Hi and sorry about the delay in the reply.
Roland Dreier wrote:
> > In issue number 296 that i opened several months ago in the Bugzilla, i
> > reported about two missing attributes: the first one is the static_rate,
> > and the second one is the src_path_bits which is not being filled right.
>
Roland Dreier wrote:
> I merged all these manpages into my libibverbs tree and pushed the
> result out to kernel.org.
>
> Please send any future updates as diffs against the libibverbs tree.
>
> Thanks,
> Roland
>
those are great news, thanks.
Before the OFED 1.2 release i plan to send you a
Roland Dreier wrote:
> > What about the patch that i sent on "Allow the following QP state
> > transition : reset --> reset"?
>
> OK, I'll merge that in the next patch. It's the kind of patch I'm not
> happy about merging, since it bloats the code to handle a corner case
> no one is likely to hi
Hi Roland.
Roland Dreier wrote:
> Linus, please pull from
>
> master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
> for-linus
>
> This tree is also available from kernel.org mirrors at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
> for-linus
>
>
Hi CQ.
Tang, Changqing wrote:
> Roland:
> If I only want to send/recv 4 bytes with immediate data:
>
> On sender side:
> opcode = IBV_WR_SEND_WITH_IMM;
> imm_data = my_4_bytes_data;
>
> Do I still need to specify sg_list and num_sge ?
>
If the data that is being sent is
Hi Mini and thanks for the quick response.
Moni Shoua wrote:
> OK. So I ran more tests on my setup which now include
> - Dual x86_64 processor (Intel Xeon)
> - 1GB RAM
> - 25204 HCA - fw_ver=1.1.0
>
> In the range of 16K - to 256K of value for num_qp I got no errors.
> For lower and higher values
Hi Moni.
I tried to use the mthca module parameter: for example i tried to change
the number of QPs.
I got several failures when i used the HCA 25204:
* sometimes i got the following error message (when using big values,
for example 512K QPs):
ib_mthca: :0c: INIT_HCA command failed aborting
Michael S. Tsirkin wrote:
>> I think that now, when implementation of IPoIB CM is available and SRQ
>> is being used, one may need to use a SRQ with more than 16K WRs.
>>
>
> Not really: IPoIB CM uses a common CQ for all recv completions, so
> it does not make sense for IPoIB CM to create a S
Hi Roland.
During the last night many tests failed in our regression (new failure
that appeared only during
the last night).
It seems that destroy an AH causes a seg fault, i reproduced it using
the ibv_ud_pingpong.
Here are the machine props:
**
Roland Dreier wrote:
> > anyway, the solution that comes into my mind is to disable creating a
> > QP/SRQ for which > 128KB allocations are needed. So
> > mthca_query_device() will set the max_qp_wr and max_srq_wr attributes
> > to values whose derived size still allows to use kmalloc.
>
> But
Roland Dreier wrote:
> > I created a git tree for the libibverbs man pages in the path:
> > ~dotanb/libibverbs_man_pages.git
>
> Great, I was just about to ask for your latest work so that I can
> start reviewing the man pages and merging them.
>
> However, what's the URL of your git tree...
> ne
Hi all.
I created a git tree for the libibverbs man pages in the path:
~dotanb/libibverbs_man_pages.git
Roland, can you please take those files and add them to libibverbs?
I will be more than happy to see those man pages in OFED 1.2
thanks
Dotan
Hi Roland.
I opened bug 331 in the bugzilla with the following content:
When one tries to create a SRQ with many WR (> 16K WR), creation of the SRQ
fails.
The problem appears to be in the file: mthca_srq.c.
Here is the problematic code:
static int mthca_alloc_srq_buf(struct mthca_dev *dev, st
Added resource cleaning before end of pingpong tests + ack to CQ events.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/examples/rc_pingpong.c
===
--- gen2_devel_user.or
Added checks to memory allocation failure when using asprintf in pingpong tests.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/examples/rc_pingpong.c
===
--- gen2_devel_use
Roland Dreier wrote:
> Looks pretty good, but could you please:
>
> - split off the asprintf() checks into a separate patch ("one idea
>per patch").
