streams for our real time data stuff, does InfiniBand provide anything like this? TIA -- Travis Griggs Objologist "It had better be a pretty good meeting, to be better than no meeting at all" -- Boyd K Packer ----------------------------------------- DISCLAIMER: This email is bound by the terms and conditions described at http://www.key.net/disclaimer.htm |
|
From: Woodruff, R. J <rob...@in...> - 2004-09-24 21:07:19
|
A new Beta release tar ball of the IBAL InfiniBand stack has been posted to sourceforge InfiniBand project. This release is based on Bitkeeper change set 284, plus one additional complib bug fix that will be=20 pushed to bitkeeper soon.=20 http://sourceforge.net/projects/infiniband The code has a couple of more kernel panic bug fixes and a new feature to prevent applications from pinning down too much memory and causing the kernel to hang as a result. See the Release Notes.txt in the tar ball for details. |
|
From: Woodruff, R. J <rob...@in...> - 2004-08-24 18:39:08
|
A new release of the IBAL code has been posted for download to the sourceforge site.=20 http://sourceforge.net/projects/infiniband This release is based upon bitkeeper change set 275, but has a few changes that have not yet been merged and pushed to bitkeeper, which should happen in a day or two. This release is primarily a bug fix release but also adds support for=20 EMT64 (X86_64).=20 |
|
From: flor P. <the...@in...> - 2004-08-06 01:47:38
|
My name is Flor, Greetings from the other side of the World! I have to be Honest with you. This is a business proposal that you might get interested. Believe me, this is Totally Different from what you have heard or tried already! This is phenominal and revolutionary. If Bill Gates once dream of proving a PC in everyhome, this one, is providing Tech Support in every PC. This is a giant company in the making! The system is unique and fair. Everybody is benefited from everybody's effort. This is awesome! The company pays out generously. And most of all, the timing is right. Believe me, you will not be waisting your time asking what it is. Hurry! If you would like to know what it is for free, please send an email to mir...@wo... with, "Let Me Know" as the subject line. Kindly include your full name in the body of the letter and country Time is of the essence, don't wait for another second! Respectfully Yours, Flor P. ------- P.S. Please reply Remove if you want no more inputs from me |
|
From: Grant G. <io...@hp...> - 2004-07-28 22:00:39
|
On Wed, Jul 28, 2004 at 09:42:45AM -0700, Woodruff, Robert J wrote: > > People at the OLS InfiniBand BOF were asking if I could provide the > slides that were presented. I posted them on the sourceforge website, > since I manage that one. > http://sourceforge.net/projects/infiniband Robert, thanks for getting the BOF scheduled. Two issues came up that I care about but can't fix: 1) SDP and Microsoft IP. Can we get a clear statement what this is about and/or an ETA of when it will be resolved. 2) Change the charter so anyone can be given write access who is trusted by some subset of openib.org maintainers. I still think I can send some HW in 2004Q4 and more in 2005Q1 to OSDL to be hosted for external users. The OSDL charter won't allow this because of existing openib.org rules about who can get write access. > Also many thanks to Troy Benjegerdes for presenting his InfiniBand > performance data > http://www.scl.ameslab.gov/Publications/pubs_troy.html Yes - thanks Troy. grant |
|
From: Woodruff, R. J <rob...@in...> - 2004-07-28 16:43:13
|
People at the OLS InfiniBand BOF were asking if I could provide the slides that were presented. I posted them on the sourceforge website, since I manage that one.=20 http://sourceforge.net/projects/infiniband Hopefully, they accurately reflect the status of InfiniBand open source direction. Also many thanks to Troy Benjegerdes for presenting his InfiniBand performance data http://www.scl.ameslab.gov/Publications/pubs_troy.html Next year, it would be good to get more representation from other people in openib.org at OLS,=20 as people were asking why people from Topspin, InfiniCon, Voltaire, and Mellanox did not attend. One comment I got was that the "InfiniBand people=20 are ignoring us". i.e., the Linux Community.=20 The good news is that most of the people I spoke with were supportive of the phased approach being taken by openib.org, i.e, first get a lean driver, access layer, and IPoIB running and submitted to the kernel tree, then add ULPs and=20 enhancements over time, so it seems like we are on the right track.=20 woody |
|
From: Greg KH <gr...@kr...> - 2004-05-12 19:07:50
|
On Wed, May 12, 2004 at 11:37:53AM -0700, Woodruff, Robert J wrote: > > > As the project gets wider, use the same rules lkml uses for sending > patches. > > Does BK or SVN provide automatic generation of patches that are > acceptable to lkml ? Heh, you mean in plain text diff form? Yes they both do. greg k-h |
|
From: Woodruff, R. J <wo...@co...> - 2004-05-12 19:02:54
|
> As the project gets wider, use the same rules lkml uses for sending patches. Does BK or SVN provide automatic generation of patches that are acceptable to lkml ? |
|
From: Raj, A. <ash...@in...> - 2004-05-12 18:20:41
|
