On Mon, 20 Dec 2010 13:57:36 -0800
Jay Fenlason wrote:
> Sorry if you get this more than once, I seem to have outgoing mail
> misconfiguration here.
>
> On Wed, Dec 15, 2010 at 11:47:09AM -0800, Ira Weiny wrote:
> >
> > Verify timeout value specified to diagnostics
&
[PATCH] fix rpmbuild with and w/o ibmgtsim build
Signed-off-by: Ira Weiny
---
Makefile.am |2 +-
ibutils.spec.in | 14 ++
2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/Makefile.am b/Makefile.am
index 87b071d..cb13dbd 100644
--- a/Makefile.am
+++ b
[PATCH] Update requirements for building and installing
Signed-off-by: Ira Weiny
---
ibutils.spec.in |3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/ibutils.spec.in b/ibutils.spec.in
index a5d7b76..4209a4c 100644
--- a/ibutils.spec.in
+++ b/ibutils.spec.in
@@ -42,7
From: Ira Weiny
Date: Tue, 25 Jan 2011 17:09:04 -0800
Subject: [PATCH] Add node/port information to some error messages
Signed-off-by: Ira Weiny
---
opensm/opensm/osm_sa_path_record.c | 116 +++
opensm/opensm/osm_ucast_mgr.c |5 +-
2 files changed
From: Ira Weiny
Date: Tue, 25 Jan 2011 17:09:04 -0800
Subject: [PATCH] Add node/port information to some error messages
Signed-off-by: Ira Weiny
---
opensm/opensm/osm_sa_path_record.c | 116 +++
opensm/opensm/osm_ucast_mgr.c |5 +-
2 files changed
On Thu, 27 Jan 2011 13:35:38 -0800
Hal Rosenstock wrote:
> Ira,
>
> On 1/25/2011 8:14 PM, Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Tue, 25 Jan 2011 17:09:04 -0800
> > Subject: [PATCH] Add node/port information to some error messages
>
From: Ira Weiny
Date: Tue, 25 Jan 2011 17:09:04 -0800
Subject: [PATCH] Add node/port/qos information to some error messages
V2: further cleanup of text
include MultiPathRecord messages
add qos information where appropriate
Signed-off-by: Ira Weiny
---
opensm/opensm
> We purposely do not set the PortXmitWait CapabilityMask bit, this
> driver does not implement that capability.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.
From: Ira Weiny
Date: Mon, 14 Feb 2011 15:25:36 -0800
Subject: [PATCH] Fix compile warning introduced by patch "fixed getline pointer
allocation free in osm_console_io"
Signed-off-by: Ira Weiny
---
opensm/osm_console_io.c |1 +
1 files changed, 1 insertions(+), 0 deletion
* fabric)
> /* now, make another pass to see which nodes are part of chassis */
> /* (defined as chassis->nodecount > 1) */
> for (node = fabric->nodes; node; node = node->next) {
> - if (mad_get_field(node->info, 0,
> -
IBPATH=${IBPATH:-@IBSCRIPTPATH@}
>
> diff --git a/scripts/ibstatus b/scripts/ibstatus
> index f7fbbc2..6f01be0 100755
> --- a/scripts/ibstatus
> +++ b/scripts/ibstatus
> @@ -1,4 +1,4 @@
> -#!/bin/sh
> +#!/bin/bash
>
> # Usage ibstatus [devname[:port]]
>
> diff --gi
...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a me
side I think the answer is "yes"
it is pretty easy.
That said getting that hook into sethostname might be harder to get upstream
than just writing the code. I can't comment on that because I don't have any
idea how hard that would be. :-(
Ira
>
> Jason
>
--Original Message-
> From: linux-rdma-ow...@vger.kernel.org
> [mailto:linux-rdma-ow...@vger.kernel.org] On Behalf Of Ira Weiny
> Sent: Tuesday, February 15, 2011 2:07 AM
> To: Tamir Ronen
> Cc: linux-rdma@vger.kernel.org
> Subject: Re: [PATCH] infiniband-diags: add support
if (status != IB_SUCCESS)
OSM_LOG(pm->log, OSM_LOG_ERROR, "ERR 4C14: "
@@ -1163,7 +1304,7 @@ static void pc_recv_process(void *context, void *data)
perfmgr_db_clear_prev_dc(pm->db, node_guid, port);
}
- perfmgr_check_over
out);
+ } else if (strcmp(p_cmd, "clear_redir") == 0) {
+ p_cmd = name_token(p_last);
+ clear_redir(p_osm, p_cmd, out);
} else if (strcmp(p_cmd, "sweep_time") == 0) {
p_cmd = next_token(p_la
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8
lags' '$verbose'
> '$brief' " lid " " port);
> + return system("'$IBPATH'/ibdatacounts '"$ca_info"' '$gflags' '$verbose'
> '$brief' " lid " " port);
> }
>
> /^Ca
For NodeRecord querys in particular if a name was not found all NodeRecords
were printed. Correct behavior is to report "node not found".