> - change the code so it keeps a count of cq events and then just
>does one ibv_ack_cq_events(cq, num_cq_events) at the end. If
>peopl
Roland Dreier wrote:
> > Did you push the static library link support in the last fixes/changes
> > that you made?
>
> Yes, it should be working better now.
>
I don't know what i tried to do several days ago (or on which driver
version), but now it works without any problem.
I'm adding this
Added resource cleaning before end of test + ack to CQ events.
Added checks to memory allocation failure when using asprintf.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/examples/rc_ping
Fix some memory leaks in case of error flows during driver init.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/src/init.c
===
--- gen2_devel_user.orig/src/userspace/libibver
Added checks to memory allocation failure when using asprintf.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/src/device.c
===
--- gen2_devel_user.orig/src/userspace/libibver
Added checks to memory allocation failure when using asprintf.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/perftest/rdma_bw.c
===
--- gen2_devel_user.orig/src/userspace/perftest/rdm
Added checks to memory allocation failure when using asprintf.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibcm/src/cm.c
===
--- gen2_devel_user.orig/src/userspace/libibcm/src/cm.
Hi Roland.
Dotan Barak wrote:
> Roland Dreier wrote:
>
>> > This is version 1.1-pre1.
>>
>> OK, I haven't pushed the changes to fix static linking in 1.1-pre
>> because I still need to finish fixing all the drivers for the ABI changes.
>>
&
Roland Dreier wrote:
> I would accept a patch that actually destroys all the IB objects, in
> which case acking CQ events is necessary. But I think I would prefer
> a patch that calls ibv_ack_cq_events() only once by keeping a count of
> the # of events to ack, since that style is likely to perfor
Joerg Zinke wrote:
> Hi,
>
> is there a non-blocking alternative for ib_cm_get_event() available? Any
> hints on how to check for events without blocking and waiting for the
> next one?
>
> Regards,
>
> Joerg
>
Here is a response that Or Gerlitz send a few weeks ago on getting
completion events
Roland Dreier wrote:
> OK, this is correct -- but since the examples don't destroy the CQ, is
> there any point in acking the events?
>
> - R.
>
(sorry if there is any duplication, i got an email warning)
I think that the answer is yes, those tests are being used as a code
reference for new us
Adding acks to all of the CQ events in the pingpong examples to show how
completion events should be used.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_user/src/userspace/libibverbs/examples/rc_ping
Steven Wooding wrote:
> Hi,
>
> I'm getting an IBV_WC_LOC_ACCESS_ERR when getting a work completion
> item related to an RDMA with ImmData transfer.
>
> What does this error actually mean?
>
> Thanks,
>
> Steve.
in which side do you get this completion?
My guess is that you are trying to s
Allow the following QP state transition : reset --> reset.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: gen2_devel_kernel/drivers/infiniband/hw/mthca/mthca_qp.c
===
--- gen2_devel_kernel.orig/drivers/infiniband
[EMAIL PROTECTED] wrote:
> Hi all and Happy new year.
>
> * I rewrote the man pages and removed all of the extra characters of the
> POD module (according to Roland request).
> * I tried to stick with the 80 characters limit (according to James
> request), without 100% success (when i
>descri
Sean Hefty wrote:
> Today, userspace support for SA related operations is limited to the libibmad
> interface, which supports sending and receiving MADs only. I've been assigned
> with the task of exposing multicast and informinfo support to userspace.
> Specifically, the following functionality i
Roland Dreier wrote:
> with a mem-free or tavor mode HCA?
>
> Are your test programs available from a git tree anywhere?
>
> Thanks,
> Roland
>
Here is the output of the valgrind when executing a "standard" test
which comes with the driver:
The server was executed on tavor and the client was
Roland Dreier wrote:
> > This is version 1.1-pre1.