Not knowing what SVN is, BK is light years away in terms of usability compared to other SCM tools that I have used in the past. BK can happily accept patches from normal gnu style, and just ensure people send patches against the latest tree in bk, or atleast specify the top changeset that they pulled. This way its easy to recreate a tree and do a merge. As the project gets wider, use the same rules lkml uses for sending patches. - separate each distinct fix in a patch - never mix 2 fixes (unless related) in a single patch I use Andrew Morton's patch management scripts (if you are not using bk) to keep track of multiple patches and their order.=20 http://www.zip.com.au/~akpm/linux/patches/patch-scripts-0.16/patch-scrip ts-0.16.tar.gz These are very easy to maintain, and keep related patches separate.=20 Cheers, ashok raj - Linux Core Software Group =20 >-----Original Message----- >From: inf...@li... [mailto:infiniband-general- >ad...@li...] On Behalf Of Woodruff, Robert J >Sent: Wednesday, May 12, 2004 11:07 AM >To: ope...@op... >Cc: inf...@li... >Subject: [Infiniband-general] RE: [openib-general] SVN vs. Bitkeeper (was: MT_bufpool_destroy?) > >>I personally would like to see IBAL stay in BK, since that's what I've >been using. >>However, I suspect that you will eventually need to move to SVN or >support both - people >>will start to create patches against the SVN version, and you would >have to propagate >>these patches back to the BK repository. I don't know how hard it is >to move data between >>BK and SVN. > >>I don't have the bandwidth to switch to SVN at this point, and BK is >working wonderfully >> for me. > >> - Fab > >I was thinking for now we could leave the working data base in BK and >put snapshots into openib.org, at least for now. I'd hate to make >all the people that are sending in patches for IBAL have to switch >right now. >I guess we will just have to manually merge the SVN patches back into >BK. If the the volume of SVN patches gets greater than the BK patches, >we can revisit this. > > >------------------------------------------------------- >This SF.Net email is sponsored by Sleepycat Software >Learn developer strategies Cisco, Motorola, Ericsson & Lucent use to deliver >higher performing products faster, at low TCO. >http://www.sleepycat.com/telcomwpreg.php?From=3Ddnemail3 >_______________________________________________ >Infiniband-general mailing list >Inf...@li... >https://lists.sourceforge.net/lists/listinfo/infiniband-general |
|
From: Woodruff, R. J <wo...@co...> - 2004-05-12 18:07:09
|
>I personally would like to see IBAL stay in BK, since that's what I've been using. =20 >However, I suspect that you will eventually need to move to SVN or support both - people=20 >will start to create patches against the SVN version, and you would have to propagate=20 >these patches back to the BK repository. I don't know how hard it is to move data between=20 >BK and SVN. >I don't have the bandwidth to switch to SVN at this point, and BK is working wonderfully=20 > for me. > - Fab I was thinking for now we could leave the working data base in BK and=20 put snapshots into openib.org, at least for now. I'd hate to make all the people that are sending in patches for IBAL have to switch right now.=20 I guess we will just have to manually merge the SVN patches back into BK. If the the volume of SVN patches gets greater than the BK patches, we can revisit this.=20 |
|
From: moral m. <mor...@ho...> - 2004-04-27 03:05:20
|
Hello
According to the installation:
---------------------------------------------------------------------------------------
Source Forge Notes
1) Log onto Source Force site
a. http://infiniband.sourceforge.net
2) Download "Bitkeeper" software
a. Click on Bitkeeper Repository link (under Source Forge
Services)
b. Click on download link
c. Click on Download Bitkeeper
d. Determine proper platform and complete download
e. Note: You must fill in form and provide email address.
SW will email you login info to "bitmover site"
f. http://www.bitmover.com/download
* login: bitkeeper
* password: get bitkeeper
3) After you have downloaded bitkeeper software, change the mode of
the
file to make it executable (i.e. chmod a+x *.bin)
a. chmod a+x 3.0.1-x86-glibc22-linux.bin
b. ./ 3.0.1-x86-glibc22-linux.bin
4) The above process creates an executable called "bk". It also
creates
a symbolic link from bk to /usr/bin/bk
5) Create a directory where you would like to place the SF project
a. Ex. mkdir /usr/sf-iba
6) Use the bk program to pick up a clone of the latest Source Force
release
for iba
a. cd /usr/sf-iba
b. bk clone http://project.bkbits.net/repository
where: project = infiniband, repository = iba; producing:
c. bk clone http:/infiniband.bkbits.net/iba
7) Running "bk" will create a sub_folder in your current working
directory
a. => /usr/sf-iba/iba
8) Add Mellanox source to newly downloaded source tree
a. cd /usr/sf-iba/iba
b. Download and copy mellanox_xxx.tgz file to this directory and
unzip/untar file. Note: archive will place into base and
create
linux folders. It is very important that you place the
mellanox
files into the correct directory structure
c. tar xzvf mellanox_xxx.tgz. This will create the following:
* /usr/sf-iba/iba/base/linux/hca/mellanox
* /usr/sf-iba/iba/linux/run
9) Create a build tree for the project using the "mktree" command.
