Quoting r. Michael S. Tsirkin <[EMAIL PROTECTED]>:
> Subject: Re: convention for git directories on the new git OFA server
>
> Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> > Subject: Re: convention for git directories on the new git OFA server
> >
> > > So, what do you suggest for openfabrics
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: convention for git directories on the new git OFA server
>
> > So, what do you suggest for openfabrics? Could you write it up?
>
> Actually, ~user is probably OK. If we want to do ~ofed then we just
> have to create an ofed user, and
> So, what do you suggest for openfabrics? Could you write it up?
Actually, ~user is probably OK. If we want to do ~ofed then we just
have to create an ofed user, and a group to put everyone with write
permission to the ofed tree. Creating directories in /pub/scm just
saves creating the fake us
Thanks, applied to libibverbs and libibverbs-1.0
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Ok, I thought about this probably way more than it was worth. And I
think we might as well just go ahead and make this change. The only
sensible situation is with both a new kernel and new userspace --
everything else is broken anyway.
So I just applied this as-is.
- R.
__
On Tue, Oct 31, 2006 at 06:59:02AM +0200, Sasha Khapyorsky wrote:
> > > This would be simpler. However some web searching shows that not all
> > > printf() implementation permits not null terminated arrays even when
> > > precision is specified (some issues were reported even with glibc-2.3.2).
>
Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] diags/saquery: fix node_desc.description as string usages
>
> On 06:30 Tue 31 Oct , Michael S. Tsirkin wrote:
> > Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> > > Subject: Re: [PATCH] diags/saquery: fix node_desc.des
On 06:30 Tue 31 Oct , Michael S. Tsirkin wrote:
> Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCH] diags/saquery: fix node_desc.description as string
> > usages
> >
> > On 13:44 Mon 30 Oct , Michael S. Tsirkin wrote:
> > > Quoting r. Sasha Khapyorsky <[EMAIL PROTE
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: convention for git directories on the new git OFA server
>
> > OK, good idea. Same for OFED I guess - we can have e.g. ~ofed/ if
> > several people need to share the same ofed trees.
> >
> > So it seems it is best to stick with ~use
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: creating releases for the libraries you own
>
> > > > Well, with ~user/html I can easily cook up a perl script to generate
> a MD5
> > > > checksums or sign stuff and just stick them in the same directory as
> original files.
> >
Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] diags/saquery: fix node_desc.description as string usages
>
> On 13:44 Mon 30 Oct , Michael S. Tsirkin wrote:
> > Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> > > Subject: [PATCH] diags/saquery: fix node_desc.descrip
> > > Well, with ~user/html I can easily cook up a perl script to generate a
> > MD5
> > > checksums or sign stuff and just stick them in the same directory as
> > original files.
> >
> > But you can do that with any old hosting, can't you? Or am I missing
> > something?
>
> This de
> OK, good idea. Same for OFED I guess - we can have e.g. ~ofed/ if
> several people need to share the same ofed trees.
>
> So it seems it is best to stick with ~user/ convention - this allows
> creating trees without admin permission. Makes sense?
That's OK, although /pub/scm may be easier
> Sean, i don't familiar with the cm.c code, but i believe that the
> following patch will solve this issue:
>
> Index: last_stable/drivers/infiniband/core/cm.c
> ===
> --- last_stable.orig/drivers/infiniband/core/cm.c 2006-10-
Require registration with ib_addr module to prevent caller from unloading
while a callback is in progress.
Signed-off-by: Sean Hefty <[EMAIL PROTECTED]>
---
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 60d3fbd..894d856 100644
--- a/drivers/infiniband/core/addr
On Mon, 2006-10-30 at 17:29, Michael Krause wrote:
> At 02:05 PM 10/30/2006, Roland Dreier wrote:
> > Hal> So rate = speed * width ?
> >
> >Yes, you should see the right think on DDR systems etc.
>
> Strange. Bandwidth = signaling rate * width. This of course is raw
> bandwidth prior to en
At 02:05 PM 10/30/2006, Roland Dreier wrote:
> Hal> So rate = speed * width ?
>
>Yes, you should see the right think on DDR systems etc.