Signed-off-by: Ira Weiny
---
src/saquery.c | 27 +++
1 files changed, 19 insertions(+), 8 deletions(-)
diff -
From: Ira Weiny
Date: Wed, 9 Mar 2011 16:28:23 -0800
Subject: [PATCH] opensm/perfmgr: fix overflow processing
The stored error counters need to be cleared when the clear is issued
because of overflow.
Signed-off-by: Ira Weiny
---
opensm/osm_perfmgr.c |1 +
1 files changed, 1
like to get them applied and then
do a refactoring of the code to clean up the queries a bit more (including SL
support if possible.)
Does anyone have objections to this?
Ira
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubs
From: Ira Weiny
Date: Wed, 3 Nov 2010 13:23:23 -0700
Subject: [PATCH] opensm/osm_perfmgr.c: issue ClassPortInfo as first query to
each port.
Signed-off-by: Ira Weiny
---
include/opensm/osm_perfmgr.h |4 +
opensm/osm_perfmgr.c | 229 --
2
From: Ira Weiny
Date: Tue, 8 Mar 2011 13:54:17 -0800
Subject: [PATCH] opensm/perfmgr: clean up: break out redirect processing from
pc_recv_process
Signed-off-by: Ira Weiny
---
opensm/osm_perfmgr.c | 193 +
1 files changed, 98 insertions(+), 95
From: Ira Weiny
Date: Thu, 10 Mar 2011 14:28:10 -0800
Subject: [PATCH] opensm/perfmgr: Issue PortCountersExtended query when supported
Signed-off-by: Ira Weiny
---
include/opensm/osm_perfmgr_db.h |2 +-
opensm/osm_perfmgr.c| 303 ---
opensm
From: Ira Weiny
Date: Mon, 14 Mar 2011 13:18:28 -0700
Subject: [PATCH] opensm/console: add "print all" to print_counters console
command
Signed-off-by: Ira Weiny
---
include/opensm/osm_perfmgr_db.h |1 +
opensm/osm_console.c| 12
opensm/osm
On Mon, 28 Mar 2011 04:22:37 -0700
Hal Rosenstock wrote:
>
> Signed-off-by: Hal Rosenstock
> ---
> Change since v3:
> Yet another config change to try to fix formatting
> Change since v2:
> Another config change to try to fix formatting
> Change since v1:
> Hopefully fix formatting problem afte
On Fri, 25 Mar 2011 12:23:22 -0700
Hal Rosenstock wrote:
>
> Signed-off-by: Hal Rosenstock
> ---
> libibmad/include/infiniband/mad.h | 15 +++
> libibmad/src/fields.c | 12
> 2 files changed, 27 insertions(+), 0 deletions(-)
Thanks, applied,
Ira
--
On Fri, 25 Mar 2011 12:23:31 -0700
Hal Rosenstock wrote:
>
> Signed-off-by: Hal Rosenstock
> ---
> infiniband-diags/man/saquery.8 |3 +-
> infiniband-diags/src/saquery.c | 48
> +++-
> 2 files changed, 49 insertions(+), 2 deletions(-)
Thanks, appl
Subject: [PATCH 1/3] infiniband-diags: saquery, exit with ENODEV when queries
fail to find results
Signed-off-by: Ira Weiny
---
src/saquery.c | 29 +++--
1 files changed, 23 insertions(+), 6 deletions(-)
diff --git a/src/saquery.c b/src/saquery.c
index 03869e3
Subject: [PATCH 2/3] infiniband-diags: saquery, properly free mad when no
results are found
Signed-off-by: Ira Weiny
---
src/saquery.c |8 ++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/src/saquery.c b/src/saquery.c
index d7c8e6f..9314e4f 100644
--- a/src
Subject: [PATCH 3/3] infiniband-diags: saquery, clean up error code/return types
Signed-off-by: Ira Weiny
---
src/saquery.c | 34 ++
1 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/src/saquery.c b/src/saquery.c
index 9314e4f..e3304a6 100644
quot; in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send t
d, 0, rcvbuf);
> + return mad_rpc(srcport, &rpc, portid, rcvbuf, rcvbuf);
> }
>
> uint8_t *smp_query(void *rcvbuf, ib_portid_t * portid, unsigned attrid,
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to major
trid,
> +unsigned mod, unsigned timeout,
> +const struct ibmad_port * srcport)
> +{
> + return smp_query_status_via(rcvbuf, portid, attrid, mod, timeout, NULL,
> + srcport);
> }
>
> uint8_t *smp_query(void *rcvbuf, ib_portid_t * portid, unsigned attrid,
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
s in the past. Bump the
version and run with that until the official branch/tag.