This will pull out all sources from the base directory to a
directory
of your choosing
a. cd /usr/sf-iba/iba/base/linux/utils
b. ./mktree -source /usr/sf-iba/iba -target /usr/sf-iba/iba
* mktree create 2 new directories linux and linuxuser in
/usr/sf-iba/iba
10) Rebuild the kernel and boot with new kernel (example using
linux-2.4.18-10 kernel tree)
a. cd /usr/src/linux-2.4.18-10
b. make xconfig
* make any changes to fit your hardware configuration:
o SMP/UP option (YES for Process type and
features/Symmetric
multi-processing support buttons)
o network driver (YES for Network device
support/Ethernet
(10 or 100Mbit)/Ethernet (10 or 100Mbit)... buttons
o scsi driver (YES for SCSI support/ SCSI low-level
drivers/...
buttons)
o local file system (YES for File systems/Ext3
journaling
file system support - Second extended fs support
buttons)
* hit "save and exit" button
c. Patch the kernel to support IPoIB with larger MAX_ADDR_LEN
* edit /usr/src/linux-2.4.18-10/include/linux/netdevice.h to
change MAX_ADDR_LEN = 8 to = 32
* edit /usr/src/linux-2.4.18-10/net/core/dev.c to change:
The SIOCGIFHWADDR case from:
memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
MAX_ADDR_LEN);
to
memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
min((unsigned char)
sizeof(ifr->ifr_hwaddr.sa_data),
dev->addr_len));
The SIOCSIFHWBROADCAST case from:
memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
MAX_ADDR_LEN);
to
memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
min((unsigned char)
sizeof(ifr->ifr_hwaddr.sa_data),
dev->addr_len));
d. make dep
e. make bzImage
f. make install
g. verify /etc/lilo.conf (or /etc/grub.conf) to reboot the
system
with new kernel
11) Install Mellanox MST and MSDK
a. install mst driver
b. install MSDK
c. verify the installation (at least run vapi start)
12) The next step is to build all the driver for the stack
(including
Mellanox module)
a. cd /usr/sf-iba/iba/linux
b. edit Makeconf.inc
* edit LINUX_VERSION = 2.4.18-10
* edit REDHAT=1 if you run original kernel from RH
installation.
In our case, we are running costumed kernel, we leave it
as default
* edit LINUX_SRC. In our case, we edit LINUX_VERSION;
therefore,
we leave this as default
c. edit Makefile.config
* Change BUILD_SMP line to: BUILD_SMP =0 (if kernel is
UP)
* Change BUILD_SMP line to: BUILD_SMP =1 (if kernel is
SMP)
d. Edit Makefile; Change "MLNX=n" to "MLNX=y, MODEL,SHIM=y
to
MODEL,SHIM=n)
13) Build/Compile kernel driver components by running make from top
level
directory
a. cd /usr/sf-iba/iba/linux
b. make debug (or free)
c. All the object files are in
* ~bin/$(ARCH)/$(LINUX_VERSION)/$(MP_MODE)/$BLD
* in our case ARCH=x86, LINUX_VERSION=2.4.18-10, MP_MODE=up,
BLD=debug
14) Build/Compile user mode driver components.
a. cd /usr/sf-iba/iba/linuxuser/iba
b. make debug (or free)
c. All the executable files (opensm, alts...) are in
/usr/sf-iba/iba/linuxuser/bin/$(ARCH)/$(LINUX_VERSION)/bin/$(BLD)
d. All the libraries are in
/usr/sf-iba/iba/linuxuser/bin/$(ARCH)/$(LINUX_VERSION)/lib/$(BLD)
e. In our case ARCH=x86, LINUX_VERSION=2.4.18-10, BLD=debug
f. create the symbolic link for liballib, libcomplib and
libmlnx_uvp
* cd /usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/lib/debug
* ln -s liballib.so.0.0 liballib.so
* ln -s libcomplib.so.0.0 libcomplib.so
15) Run the stack with "ibal" script which is the equivalent to
"vapi" script
a. cd /usr/sf-iba/iba/linux/run
b. edit ibal
* edit line 35,36.
* Assuming that we are running UP kernel and debug mode then
o line 35 should be
MODPATH_I=$IBAL_PATH/bin/x86/$KERVER/up/debug
o line 36 should be
MODPATH_TV=$IBAL_PATH/drivers/iba/hca/mellanox/thh/obj_linux_x86_up
* Assuming that we are running SMP kernel and free mode then
o line 35 should be
MODPATH_I=$IBAL_PATH/bin/x86/$KERVER/smp/free
o line 36 should be
MODPATH_TV=$IBAL_PATH/drivers/iba/hca/mellanox/thh/obj_linux_x86_smp
c. cd /usr/sf-iba/iba/linux and issue command "run/ibal start"
16) Set up the linking library path. There are two ways.
a. Edit the /root/.bashrc and add in the following line
* export LD_LIBRARY_PATH=
/usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/lib/debug
b. Or
* edit /etc/ld.so.conf and add in the following line
/usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/lib/debug
* run ldconfig
17) Run the OPENSM
a. opensm executable file locates at
/usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/bin/debug or
/usr/sf-iba/iba/linuxuser/iba/opensm directories
b. cd /usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/bin/debug
c. ./opensm
d. Whew... finally
e. leave the opensm running still (sweeping mode)
18) Run IPoIB
a. cd /usr/sf-iba/iba/linux/bin/x86/2.4.18-10/up/debug
b. insmod ipoib.o
c. ifconfig -a ( you will see ib01 and ib02 pop up)
d. ifconfig ib01 11.0.0.1
e. ping 11.0.0.1
19) Run uDAPL
a. edit /etc/hosts to add in IPaddress for all DAPL nodes in
cluster.