>
> OK, I haven't pushed the changes to fix static linking in 1.1-pre
> because I still need to finish fixing all the drivers for the ABI changes.
>
Great, thanks.
Can you please update me when you'll add the static linking support to
this ve
Or Gerlitz wrote:
> Greenwood, Steve wrote:
>
>> I have a thread that uses ibv_get_cq_event to handling completing RDMA
>> requests. This call seems to have roughly the same capabilities as the
>> Mellanox vapi call EVAPI_poll_cq_block with one important exception.
>> The open-fabrics routi
Roland Dreier wrote:
> > Driver Version: gen2_devel-20070101-1730
>
> What version of libibverbs does this correspond to?
>
> > load_driver (so_path=0x5e65f0 "/usr/local//lib64/infiniband/mthca.so") at
> > src/init.c:61 (func: load_driver)
>
> This makes me think it is a version older than
Hi Roland and welcome back
Roland Dreier wrote:
> > For the following verbs (and I'm sure that this is not the full list)
> > there is a memory warning from valgrind:
> > ibv_query_device
> > ibv_dealloc_pd
> > ibv_create_cq
>
> Can you send the full warnings you get?
>
> Thanks
>
He
Hi Sean.
I'm validating the values of the CM:REQ packet and i noticed the
following behavior:
When side A sends a REQ message to side B, the values of several
attributes are being switched:
for example:
side A puts the following values:
REQ:initiator_depth = 1
REQ:responder_re
Bub Thomas wrote:
>Oops,
>I forgot to mention that the user paramter that fills this
>local_ack_timeout is called packet_life_time out of the
>ib_sa_path_record handed into the ib_cm_send_req.
>
>Maybe someone can put this into the upcoming man pages, if not already
>done.
>
>Thomas
>
>
As much
Hi.
What should happen in a completion event channel is being destroyed when
there are several CQs associated to it?
Should this operation fail (return EBUSY)?
Should this operation pass?
Is it legal for a user to perform this operation?
When i tried to do it and later on try to wait for a compl
Title: Message
Hi Diego.
You got the following
output:
utils.c: In function ‘__get_hz’:utils.c:368:
error: ‘HZ’ undeclared (first use in this function)utils.c:368: error: (Each
undeclared identifier is reported only onceutils.c:368: error: for each
function it appears in.)
because the
Added support to IB_EVENT_GID_CHANGE async event in mthca.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/drivers/infiniband/hw/mthca/mthca_mad.c
===
--- last_stable.orig/drivers/infiniband/hw
Added support to IBV_EVENT_GID_CHANGE async event to libibverbs.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/src/userspace/libibverbs/include/infiniband/verbs.h
===
--- last_stable.orig/src/use
Added support to IB_EVENT_GID_CHANGE async event in core.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/drivers/infiniband/include/rdma/ib_verbs.h
===
--- last_stable.orig/drivers/infiniband/includ
Sean Hefty wrote:
> Sean Hefty wrote:
>> This is a ROUTE_ERROR (path record query fails). Are the IP
>> addresses on different subnets? Are you having ucmatose bind to the
>> port 2 ip address.
>
> Another thing to check is what port ucmatose binds to after calling
> rdma_resolve_addr().
>
> -
Title: Message
Dotan Barak
Senior Software
Verification Engineer
Mellanox
Technologies
Tel:
+972-4-9097200 Ext: 231 Fax: +972-4-9593245
P.O. Box 86
Yokneam 20692 Israel.
___
openib-general mailing list
openib-general@openib.org
http
Hi.
Venkatesh Babu wrote:
> I don't think there is any event which says "path1 is back again". It
> is the application which needs to load the alternate path. The HW just
> sends an event IB_EVENT_PORT_ACTIVE when port comes up. Upon recipt of
> the this event the application has to see if th
Hi Roland.
I started to work on the man pages of the user level verbs few weeks ago
and
i would like to start integrating those pages to the openib svn (I
finished ~40% of the verbs) .
How can i do it:
* Do you want me to commit the files to libibverbs/man folder?