Ira
>
> Jason
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma&quo
.
>
> This patch stands on it's own and should've been just [PATCH] and not
> [PATCH 4/4]. It was my mistake when I generated/sent these patches.
No problem.
Thanks applied,
Ira
>
> -- Hal
>
> > Signed-off-by: Aviad Yehezkel
> > Signed-off-by: Hal Rosenst
On Sat, 9 Apr 2011 05:04:22 -0700
Hal Rosenstock wrote:
> On 4/8/2011 4:45 PM, Ira Weiny wrote:
> >
> > Subject: [PATCH 1/3] infiniband-diags: saquery, exit with ENODEV when
> > queries fail to find results
>
> 0 records is a perfectly valid response to a GetTable
Subject: [PATCH] opensm: perfmgr, only set orig_lid when we have a valid port.
Otherwise leave it as 0
Signed-off-by: Ira Weiny
---
opensm/osm_perfmgr.c |4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/opensm/osm_perfmgr.c b/opensm/osm_perfmgr.c
index 6a1fa63
Subject: [PATCH] opensm: fix strtoull error handling
The man page states that errno _may_ be returned when the string can not be
converted. Check that the entire string was consumed otherwise assume this is
not a guid.
Signed-off-by: Ira Weiny
---
opensm/osm_perfmgr.c |5 +++--
1 files
On Mon, 18 Apr 2011 05:42:56 -0700
Hal Rosenstock wrote:
> On 4/17/2011 9:26 PM, Weiny, Ira K. wrote:
> > On Apr 17, 2011, at 8:21 AM, Hal Rosenstock wrote:
> >
> >> On 4/15/2011 6:17 PM, Ira Weiny wrote:
> >>>
[snip]
> >>
> >> There
From: Ira Weiny
Date: Tue, 26 Apr 2011 17:35:38 -0700
Subject: [PATCH] opensm: ib_types.h add defines for PM CPI SamplesOnlySupported
and PortCountersXmitWaitSupported
Per IBTA v1.2.1 section 16.1.3.1
Signed-off-by: Ira Weiny
---
include/iba/ib_types.h |2 ++
1 files changed, 2
From: Ira Weiny
Date: Wed, 27 Apr 2011 10:08:03 -0700
Subject: [PATCH] infiniband-diags: fix "dist" target and subsequent rpm building
Signed-off-by: Ira Weiny
---
libibnetdisc/Makefile.am |3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/libibnetdisc/Mak
gt; + if (sysimgguid ||
> + (group && node->chassis && node->chassis->chassisnum))
> + fprintf(f, "\n");
> }
>
> uint64_t out_chassis(ibnd_fabric_t * fabric, unsigned char chassisnum)
--
Ira Weiny
Math Programmer/Comput
be linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send
The following 5 patches extend the functionality of ibqueryerrors to cover
some of the functionality of the ib* bash scripts.
ibqueryerrors has been our workhorse for fabric monitoring here at LLNL.
While I am working on better performance management in OpenSM this provides a
scalable "direct" opt
From: Ira Weiny
Date: Wed, 27 Apr 2011 10:43:01 -0700
Subject: [PATCH 01/5] infiniband-diags: ibqueryerrors; add error thresholds
Signed-off-by: Ira Weiny
---
Makefile.am|3 +-
configure.in | 10 -
etc/error_thresholds | 16 ++
man/ibqueryerrors.8
From: Ira Weiny
Date: Mon, 25 Apr 2011 12:39:12 -0700
Subject: [PATCH 02/5] infiniband-diags: ibqueryerrors; add ibcheckerrors like
summary
ibcheckerrors reports a summary of nodes checked, node errors, port checked, and
port errors. Track and print same as a summary.