Distribute the file for every node in the cluster. IPaddress
can be the same as IPoIB IP address as long as node name has
to end
with "xx-ibX". Even though you are not running IPoIB, you
have to add
in Interface Adapter Address (IP address) for DAPL IA. For
now,
one IP address for each DAPL IA (for each HCA)
Example: local node is mtilab10
10.2.2.10 mtilab10 ==> this is ethernet 0
10.2.2.11 mtilab11
192.0.0.10 mtilab10-ib0 ==> this is IPoIB or Interface
Adapter
address for local DAPL IA
1
192.0.0.14 mtilab10-ib0a ==> this is IPoIB or Interface
Adapter
address for local DAPL IA
1 port 1
192.0.0.12 mtilab10-ib1 ==> this is IPoIB or Interface
Adapter
address for local DAPL IA
2
192.0.0.11 mtilab11-ib0 ==> this is IPoIB or Interface
Adapter
address for remote DAPL IA
b. Copy mv_dapl/doc/dat.conf to /etc/dat.conf. Please read
mv_dapl/doc/dapl_registry_design.txt for more infomation how
to
edit /etc/dat.conf correctly
NOTES: If you compile dapltest with EXPLICIT_LINK=1 then
dapltest
is explicitly linked to libdapl.so library; therefore,
you
have to uncomment the entry in dat.conf or do not have
dat.conf in /etc.
c. dapltest executable file locates at
/usr/sf-iba/iba/linuxuser/bin/x86/2.4.18-10/up(smp)/debug(free) or
/usr/sf-iba/iba/linuxuser/iba/mv_dapl/test/udapl/dapltest
c. Run dapltest testsuite for 2 nodes (mtilab10-ib0 and
mtilab11-ib0)
* At both nodes
o start the driver (ibal start)
o cd
/usr/sf-iba/iba/linuxuser/iba/mv_dapl/test/udapl/dapltest
* At mtilab10-ib0
o ./srv.sh ==> start server
* At mtilab11-ib0
o ./bw.sh mtilab10-ib0 ==> run bw test
o ./lat_poll.sh mtilab10-ib0 ==> run latency polling
mode test
o ./lat_block.sh mtilab10-ib0 ==> run latency blocking
mode test
o ./cl.sh mtilab10-ib0 ==> run transaction tests
o ./regress.sh mtilab10-ib0 ==> run transaction
regression test
o ./quit.sh mtilab10-ib0 ==> instruct the server to
quit
* both can run limit test ./lim.sh (don't need to run server)
d. Please reference to dapltest.txt for more test options
-----------------------------------------------------------------------------------------
I have finished step 18),but I meet the problem in step 19).I think the
opensm is well in
step 18).
Thank you
WangJue
_________________________________________________________________
与联机的朋友进行交流，请使用 MSN Messenger: http://messenger.msn.com/cn
|
|
From: Woodruff, R. J <wo...@co...> - 2004-04-26 16:37:01
|
Looks like you are unable to query the SM. Is OpenSM
up and running ?
SA query callback failed status IB_REMOTE_ERROR
> > > --> DsINMG: query SA found no record
-----Original Message-----
From: inf...@li... =
[mailto:inf...@li...] On Behalf Of =
moral moral
Sent: Friday, April 23, 2004 12:32 AM
To: inf...@li...
Subject: [Infiniband-general] udapl:al:query_req_cb() !ERROR!: query =
failed:
I am a chinese student.there are two question:
1)I can run ibal and opensm,it shows"subnet up".i can ping port1 =
from=20
por1 on the same computer.when i ping other port in the subnet,the =
computer=20
died.