* Do you want me to send you t
qp_access_flags was changed to zero (this attribute is for remote access
permissions only and local write is invalid value).
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/drivers/infiniband/core
Hi Ira.
Ira Weiny wrote:
> I got the following error running with OFED 1.1 on a modified 2.6.9 RHEL4
> kernel. Hal mentioned that there might be a catastrophic error recovery patch
> submitted since then? I can't find a mention of that in the mailing list. If
> possible I would like to try such
Compilation warning on 64 bit machines was fixed.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/src/userspace/librdmacm/examples/rping.c
===
--- last_stable.orig/src/userspace/librdmacm/examples/r
Hi Troy.
Troy Benjegerdes wrote:
> If ibv_reg_mr fails, can an application (or library, such as pvfs)
> assume that this is just a temporary error, and try to deregister
> some memory, then try again?
>
I believe that the answer is not always. They may be several reasons for
a memory regis
Hi.
I'm using the following configuration:
*
Host Architecture : x86_64
Linux Distribution: SUSE Linux Enterprise Server 10 (x86_64) VERSION = 10
Kernel Version: 2.6.16.21-0.8-smp
GCC Version : gcc (GCC) 4.1.0 (SUSE Linux)
Memor
Hi.
I started to write man pages for the ib verbs API in the user level.
Those pages are based on the the verbs description (in verbs.h), on the
IB spec and on my experience.
Attached is a file with the man pages (binary + pod source files +
Makefile) of the following verbs:
ibv_get_devi
Added enumeration of port capabilities so user level application will know
the supported features of the port.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/src/userspace/libibverbs/include/infiniband/v
Michael S. Tsirkin wrote:
> Quoting r. Dotan Barak <[EMAIL PROTECTED]>:
>
>> Subject: what happens if one close the device in user level without
>> releasing the resources?
>>
>> Hi.
>>
>> What should happen if one opens the IB device, all
Hi.
What should happen if one opens the IB device, allocate resources and
close the device?
for example, if a user do the following operations in a loop:
ibv_get_device_list
in a loop:
ibv_open_device
ibv_alloc_pd
ibv_create_cq
ibv_close_device?
should the ib
Roland Dreier wrote:
> Dotan> The problem is that the private_data_len in the second side
> Dotan> (receiver) is not equal to the sent data (length).
>
> How do you expect the private data length to be passed from one side
> to the other? There is no such field in the CM protocol.
>
> The
Hi Sean.
I'm using the following configuration:
*
Host Architecture : x86_64
Linux Distribution: Red Hat Enterprise Linux AS release 4 (Nahant Update 3)
Kernel Version: 2.6.9-34.ELsmp
GCC Version : gcc (GCC) 3.4.5 20051201 (Red
amit byron wrote:
> Dotan Barak dev.mellanox.co.il> writes:
>
>
>> Hi.
>>
>> amit byron wrote:
>>
>>> hi,
>>>
>>> if i evoke/call ib_post_send(IB_WR_SEND) with message
>>> size 512 bytes, the message gets re
Hi.
When i executed "man ibv_devinfo" or "man ibstat" (for example) i
notices that those man pages are marked as part of the OpenIB package.
I believe that the package name should be changed to OFED.
what do you think?
thanks
Dotan
___
openib-general
IPoIB: Removed unused include of vmalloc.h.
Signed-off-by: Dotan Barak <[EMAIL PROTECTED]>
---
Index: last_stable/drivers/infiniband/ulp/ipoib/ipoib_main.c
===
--- last_stable.orig/drivers/infiniband/ulp/ipoib/ipoib_main.c
2
Robert Walsh wrote:
> Another quick question: I noticed that in the latest changes your
> pushed, including my patches, you removed the following check in test_qp.c:
>
> @@ -1702,7 +1700,6 @@
> CHECK_VALUE("qp_type", query_init_attr.qp_type,
> attr.qp_type, goto cleanup);
>
Robert Walsh wrote:
> gen2_basic - handle other vendor devices for max QP count
>
> When choosing the actual max QP number, handle non-Mellanox devices too.