Strange. Bandwidth = signaling rate * width. This of course is raw
bandwidth prior to encoding, protocol, etc. overheads which will derate the
effective
On Mon, 2006-10-30 at 17:11, Roland Dreier wrote:
> > > I guess so. If someone sends a patch I would be inclined to merge it.
> >
> > OK; How should devices that didn't support these be handled ? Should
> > there be missing files or the files have values of 0 or something else ?
>
> I would
I tried this patch and it is working fine. Now if I remove the both
the cables connected to the destination, the IB_WC_RETRY_EXC_ERR on the
first outstanding WR on a CQ as expected.
With this patch I think all my APM related isses were resolved.
Dotan, you can check this fix into the OFED s
> > I guess so. If someone sends a patch I would be inclined to merge it.
>
> OK; How should devices that didn't support these be handled ? Should
> there be missing files or the files have values of 0 or something else ?
I would only create the files if the counters are supported.
> > But
On Mon, 2006-10-30 at 16:56, Roland Dreier wrote:
> > Should the optional 64-bit port counters be supported in sysfs ?
>
> I guess so. If someone sends a patch I would be inclined to merge it.
OK; How should devices that didn't support these be handled ? Should
there be missing files or the fil
Hal> So rate = speed * width ?
Yes, you should see the right think on DDR systems etc.
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org
On Mon, 2006-10-30 at 16:55, Roland Dreier wrote:
> > Should support for speed be added to ibstatus ?
>
> What is "speed"? Is that something beyond the existing "rate" line:
>
> > rate:10 Gb/sec (4X)
So rate = speed * width ?
-- Hal
> - R.
> Should the optional 64-bit port counters be supported in sysfs ?
I guess so. If someone sends a patch I would be inclined to merge it.
But are there any devices that support them?
- R.
___
openib-general mailing list
openib-general@openib.org
http
> Should support for speed be added to ibstatus ?
What is "speed"? Is that something beyond the existing "rate" line:
> rate:10 Gb/sec (4X)
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailma
Should the optional 64-bit port counters be supported in sysfs ?
-- Hal
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-
Should support for speed be added to ibstatus ?
Infiniband device 'mthca0' port 1 status:
default gid: fe80::::0008:f104:0396:0559
base lid:0xa
sm lid: 0xa
state: 1: DOWN
phys state: 2: Polling
rate:
OpenSM: Update opensm man page and modular-routing.txt for LID matrix
handling
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
Index: man/opensm.8
===
--- man/opensm.8(revision 10004)
+++ man/opensm.8(working copy)
On 13:44 Mon 30 Oct , Michael S. Tsirkin wrote:
> Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> > Subject: [PATCH] diags/saquery: fix node_desc.description as string usages
> >
> >
> > node_desc.description buffer is received from the network and should
> > not be NULL-terminated. In suc
Sean Hefty wrote:
>>One of the systems kernel is actually 2.6.19-rc3 and patches 1-7 (ie not
>>roland's tree) and i see there some issues also with ip multicast over
>>ipoib. I will move to use the same kernel config (roland's tree and
>>patches 1-7), then test ipoib and only then mckey, will le
Thanks for sending the patch. I will try this out and let you know the
results.
VBabu
Dotan Barak wrote:
> 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
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: creating releases for the libraries you own
>
> > Well, with ~user/html I can easily cook up a perl script to generate a MD5
> > checksums or sign stuff and just stick them in the same directory as
> original files.
>
> But you can d
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: convention for git directories on the new git OFA server
>
> > Yes, but:
> >
> > Linus's tree is under
> > git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
> > E.g. stable tree is under
> > git://git.kernel.org
Or Gerlitz wrote:
> One of the systems kernel is actually 2.6.19-rc3 and patches 1-7 (ie not
> roland's tree) and i see there some issues also with ip multicast over
> ipoib. I will move to use the same kernel config (roland's tree and
> patches 1-7), then test ipoib and only then mckey, will le
> Well, with ~user/html I can easily cook up a perl script to generate a MD5
> checksums or sign stuff and just stick them in the same directory as
> original files.