2)i run a server which is waiting on scorce1.ustb.cn,after i start =
ibal=20
and opensm.when i run a client on score2.ustb.cn,it has these error:
> > >
> > > root@score2 dapltest]# ./bw.sh
> > > Usage: bw.sh [hostname [size [device]]]
> > > [root@score2 dapltest]# ./bw.sh score1.ustb.cn-ib0
> > > UAL: _init: Entered UAL Shell Initialization
> > > cl_open_device: opening device /dev/al
> > > uvp_get_interface() [
> > > mlnx_get_pd_interface() [
> > > mlnx_get_pd_interface() ]
> > > mlnx_get_qp_interface() [
> > > mlnx_get_qp_interface() ]
> > > mlnx_get_cq_interface() [
> > > mlnx_get_cq_interface() ]
> > > mlnx_get_eec_interface() [
> > > mlnx_get_eec_interface() ]
> > > mlnx_get_mrw_interface() [
> > > mlnx_get_mrw_interface() ]
> > > mlnx_get_mcast_interface() [
> > > mlnx_get_mcast_interface() ]
> > > mlnx_get_errh_interface() [
> > > mlnx_get_errh_interface() ]
> > > uvp_get_interface() ]
> > > mlnx_pre_open_ca() [
> > > mlnx_pre_open_ca() ]
> > > mlnx_post_open_ca() [
> > > cl_open_device: opening device /dev/mlx8cd30a0
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 1
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 1
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_post_open_ca(): comm 27904 buf_size 48
> > > mlnx_post_open_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > UAL: _init: Initialization completed successfully
> > > -------------------------------------
> > > PerfCmd.server_name : score1.ustb.cn-ib0
> > > PerfCmd.dapl_name : IbalHca0
> > > PerfCmd.mode : POLLING
> > > PerfCmd.num_iterations : 1024
> > > PerfCmd.pipeline_len : 16
> > > PerfCmd.op.transfer_type : RDMA_WRITE
> > > PerfCmd.op.num_segs : 1
> > > PerfCmd.op.seg_size : 65536
> > > DT_cs_Client: Starting Test ...
> > > Server Name: score1.ustb.cn-ib0
> > > Server Net Address: 192.168.67.0
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > WARNING: <score2-ib0> not registered in DNS, using dummy IP value
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > cl_open_device: opening device /dev/mvdapl8cd30a0
> > > cl_open_dev: error opening /dev/mvdapl8cd30a0 (No such file or
> directory)
> > > --> DsMI: Init MRDB failed =3D 0x1
> > > DT_cs_Client: IA IbalHca0 opened
> > > mlnx_pre_allocate_pd() [
> > > mlnx_pre_allocate_pd(): umv_buf->input_size 20, pd_ul_res_sz 16
> > > mlnx_pre_allocate_pd() ]
> > > mlnx_post_allocate_pd() [
> > > mlnx_post_allocate_pd() ]
> > > mlnx_pre_create_cq() [
> > > mlnx_pre_create_cq(): The created cq_size 15 different than=20
> > > *p_size 8
> > > mlnx_pre_create_cq() ]
> > > mlnx_post_create_cq() [
> > > mlnx_post_create_cq(): Newly created CQ cq_idx 0x88
> > > mlnx_post_create_cq() ]
> > > mlnx_enable_cq_notify() [
> > > mlnx_enable_cq_notify() ]
> > > mlnx_pre_create_cq() [
> > > mlnx_pre_create_cq(): The created cq_size 15 different than =
*p_size 8
> > > mlnx_pre_create_cq() ]
> > > mlnx_post_create_cq() [
> > > mlnx_post_create_cq(): Newly created CQ cq_idx 0x8a
> > > mlnx_post_create_cq() ]
> > > mlnx_enable_cq_notify() [
> > > mlnx_enable_cq_notify() ]
> > > mlnx_pre_create_qp() [
> > > mlnx_pre_create_qp() ]
> > > mlnx_post_create_qp() [
> > > mlnx_post_create_qp(): Newly created QP qp_idx 0x10019
> > > mlnx_post_create_qp() ]
> > > mlnx_pre_modify_qp() [
> > > mlnx_pre_modify_qp() ]
> > > mlnx_post_modify_qp() [
> > > mlnx_post_modify_qp(): Committed to modify QP to state 1
> > > mlnx_post_modify_qp() ]
> > > DT_cs_Client: EP created
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op =3D 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > ***** DAPL Characteristics *****
> > > Provider: IbalHca0 Version 1.0 DAPL 1.1
> > > Adapter: InfiniHost (Tavor) by Mellanox Technolgy Inc. Version
> 23108.161
> > > Supporting:
> > > 65512 EPs with 65535 DTOs and 4 RDMA/RDs each
> > > 16256 EVDs of up to 131071 entries (default S/R size is
> 16/16)
> > > IOVs of up to 60 elements
> > > 131056 LMRs (and 262128 RMRs) of up to 0xffffffffffffffff
> bytes
> > > Maximum MTU 0x80000000 bytes, RDMA 0x80000000 bytes
> > > Maximum Private data size 92 bytes
> > > Local IP address 4.3.2.1
> > > ***** ***** ***** ***** ***** *****
> > > DT_cs_Client: Posting 1 recv buffer
> > > mlnx_post_recv() [
> > > mlnx_post_recv() ]
> > > DT_cs_Client: Connect Endpoint
> > > al:query_req_cb() !ERROR!: query failed: IB_REMOTE_ERROR
> > > --> DiISQC: SA query callback failed status IB_REMOTE_ERROR
> > > --> DsINMG: query SA found no record
> > > --> DsIC: fail to map remote_ia_addr (sa_family 2) to gid
> > > DT_cs_Client: Cannot connect Endpoint DAT_INVALID_PARAMETER
> > > DT_cs_Client: Cleaning Up ...