> Make sure we only clean up the QPs we actually created.
>
> Signed-off by: Robert Walsh <[EMAIL PROTECTED]>
>
> diff -rNu a/gen2_basic/test_
Robert Walsh wrote:
> gen2_basic - fix static_rate check
>
> Make sure we're comparing apples to apples in the static_rate check.
>
> Signed-off by: Robert Walsh <[EMAIL PROTECTED]>
>
> diff -rNu a/gen2_basic/test_qp.c b/gen2_basic/test_qp.c
> --- a/gen2_basic/test_qp.c2006-09-13 19:17:17.83592
Robert Walsh wrote:
> gen2_basic - handle auto path migration properly
>
> Signed-off by: Robert Walsh <[EMAIL PROTECTED]>
>
> diff -rNu a/gen2_basic/test_qp.c b/gen2_basic/test_qp.c
> --- a/gen2_basic/test_qp.c2006-09-13 19:15:59.829006000 -0700
> +++ b/gen2_basic/test_qp.c2006-08-14 14:16
Robert Walsh wrote:
> gen2_basic - choose illegal max_qp_init_rd_atom values correctly
>
> Signed-off by: Robert Walsh <[EMAIL PROTECTED]>
>
> diff -rNu a/gen2_basic/test_qp.c b/gen2_basic/test_qp.c
> --- a/gen2_basic/test_qp.c2006-09-13 19:09:47.419791000 -0700
> +++ b/gen2_basic/test_qp.c
Hi Robert.
Robert Walsh wrote:
> Hi Dotan,
>
> I just noticed that you didn't apply one of my patch hunks that called
> get_is_global(). I know why you didn't do it (the dlid is always 0: see
> line 218 of test_av.c), but should you still be setting the is_global
> field in the ah_attr structure
Hi.
amit byron wrote:
> hi,
>
> if i evoke/call ib_post_send(IB_WR_SEND) with message
> size 512 bytes, the message gets received on the
> peer (second) node. the 2 nodes are connected point-to
> -point.
>
> but if message size is increased to 4096 bytes then
> second node receives the message; bu
Hal Rosenstock wrote:
> On Wed, 2006-09-20 at 01:05, Michael S. Tsirkin wrote:
>
>> Quoting r. Hal Rosenstock <[EMAIL PROTECTED]>:
>>
>>> Subject: Re: gen2_basic patch 5/10: select a valid port number
>>>
>>> On Tue, 2006-09-19 at 21:16, Robert Walsh wrote:
>>>
Hal Rosenstock wr
Dotan Barak wrote:
> Robert Walsh wrote:
>
>> -BEGIN PGP SIGNED MESSAGE-
>> Hash: SHA1
>>
>> Hi all,
>>
>> We've got some patches to gen2_basic to fix some problems with the test
>> suite. Some are trivial (fix typos, etc.) and som
Robert Walsh wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Hi all,
>
> We've got some patches to gen2_basic to fix some problems with the test
> suite. Some are trivial (fix typos, etc.) and some are more serious
> (handle max_qp counts correctly, etc.) I'm going to be sending them
Mahesh Barve wrote:
> Hi,
> Infiniband allows the creation of 16M QPs.
> Suppose a programmer wants to post separate requests on each of the
> QPs simultaneously,
> what would be the most efficient way of doing it?
> regards,
> -mahesh
>
what is your question: should you use threads? shoul
ort of HCA2.
If you wish, your SW can handle all of the HCAs: you can open a QP for
every port in every HCA( total QPs: #HCAs * #Ports ).
i hope i was more clear this time ...
Dotan
>
>
> On 9/18/06, *Dotan Barak* <[EMAIL PROTECTED]
> <mailto:[EMAIL PROTECTED]>>
Hi john.
john t wrote:
> Hi
>
> I have two HCA cards each having one port. I want to use same memory
> buffer to store packets arriving on the two ports. Can I do this,
> meaning can I use same pd (protection domain) and mr (memory
> registration) for the two QPs (one QP on each port), though
Hi all.