Signed-off-by: Ira
From: Ira Weiny
Date: Tue, 26 Apr 2011 22:18:27 -0700
Subject: [PATCH 03/5] infiniband-diags: ibqueryerrors; use #defines for
CapabilityMask
Signed-off-by: Ira Weiny
---
include/ibdiag_common.h |6 ++
src/ibqueryerrors.c |8
2 files changed, 10 insertions(+), 4
From: Ira Weiny
Date: Tue, 26 Apr 2011 22:59:15 -0700
Subject: [PATCH 04/5] infiniband-diags: ibqueryerrors --data; show/clear
PortCountersExtended when supported
Signed-off-by: Ira Weiny
---
src/ibqueryerrors.c | 88 ++
1 files changed, 81
From: Ira Weiny
Date: Wed, 27 Apr 2011 01:07:59 -0700
Subject: [PATCH 05/5] infiniband-diags: ibqueryerrors; add --counters option
Display the data counters (optionally extended data counters) for all ports in
the fabric.
Signed-off-by: Ira Weiny
---
src/ibqueryerrors.c | 139
On Thu, 28 Apr 2011 07:46:10 -0700
Hal Rosenstock wrote:
> On 4/27/2011 9:46 PM, Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Tue, 26 Apr 2011 22:59:15 -0700
> > Subject: [PATCH 04/5] infiniband-diags: ibqueryerrors --data; show/clear
> > Po
eptable to everyone?
Oh yes, I was just codeing along and added the define where the others were. I
would very much like the diags to not depend on opensm. Please do resubmit
your patches.
For now I am going to accept this patch which will mark perfquery as something
which needs to transition.
_mask & 0x1000))
> + if (argc <= 2 && !extended && (cap_mask & IB_PM_PC_XMIT_WAIT_SUP))
> mask |= (1 << 16); /* reset portxmitwait */
>
> if (all_ports_loop || (loop_ports && (all_ports || port == ALL_PORTS)
; + rpc.mgtclass = IB_PERFORMANCE_CLASS | IB_MAD_RPC_VERSION1;
> rpc.method = IB_MAD_METHOD_SET;
> rpc.attr.id = id;
>
> @@ -115,5 +124,7 @@ uint8_t *performance_reset_via(void *rcvbuf, ib_portid_t
> * dest,
> if (!dest->qkey)
> dest->q
eturn mad_send_via(rpcold, portid, 0, data, srcport) < 0 ? 0 : data;
> /* FIXME: no RMPP for now */
> }
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at
failed; dport (%s)", portid2str(dport));
> return NULL;
> }
>
> + if ((rpc->mgtclass & IB_MAD_RPC_VERSION_MASK) == IB_MAD_RPC_VERSION1)
> + rpcv1->error = error;
> +
> mad = umad_get_mad(rcvbuf);
>
> if
From: Ira Weiny
Date: Tue, 26 Apr 2011 22:59:15 -0700
Subject: [PATCH 04/5 V2] infiniband-diags: ibqueryerrors --data; show/clear
PortCountersExtended when supported
Chages in V2:
Only print/clear Unicast/Multicast fields when IsExtendedWidthSupported is
indicated.
Signed-off-by: Ira Weiny
From: Ira Weiny
Date: Wed, 27 Apr 2011 01:07:59 -0700
Subject: [PATCH 05/5 V2] infiniband-diags: ibqueryerrors; add --counters option
Display the data counters (optionally extended data counters) for all ports in
the fabric.
Chages in V2:
Only print Unicast/Multicast fields when
gt; >> --- a/src/vendstat.c
> >> +++ b/src/vendstat.c
> >> @@ -375,6 +375,7 @@ int main(int argc, char **argv)
> >>gi = (is3_general_info_t *) & buf;
> >>if (do_vendor(&portid, srcport, IB_MLX_VENDOR_CLASS, IB_MAD_METHOD_GET,
> >>
Signed-off-by: Sean Hefty
Acked-by: Ira Weiny
> ---
> This patch was originally submitted as patch 2 of the AF_IB patch set;
> however, it will also be used by the REUSEADDR support for patch 2/2.
>
> drivers/infiniband/core/cma.c | 29 ++---
> 1 f
bound to that same
> address. The reuse option is exported to user space. The behavior
> of the kernel reuse implementation was verified against that given
> by sockets.
>
> This patch is derived from a path by: Ira Weiny
>
> Signed-off-by: Sean Hefty
Signed-off
tre on clusters larger than 1024 nodes.