> > > DT_cs_Client: dat_ep_disconnect (abrupt) error: DAT_INVALID_STATE
> > > mlnx_poll_cq() [
> > > mlnx_poll_cq() ]
> > > mlnx_pre_modify_qp() [
> > > mlnx_pre_modify_qp() ]
> > > mlnx_post_modify_qp() [
> > > mlnx_post_modify_qp(): Committed to modify QP to state 0
> > > mlnx_post_modify_qp() ]
> > > mlnx_pre_destroy_qp() [
> > > mlnx_pre_destroy_qp() ]
> > > mlnx_post_destroy_qp() [
> > > mlnx_post_destroy_qp() ]
> > > mlnx_pre_destroy_cq() [
> > > mlnx_pre_destroy_cq() ]
> > > mlnx_post_destroy_cq() [
> > > mlnx_post_destroy_cq() ]
> > > mlnx_pre_destroy_cq() [
> > > mlnx_pre_destroy_cq() ]
> > > mlnx_post_destroy_cq() [
> > > mlnx_post_destroy_cq() ]
> > > mlnx_pre_deallocate_pd() [
> > > mlnx_pre_deallocate_pd() ]
> > > mlnx_post_deallocate_pd() [
> > > mlnx_post_deallocate_pd() ]
> > > DT_cs_Client: IA IbalHca0 closed
> > > DT_cs_Client: =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D End of Work -- Client =
Exiting
> > > mlnx_pre_close_ca() [
> > > mlnx_pre_close_ca() ]
> > > mlnx_post_close_ca() [
> > > mlnx_post_close_ca(): PRE block
> > > mlnx_post_close_ca(): comm 27905 buf_size 48
> > > mlnx_post_close_ca(): POST block
> > > mlnx_post_close_ca() ]
> > > al:sync_destroy_obj() !ERROR!: Error waiting for references to be=20
> > > released. Forcing shutdown now. Ref_cnt =3D 1
> > > al:sync_destroy_obj() !ERROR!: 0x8077200(AL_OBJ_TYPE_H_AL)
> > > dapltest: al_common.c:504: async_destroy_cb: Assertion
> `!p_obj->ref_cnt'
> > > failed.
> > > ./bw.sh: line 22: 2392 Aborted ./dapltest -T P -d =
-i
> 1024
> > > -s ${host} -D ${device} -p 16 -m p RW ${size} 1
> > >
> > > i am a baby in iba.please tell me the detail,thanks. wangjue
_________________________________________________________________
=C3=E2=B7=D1=CF=C2=D4=D8 MSN Explorer: http://explorer.msn.com/lccn/ =20
-------------------------------------------------------
This SF.net email is sponsored by: The Robotic Monkeys at ThinkGeek For =
a limited time only, get FREE Ground shipping on all orders of $35 or =
more. Hurry up and shop folks, this offer expires April 30th! =
http://www.thinkgeek.com/freeshipping/?cpg=3D12297
_______________________________________________
Infiniband-general mailing list Inf...@li...
https://lists.sourceforge.net/lists/listinfo/infiniband-general
|
|
From: moral m. <mor...@ho...> - 2004-04-23 07:32:32
|
I am a chinese student.there are two question:
1)I can run ibal and opensm,it shows"subnet up".i can ping port1 from
por1 on the same computer.when i ping other port in the subnet,the computer
died.
2)i run a server which is waiting on scorce1.ustb.cn,after i start ibal
and opensm.when i run a client on score2.ustb.cn,it has these error:
> > >
> > > root@score2 dapltest]# ./bw.sh
> > > Usage: bw.sh [hostname [size [device]]]
> > > [root@score2 dapltest]# ./bw.sh score1.ustb.cn-ib0
> > > UAL: _init: Entered UAL Shell Initialization
> > > cl_open_device: opening device /dev/al
> > > uvp_get_interface() [
> > > mlnx_get_pd_interface() [
> > > mlnx_get_pd_interface() ]
> > > mlnx_get_qp_interface() [
> > > mlnx_get_qp_interface() ]
> > > mlnx_get_cq_interface() [
> > > mlnx_get_cq_interface() ]
> > > mlnx_get_eec_interface() [
> > > mlnx_get_eec_interface() ]
> > > mlnx_get_mrw_interface() [
> > > mlnx_get_mrw_interface() ]
> > > mlnx_get_mcast_interface() [
> > > mlnx_get_mcast_interface() ]
> > > mlnx_get_errh_interface() [
> > > mlnx_get_errh_interface() ]
> > > uvp_get_interface() ]
> > > mlnx_pre_open_ca() [
> > > mlnx_pre_open_ca() ]
> > > mlnx_post_open_ca() [
> > > cl_open_device: opening device /dev/mlx8cd30a0
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 1
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 1
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_post_open_ca(): comm 27904 buf_size 48
> > > mlnx_post_open_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > UAL: _init: Initialization completed successfully
> > > -------------------------------------
> > > PerfCmd.server_name : score1.ustb.cn-ib0
> > > PerfCmd.dapl_name : IbalHca0
> > > PerfCmd.mode : POLLING
> > > PerfCmd.num_iterations : 1024
> > > PerfCmd.pipeline_len : 16
> > > PerfCmd.op.transfer_type : RDMA_WRITE
> > > PerfCmd.op.num_segs : 1
> > > PerfCmd.op.seg_size : 65536
> > > DT_cs_Client: Starting Test ...