In
https://openib.org/svn/trunk/contrib/mellanox/ibtp/gen2/userspace/useraccess/multicast_test
there is
an example for using multicast messages over the verbs.
This test (for now) don't send any join message to the SA, it only
attach (and detach) the QP to the multicast group.
Dotan
Bub Thomas wrote:
> Dortan Barak wrote:
> If you are using RC QP:
> the reason for not getting any completion in the CQ is that
>
> Did you post any RR (Receive Request) at the listener side?
>
>
> Dotan,
> with the cmpost.c example I now get a cm connection even with another
> machine.
> However I
Hi john.
john t wrote:
> Hi OpenIB group,
>
> What is the difference between HCAs with memory and without memory.
> How is the on-board memory used by HCAs? Is it that data is first
> copied into this memory and then into physical memory?
>
> Regards,
> John T.
If you are asking about Mella
Tom Tucker wrote:
> Sean:
>
> The user-mode cm header files don't have the C++ stuff to identify all
> the declarations as C. The verbs.h file has it and works fine if you
> wanted to copy it, but all you really need is ...
>
> #ifdef __cpluplus
> extern "C" {
> #endif
>
> at the top
Bub Thomas wrote:
Dotan,
the ibv_rc_pingpong example works for me so I can exclude the
architecture.
I never got the libibcm example compiled.
Which is your example and which architecture x86 vs. x86_64 did you
compile it for?
Can you share your libibcm the example code? (if it is not the standar
Sean Hefty wrote:
>> # udaddy
>> udaddy: starting server
>> librdmacm: Kernel ABI does not support requested port space.
>> udaddy: listen request failed
>> test complete
>> return status -93
>>
>
> UD QP and multicast support requires kernel ABI version 2. It appears that
> the
> kernel ver
Hi Thomas.
Bub Thomas wrote:
>
> I’m still in the process of porting my gen1 code to gen2.
>
> As mentioned yesterday I can connect to a listener on the same machine
> using libibcm.
>
> Doing this I have to do the ibv_modify_qp by myself to get the qp’s
> from INIT via RTR to RTS on both sides
Here are the machine/driver props:
*
Host Architecture : x86_64
Linux Distribution: SUSE Linux Enterprise Server 10 (x86_64) VERSION = 10
Kernel Version: 2.6.16.21-0.8-smp
GCC Version : gcc (GCC) 4.1.0 (SUSE Linux)
Memory size
Hi bub.
Bub Thomas wrote:
>
> I’m still in the process of migrating my gen1 application to gen2.
>
> Actually I CAN connect a gen2 application to a gen2 listener
> application on the same machine but NOT to a gen 2 listener on another
> machine.
>
> Any hints where to look at?
>
> Is there anyt
Hal Rosenstock wrote:
> John,
>
> On Mon, 2006-09-04 at 08:56, john t wrote:
>
>> Hi,
>>
>> I have 3 nodes connected via IB as shown below:
>>
>> node1 ---> switch1 ---> node2
>> |--> node3
>>
>> If node1 sends a brodcast message to node2 and node3, I want to kn
yipee wrote:
> Hi,
>
> Is it possible for several memory registrations (using ibv_reg_mr) to have a
> single rkey?
> Can I add memory registrations to a previous rkey?
>
>
> thanks,
> y
>
I believe that the answer is no.
Dotan
___
openib-general mail
Sean Hefty wrote:
> Jack Morgenstein wrote:
>
>> Fix compilation on SLES10:
>> cm.c uses offsetof, so it must include stddef.h
>>
>
> Thanks - committed in 9150.
>
>
I checked this libibcm with multithreaded test (qp_test) and it is
working with no problems.
thanks
Dotan
Sunil Patil wrote:
> I am using socket based communication for exchanging intial
> information such as lid,qpn,psn, in fact, more or less the same code
> that is there in the examples. Is there any CM based example that I
> can look at?