But you can do that with any old hosting, can't you? Or am I missing
something? I just don't see much point in yet another pla
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: creating releases for the libraries you own
>
> > Right, but consider that longterm we will need to add checksums
> > and possibly sign packages, etc. Doing all this manually
> > through wiki just to publish an RC will be a hassle, an
> Yes, but:
>
> Linus's tree is under
> git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
> E.g. stable tree is under
> git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-2.6.18.y.gi
>
> So I do see the analogy: development trees are under developer's name,
> s
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: convention for git directories on the new git OFA server
>
> >1. Development trees: each one will place the development tree under
> > his/her home:
> > ~/scm/topic.git (e.g. ~mst/scm/sdp.git)
> >2. Stable/release
> Right, but consider that longterm we will need to add checksums
> and possibly sign packages, etc. Doing all this manually
> through wiki just to publish an RC will be a hassle, and error prone.
Yes, I agree. That's why I said that just having ~user/html or
whatever isn't very interesting.
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: creating releases for the libraries you own
>
> > How about allowing web server serve static pages from
> > /pub/html and ~/html? Then anyone with an account
> > can easily upload files by scp, and post a link.
>
> I think that solve
On Sat, 2006-10-28 at 16:17, Sasha Khapyorsky wrote:
> On 22:35 Thu 19 Oct , Sasha Khapyorsky wrote:
> > This unifies ucsat_mgr dumper. Main goal is to provide infrastructure
> > for different dump file generation using the same routines.
> >
> > Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECT
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH/RFC 2/2] IPoIB: Convert to NAPI
>
> > #of sockets : 124 8 16
> > NONAPI BW :276 297 304 306 303
> > NAPI BW :302 311 349 408 367
>
> OK, the NAPI numbers are > than the NONAPI numbers, which I
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] IB/mthca: fix MAD extended header format
>
> > Roland, the offsets look wrong. Am I missing something?
> > Please review vs the spec, and if correct consider for 2.6.19.
>
> I just applied your original patch without checking
On Thu, 2006-10-19 at 16:35, Sasha Khapyorsky wrote:
> This is bonus - switch forwarding tables dump compatible with output
> produced by dump_lfts.sh and which can be used as input for unicast
> forwarding tables loader (with -R 'file' -U ). The dump file
> name is 'opensm-lfts.sh' and will be gen
> By the way, by userspace DMA do you mean DMA to userspace buffers, or
> DMA initiated by userspace? I'm assuming the former, but if it's the
> latter, how are the addresses returned from dma_map_sg communicated to
> userspace?
Actually, both. Userspace deals in virtual addresses (it asks th
> #of sockets : 124 8 16
> NONAPI BW :276 297 304 306 303
> NAPI BW :302 311 349 408 367
OK, the NAPI numbers are > than the NONAPI numbers, which I guess is
good :) What are the units?
- R.
___
openib-general mail
>1. Development trees: each one will place the development tree under
> his/her home:
> ~/scm/topic.git (e.g. ~mst/scm/sdp.git)
>2. Stable/release trees: these trees will be located under /pub:
> /pub/scm/.git (e.g. /pub/scm/ofed-1.1.git)
>3. All trees (developme
> Roland, the offsets look wrong. Am I missing something?
> Please review vs the spec, and if correct consider for 2.6.19.
I just applied your original patch without checking it carefully :)
Yes, the offsets in your patch look like they match the PRM now.
However:
> +#define MAD_IFC_RLID_OFFSE
> How about allowing web server serve static pages from
> /pub/html and ~/html? Then anyone with an account
> can easily upload files by scp, and post a link.
I think that solves the wrong part of the problem. It's trivial for
me to find places to host stuff. The issue is having a place for
"
Hi all,
I suggest we use the following convention for all our git trees in the
OFA server:
1. Development trees: each one will place the development tree under
his/her home:
~/scm/topic.git (e.g. ~mst/scm/sdp.git)
2. Stable/release trees: these trees will be located under /pub:
Hello Tziporet,
> When accessing this page there is a login form What is this used for?
The package drupal was installed as an experiment to serve up web pages. I
am barely familiar with it but gather that it allows users to login and
maintain portions of the site. There is more information on
Hi Johann,
When accessing this page there is a login form
What is this used for?
I also see it's not https?
Tziporet
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Johann George
Sent: Thursday, October 26, 2006 3:28 AM
To: Open Fabrics; openib-general@op
On Thu, 2006-10-19 at 16:35, Sasha Khapyorsky wrote:
> This adds dumping switches lid matrices to the file
> 'opensm-lid-matrix.dump'. Like other routing related dumps this code
> will be activated when OSM_LOG_ROUTING logging flag is set.