> > > Server Name: score1.ustb.cn-ib0
> > > Server Net Address: 192.168.67.0
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > WARNING: <score2-ib0> not registered in DNS, using dummy IP value
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca() ]
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > cl_open_device: opening device /dev/mvdapl8cd30a0
> > > cl_open_dev: error opening /dev/mvdapl8cd30a0 (No such file or
> directory)
> > > --> DsMI: Init MRDB failed = 0x1
> > > DT_cs_Client: IA IbalHca0 opened
> > > mlnx_pre_allocate_pd() [
> > > mlnx_pre_allocate_pd(): umv_buf->input_size 20, pd_ul_res_sz 16
> > > mlnx_pre_allocate_pd() ]
> > > mlnx_post_allocate_pd() [
> > > mlnx_post_allocate_pd() ]
> > > mlnx_pre_create_cq() [
> > > mlnx_pre_create_cq(): The created cq_size 15 different than *p_size 8
> > > mlnx_pre_create_cq() ]
> > > mlnx_post_create_cq() [
> > > mlnx_post_create_cq(): Newly created CQ cq_idx 0x88
> > > mlnx_post_create_cq() ]
> > > mlnx_enable_cq_notify() [
> > > mlnx_enable_cq_notify() ]
> > > mlnx_pre_create_cq() [
> > > mlnx_pre_create_cq(): The created cq_size 15 different than *p_size 8
> > > mlnx_pre_create_cq() ]
> > > mlnx_post_create_cq() [
> > > mlnx_post_create_cq(): Newly created CQ cq_idx 0x8a
> > > mlnx_post_create_cq() ]
> > > mlnx_enable_cq_notify() [
> > > mlnx_enable_cq_notify() ]
> > > mlnx_pre_create_qp() [
> > > mlnx_pre_create_qp() ]
> > > mlnx_post_create_qp() [
> > > mlnx_post_create_qp(): Newly created QP qp_idx 0x10019
> > > mlnx_post_create_qp() ]
> > > mlnx_pre_modify_qp() [
> > > mlnx_pre_modify_qp() ]
> > > mlnx_post_modify_qp() [
> > > mlnx_post_modify_qp(): Committed to modify QP to state 1
> > > mlnx_post_modify_qp() ]
> > > DT_cs_Client: EP created
> > > mlnx_pre_query_ca() [
> > > mlnx_pre_query_ca(): priv_op = 0
> > > mlnx_pre_query_ca() ]
> > > mlnx_post_query_ca() [
> > > mlnx_post_query_ca(): got ul resource size 48
> > > mlnx_post_query_ca() ]
> > > ***** DAPL Characteristics *****
> > > Provider: IbalHca0 Version 1.0 DAPL 1.1
> > > Adapter: InfiniHost (Tavor) by Mellanox Technolgy Inc. Version
> 23108.161
> > > Supporting:
> > > 65512 EPs with 65535 DTOs and 4 RDMA/RDs each
> > > 16256 EVDs of up to 131071 entries (default S/R size is
> 16/16)
> > > IOVs of up to 60 elements
> > > 131056 LMRs (and 262128 RMRs) of up to 0xffffffffffffffff
> bytes
> > > Maximum MTU 0x80000000 bytes, RDMA 0x80000000 bytes
> > > Maximum Private data size 92 bytes
> > > Local IP address 4.3.2.1
> > > ***** ***** ***** ***** ***** *****
> > > DT_cs_Client: Posting 1 recv buffer
> > > mlnx_post_recv() [
> > > mlnx_post_recv() ]
> > > DT_cs_Client: Connect Endpoint
> > > al:query_req_cb() !ERROR!: query failed: IB_REMOTE_ERROR
> > > --> DiISQC: SA query callback failed status IB_REMOTE_ERROR
> > > --> DsINMG: query SA found no record
> > > --> DsIC: fail to map remote_ia_addr (sa_family 2) to gid
> > > DT_cs_Client: Cannot connect Endpoint DAT_INVALID_PARAMETER
> > > DT_cs_Client: Cleaning Up ...