>
> Regards,
> John
in: https://openib.org/svn/gen2/trunk
Hi.
john t wrote:
> Hi Dotan
>
> Is there a way to know if the two QPs (local and remote) are in sync
> or to wait for them to get in sync and then do the data transfer.
>
> I think in my case it is more like one QP is sending the message but
> the other end (receiver) is not in RTR state at
Hi.
john t wrote:
> Hi,
>
> In one of my multi-threaded application (simple send/recv application
> written using uverbs), I am repeatedly getting an error code 12
> (IB_WC_RETRY_EXC_ERR) from "ibv_poll_cq". Not able to figure out
> what is going wrong. Cam some one please give a suggestion s
Sean Hefty wrote:
>> Modify the libibcm API to provide better support for multi-threaded
>> event processing. CM devices are no longer tied to verb devices
>> and hidden from the user. This should allow an application to direct
>> events to specific threads for processing.
>>
>> This patch also rem
resending the response (after a problem in my mail client):
> john t wrote:
>>
>> What is the meaning of above fields or where can I find the
>> definition of above fields ? Can I change the value of fields like
>> "timeout" or should it be always set to a fixed value.
> You can find the descri
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Sean Hefty
> Sent: Friday, August 18, 2006 7:06 PM
> To: Bub Thomas
> Cc: openib-general@openib.org
> Subject: Re: [openib-general] libibcm can't open /dev/infiniband/ucm0
>
>
> Bub Thomas wrote:
> >
Hi and welcome John
:)
On Wednesday 16 August 2006 09:01, john t wrote:
> Hi,
>
> I am new to openIB and have some questions.
>
> - A QP has two work queues, send work queue and receive work queue. When
> host A sends a data buffer to host B using a QP (RC), I want to know if data
> is copied
Hi guys.
On Monday 14 August 2006 23:33, Sean Hefty wrote:
> Steve Wise wrote:
> > So is this replicating done in the mthca hca?
>
> As just an FYI, I didn't see anything wrong in the mthca driver either when I
> was looking at this problem.
>
> > Since one app is getting the mcast packet, ca
On Monday 14 August 2006 16:09, Sasha Khapyorsky wrote:
> >
> > Why doesn't the SM print that this file was found?
>
> Yes, some prints may be helpful. Do you mean just log file or would prefer
> the message on stdout too?
I believe that most of the users don't look at the log file, so a message
Thanks for the quick response.
On Monday 14 August 2006 15:17, Sasha Khapyorsky wrote:
> Hi Dotan,
>
> On 14:36 Mon 14 Aug , Dotan Barak wrote:
> > Hi.
> >
> > I noticed that the behavior of the openSM was changed in the latest driver:
> >
> > in the
Hi.
I noticed that the behavior of the openSM was changed in the latest driver:
in the past, every HCA was configured (by the FW) with 0x in the first
entry.
today, the PKey table is being configured by the openSM: the first entry
is being set to 0x7fff (except for the host that the SM is b
Hi.
I noticed the following code in the librdmacm (in gen2_linux-20060807-1730
(REV=8840)):
static void ucma_copy_conn_param_to_kern(struct ucma_abi_conn_param *dst,
struct rdma_conn_param *src,
uint32_t qp_num,
On Monday 07 August 2006 21:02, Sean Hefty wrote:
> Dotan Barak wrote:
> > enum ib_cm_sidr_status { 0, 1, 2, 3, 4, IB_SIDR_UNSUPPORTED_VERSION };
> >
> > it seems that the enumerations values were replaced with integers.
> >
> > when i searched for the values t
On Monday 07 August 2006 20:37, Sean Hefty wrote:
> > How should a multithreaded application need to work with the libibcm?
>
> I understand what the problem is, and I think you're right. If
> ib_cm_get_device() returned a new ib_cm_device, you could more easily control
> event processing. I w
1 - 100 of 260 matches
Mail list logo