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
T
On Thu, 2006-10-19 at 16:35, Sasha Khapyorsky wrote:
> This unifies ucsat_mgr dumper. Main goal is to provide infrastructure
> for different dump file generation using the same routines.
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
Thanks. Applied.
-- Hal
___
Several fiels in an incoming MAD extended info header were passed at incorrect
offsets (mostly off by 4 bytes). As the result, the HCA will fail to generate
traps in which this info is needed (e.g. traps which include the GRH of the
incoming packet), in violation of the IB spec.
Signed-off-by: Mi
On Sat, 28 Oct 2006, Or Gerlitz wrote:
> What's RNFS?
NFS-RDMA.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-genera
On Thu, 2006-10-19 at 16:35, Sasha Khapyorsky wrote:
> This adds new method named build_lid_matrices() to OpenSM routing engine
> structure. When defined this method will be used by ucast_mgr_process()
> for switch min hop tables (aka lid matrices) preparation. In case of
> failure default lid matr
Title: Message
Hi
Michael,
The output of
mstflint is changed on ppc64 as result of byte ordering
issues.
If you take a HCA
that was burned using x86_64 or Mellanox manufacturing and perform
mstflint -d ... q on ppc64
you'll find that the
value of PSID VSD and Board Id was changed.
Or Gerlitz wrote:
> Or Gerlitz wrote:
>> OK, Sean, i have one system up and running, with kernel based on
>> Roland's git plus patches 1-7 and user space based on the svn with the
>> librdmacm patch. Will clone this config on Sunday such that i can
>> actually run mckey and see it working. Thank
On Sat, 2006-10-28 at 16:33, Sasha Khapyorsky wrote:
> node_desc.description buffer is received from the network and should
> not be NULL-terminated. In such cases using it as regular string in
> functions like printf() leads to segmentation faults. This patch fixes
> such usages.
>
> Signed-off-b
On Sat, 2006-10-28 at 16:41, Sasha Khapyorsky wrote:
> Hmm, in one place there was the same copy-paste error as in the osmtest
> patch. Resend this one too...
>
> Sasha
>
>
> node_desc.description buffer is received from the network and should
> not be NULL-terminated. In such cases using it as
On Sat, 2006-10-28 at 16:06, Sasha Khapyorsky wrote:
> Some trivial indentation fixes.
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
> ---
Thanks. Applied.
-- Hal
___
openib-general mailing list
openib-general@openib.org
http://openib.org/m
On Sat, 2006-10-28 at 15:57, Sasha Khapyorsky wrote:
> This converts guid value to host byte order before printing.
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
Thanks. Applied.
-- Hal
___
openib-general mailing list
openib-general@openib.
Quoting r. Sasha Khapyorsky <[EMAIL PROTECTED]>:
> Subject: [PATCH] diags/saquery: fix node_desc.description as string usages
>
>
> node_desc.description buffer is received from the network and should
> not be NULL-terminated. In such cases using it as regular string in
> functions like strcmp()
On Sun, 2006-10-29 at 15:06, Sasha Khapyorsky wrote:
> Then new partition creation is requested strip unconditionally
> membership bit before == 0 verification (when autogenerated pkey value
> is requested).
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
Thanks. Applied.
-- Hal
__
On Sat, 2006-10-28 at 16:04, Sasha Khapyorsky wrote:
> node_desc.description buffer is received from the network and should
> not be NULL-terminated. In such cases using it as regular string in
> functions like strcmp() or printf() leads to segmentation faults.
> This patch fixes such usages.
>
>
On Sat, 2006-10-28 at 20:09, Sasha Khapyorsky wrote:
> This removes non-referenced include/opensm/osm_mcmember.h header file.
>
> Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
Thanks. Applied.
-- Hal
___
openib-general mailing list
openib-gener
Hi guys , I am getting the following error while running Chears runs on my cluster .. Can any of you tell me why this is happening .. Thanks and RegardsShiraz [node021:12] Fatal Error: Unexpected disconnect received from [node003:30] at line 1698 in file vapiutil.c
[node010:23] Fatal Error: Unexpe
68 matches
Mail list logo