> > > DT_cs_Client: dat_ep_disconnect (abrupt) error: DAT_INVALID_STATE
> > > mlnx_poll_cq() [
> > > mlnx_poll_cq() ]
> > > mlnx_pre_modify_qp() [
> > > mlnx_pre_modify_qp() ]
> > > mlnx_post_modify_qp() [
> > > mlnx_post_modify_qp(): Committed to modify QP to state 0
> > > mlnx_post_modify_qp() ]
> > > mlnx_pre_destroy_qp() [
> > > mlnx_pre_destroy_qp() ]
> > > mlnx_post_destroy_qp() [
> > > mlnx_post_destroy_qp() ]
> > > mlnx_pre_destroy_cq() [
> > > mlnx_pre_destroy_cq() ]
> > > mlnx_post_destroy_cq() [
> > > mlnx_post_destroy_cq() ]
> > > mlnx_pre_destroy_cq() [
> > > mlnx_pre_destroy_cq() ]
> > > mlnx_post_destroy_cq() [
> > > mlnx_post_destroy_cq() ]
> > > mlnx_pre_deallocate_pd() [
> > > mlnx_pre_deallocate_pd() ]
> > > mlnx_post_deallocate_pd() [
> > > mlnx_post_deallocate_pd() ]
> > > DT_cs_Client: IA IbalHca0 closed
> > > DT_cs_Client: ========== End of Work -- Client Exiting
> > > mlnx_pre_close_ca() [
> > > mlnx_pre_close_ca() ]
> > > mlnx_post_close_ca() [
> > > mlnx_post_close_ca(): PRE block
> > > mlnx_post_close_ca(): comm 27905 buf_size 48
> > > mlnx_post_close_ca(): POST block
> > > mlnx_post_close_ca() ]
> > > al:sync_destroy_obj() !ERROR!: Error waiting for references to be
> > > released.
> > > Forcing shutdown now. Ref_cnt = 1
> > > al:sync_destroy_obj() !ERROR!: 0x8077200(AL_OBJ_TYPE_H_AL)
> > > dapltest: al_common.c:504: async_destroy_cb: Assertion
> `!p_obj->ref_cnt'
> > > failed.
> > > ./bw.sh: line 22: 2392 Aborted ./dapltest -T P -d -i
> 1024
> > > -s ${host} -D ${device} -p 16 -m p RW ${size} 1
> > >
> > > i am a baby in iba.please tell me the detail,thanks.
> > > wangjue
_________________________________________________________________
免费下载 MSN Explorer: http://explorer.msn.com/lccn/
|
|
From: s_zheng <s_...@ir...> - 2004-04-13 18:04:07
|
Hi, Could anyone tell me, whether there is an implementation of uDAPL or VIA, that is based on Infiniband? Thanks Ting |
|
From: Ting Z. <tin...@ra...> - 2004-04-13 18:02:37
|
Hi, Could anyone tell me, whether there is an implementation of uDAPL or VIA, that is based on Infiniband? Thanks Ting |
|
From: Tziporet K. <tzi...@me...> - 2004-03-14 08:13:53
|
Hi, In general InfiniBand requires memory registration to perform DMA with kernel bypass. This require special operations on the user level memory that currently are not available in the kernel. Of course we will be happy to enhance our implementation to work with more standard Linux API and drive new services needed by InfiniBand to the Linux kernel. Eli Cohen is Mellanox expert to the memory management in the HCA driver and he will answer in details regarding all memory management issues. Tziporet Tziporet Koren HCA drivers project leader Mellanox Technologies, Ltd mailto:tzi...@me... Tel +972-4-9097200, ext 380 -----Original Message----- From: Troy Benjegerdes [mailto:ho...@ho...] Sent: Friday, March 12, 2004 5:33 AM To: Roland Dreier; lin...@vg...; inf...@li... Subject: [Infiniband-general] Re: ANNOUCE: OpenIB InfiniBand software On Sat, Mar 06, 2004 at 01:00:59PM -0800, Roland Dreier wrote: > Several people have requested that we split the possibly-encumbered > SDP code into a separate package so that they don't have to download > it to get the free code. To allow that, I have split the kernel code > into two packages: > > infiniband-kernel-2004-03-05.tar.bz2 > infiniband-kernel-sdp-2004-03-05.tar.bz2 > Since the openib.org mailing lists don't seem to be alive yet, I'll bring this up here.. Can we get this split out into the following components? * kernel level infiniband access layer * lowlevel hardware driver (aka mellanox driver) * all other 'upper layer protocols' All the existing code has big problems with how it interfaces to the kernel memory management.. it doesn't use the regular interfaces like get_user_pages, pci_map_page, and pci_map_sq, and goes and looks at the guts of the pagetables directly. This is either a problem with the kernel interfaces made available, or a design issue with the existing codebases. Can someone please tell me which it is? -- -------------------------------------------------------------------------- Troy Benjegerdes 'da hozer' ho...@ho... Somone asked my why I work on this free (http://www.fsf.org/philosophy/) software stuff and not get a real job. Charles Shultz had the best answer: "Why do musicians compose symphonies and poets write poems? They do it because life wouldn't have any meaning for them if they didn't. That's why I draw cartoons. It's my life." -- Charles Shultz ------------------------------------------------------- This SF.Net email is sponsored by: IBM Linux Tutorials Free Linux tutorial presented by Daniel Robbins, President and CEO of GenToo technologies. Learn everything from fundamentals to system administration.http://ads.osdn.com/?ad_id=1470&alloc_id=3638&op=click _______________________________________________ Infiniband-general mailing list Inf...@li... https://lists.sourceforge.net/lists/listinfo/infiniband-general |
14 messages has been excluded from this view by a project administrator.
