Although not a fit IMO, the pragmatic solution is to move ib_types,h into
libibumad. I think it is better there than OpenSM which was never quite right
either. That can at least start to eliminate the duplications in this area.
ib_types.h includes complib header files...
This email was generated automatically, please do not reply
git_url: git://git.openfabrics.org/ofed_1_5/linux-2.6.git
git_branch: ofed_kernel_1_5
Common build parameters:
Passed:
Passed on i686 with linux-2.6.19
Passed on i686 with linux-2.6.18
Passed on i686 with linux-2.6.21.1
Passed on
* Roland Dreier rdre...@cisco.com wrote:
But yeah, I currently don't see a very nice match to perf counters.
OK. It would be nice to tie into something more general, but I think
I agree -- perf counters are missing the filtering and the no lost
events that ummunotify does have. And
When multiple MCMember leave requests are issued the request processors
may run concurrently and then the race between port from multicast group
removing and multicast group deletion (then it becomes empty) is
possible for different processors, as result we are getting double free
crash
Consolidate port addition/removing to multicast groups code and mlid
rerouting requests so that SA MCMember join and leave requests processor
will use just a single call (osm_mgrp_add_port() and
osm_mgrp_remove_port() respectively) to update multicast group related
data and to request (schedule)
On 16:44 Fri 18 Sep , Sasha Khapyorsky wrote:
This patch fixes this by moving multicast group cleanup call under some
lock protected block as port removing code.
Please disregard this patch - it is not against mainstream where problem
exists, but not so trivially fixable. I will fix it in
Merge osm_mcm_port (mgrp's joined ports list) and osm_mcm_info (port's
multicast groups list where port is joined in) structures in a single
one - we need a both equivalently and merging simplifies allocation and
cleanup mechanisms dramatically.
As side effect it also fixes non-member re-join
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
---
diff --git a/opensm/opensm/osm_perfmgr_db.c b/opensm/opensm/osm_perfmgr_db.c
index e5dfc19..329743a 100644
--- a/opensm/opensm/osm_perfmgr_db.c
+++ b/opensm/opensm/osm_perfmgr_db.c
@@ -49,6 +49,8 @@
#include opensm/osm_perfmgr.h
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
---
diff --git a/ibsim/sim_cmd.c b/ibsim/sim_cmd.c
index cb6e639..6d3a893 100644
--- a/ibsim/sim_cmd.c
+++ b/ibsim/sim_cmd.c
@@ -295,7 +295,7 @@ static int do_seterror(FILE * f, char *line)
orig = strsep(s, \);
if
Hi All in the list,
I would like to know if it's possible to configure a linux server with 2
or 3 HCAs, with 2 ports each, so that I can connect 4 or 6 nodes without
using any switch in the middle. If possible, please show an example of the
network configuration.
Please CC me since I'm not
On Mon, Sep 7, 2009 at 5:58 AM, Vladislav Bolkhovitin v...@vlnb.net wrote:
Chris Worley, on 09/06/2009 05:41 PM wrote:
On Sun, Sep 6, 2009 at 3:36 PM, Chris Worleyworl...@gmail.com wrote:
On Sun, Sep 6, 2009 at 3:17 PM, Bart Van Asschebart.vanass...@gmail.com
wrote:
On Fri, Sep 4, 2009 at
On Fri, Sep 18, 2009 at 3:31 PM, Chris Worley worl...@gmail.com wrote:
On Mon, Sep 7, 2009 at 5:58 AM, Vladislav Bolkhovitin v...@vlnb.net wrote:
Chris Worley, on 09/06/2009 05:41 PM wrote:
On Sun, Sep 6, 2009 at 3:36 PM, Chris Worleyworl...@gmail.com wrote:
On Sun, Sep 6, 2009 at 3:17 PM,
On Thu, 17 Sep 2009 23:09:22 -0700
Sean Hefty sean.he...@intel.com wrote:
Although not a fit IMO, the pragmatic solution is to move ib_types,h into
libibumad. I think it is better there than OpenSM which was never quite right
either. That can at least start to eliminate the duplications in
Rough hack. Does windows have stdint.h, byteswap.h, and endian.h?
If not, adding the headers with the needed definitions is trivial.
+/* 16bit */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define CL_NTOH16( x )(uint16_t)( \
+ (((uint16_t)(x) 0x00FF)
On Thu, 27 Aug 2009 12:20:56 -0600
Jason Gunthorpe jguntho...@obsidianresearch.com wrote:
On Thu, Aug 27, 2009 at 09:48:10AM -0700, Ira Weiny wrote:
FSM multiplexing the recv path usually gives much better performance,
something like net discovery is quite easy..
Using the original
On Fri, 18 Sep 2009 15:23:40 -0700
Sean Hefty sean.he...@intel.com wrote:
Rough hack. Does windows have stdint.h, byteswap.h, and endian.h?
If not, adding the headers with the needed definitions is trivial.
+/* 16bit */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define CL_NTOH16( x )
On Fri, Sep 18, 2009 at 03:22:22PM -0700, Ira Weiny wrote:
main()
{
foo = libibnetdisc_setup();
libibnetdisc_discover_all(foo,res);
// Do interesting things with res.
}
That is the current use case. However I can see use cases were discover is
called periodically to get a
On Fri, Sep 18, 2009 at 03:28:48PM -0700, Ira Weiny wrote:
One is for static defines CL_NTOH and the other is for variables at
run time. I found this code in Linux.
Thats gross, and is exactly why you don't do this yourself...
bswap64/32/16 do this all automatically. ntohl also do it and are
On Fri, 18 Sep 2009 17:23:36 -0600
Jason Gunthorpe jguntho...@obsidianresearch.com wrote:
On Fri, Sep 18, 2009 at 03:28:48PM -0700, Ira Weiny wrote:
One is for static defines CL_NTOH and the other is for variables at
run time. I found this code in Linux.
Thats gross, and is exactly why
On Fri, Sep 18, 2009 at 05:05:39PM -0700, Ira Weiny wrote:
I'd say just use the ntohl, ntohs, and bswap64 macros directly and
Window can provide headers with whatever it needs instead. They are
already doing this..
I agree but ntohl etc do not seem to work for the macros which are
20 matches
Mail list logo