>
> Signed-off-by: Sean Hefty
Acked-by: Ira Weiny
> ---
> include/rdma/rdma_cma.h |5 +++--
> 1 files changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/include/rdma/rdma_cma.h b/include/rdma/rdma_cma.h
> index b48cd2e..
}
> port->guid =
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Ira Weiny
Math Programmer/
From: Ira Weiny
Date: Thu, 12 May 2011 17:31:15 -0700
Subject: [PATCH 1/2] infiniband-diags: perfquery; print cap_mask for information
Also fix cap_mask endianess in error print
Signed-off-by: Ira Weiny
---
src/perfquery.c | 32 +++-
1 files changed, 19
From: Ira Weiny
Date: Fri, 13 May 2011 22:28:55 -0700
Subject: [PATCH 2/2] infiniband-diags: perfquery; Support
PortCountersExtendedNoIETF
Signed-off-by: Ira Weiny
---
src/perfquery.c | 52
1 files changed, 32 insertions(+), 20 deletions
On Wed, 25 May 2011 05:30:20 -0700
Hal Rosenstock wrote:
> On 5/24/2011 5:42 PM, Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Fri, 13 May 2011 22:28:55 -0700
> > Subject: [PATCH 2/2] infiniband-diags: perfquery; Support
> > PortCountersExtendedNoIETF
From: Ira Weiny
Date: Fri, 13 May 2011 22:28:55 -0700
Subject: [PATCH 2/2] infiniband-diags: perfquery; Support
PortCountersExtendedNoIETF
Changes since V1:
fix typo
if (cap_mask & IB_PM_EXT_WIDTH_NOIETF_SUP) {
to
if (cap_mask & IB_PM_EXT_WIDTH_SUPPORTED) {
Signed-off-by: I
On Wed, 25 May 2011 11:18:52 -0700
Hal Rosenstock wrote:
> On 5/25/2011 12:50 PM, Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Fri, 13 May 2011 22:28:55 -0700
> > Subject: [PATCH 2/2] infiniband-diags: perfquery; Support
> > PortCountersExtendedNoIETF
&
2`"
> +IBSCRIPTPATH="${with_ibpath_override:-`eval echo $IBSCRIPTPATH_TMP2`}"
> AC_SUBST(IBSCRIPTPATH)
>
> dnl Begin libibnetdisc stuff
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe
- 1)
> +
> static inline const char *ib_sa_err_str(IN uint8_t status)
> {
> if (status > SA_ERR_UNKNOWN)
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "un
ASS)
> + if (class < 1 || class >= MAX_CLASS)
> return -1;
> return port->class_agents[class];
> }
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send
t; sizeof(path->p) - 1)
> + if (path->cnt > sizeof(path->p) - 2)
> return -1;
> ++path->cnt;
> path->p[path->cnt] = (uint8_t) nextport;
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei.
zeof(ibnd_port_t));
> if (!port) {
> IBND_DEBUG("OOM: port\n");
> + free(port_cache);
> return -1;
> }
> memset(port, '\0', sizeof(ibnd_port_t));
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National
gt;
> - mad_dump_portstates(buf, sizeof buf, data, sizeof data);
> + mad_dump_portstates(buf, sizeof buf, data, sizeof *data);
> mad_decode_field(data, IB_PORT_LID_F, val);
> mad_dump_field(IB_PORT_LID_F, buf + strlen(buf),
> sizeof buf - strlen(b
,
Ira
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kerne
s;
> > + __be64 port_rcv_packets;
> > + __be64 port_unicast_xmit_packets;
> > + __be64 port_unicast_rcv_packets;
> > + __be64 port_multicast_xmit_packets;
> > + __be64 port_multicast_rcv_packets;
> > +} __attribute__ ((packed));
> > +
> > +#define
ying patches and building custom kernels.
FYI,
http://jira.whamcloud.com/browse/LU-20
Ira
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kern
bcheckportspeed.in | 146
> > ++
> > infiniband-diags/scripts/ibcheckportwidth.in |2 +-
> > infiniband-diags/scripts/ibcheckspeed.in | 135
> >
> > 3 files changed, 282 insertions(+), 1 deletions(-)
> >
ust to be clear, the examples below are running in a cluster which I "forced"
to SDR using OpenSM's "force_link_speed" option. This just happened to be the
easiest way for me to show you the output of a link which is running at
sub-optimal speeds.
Ira
>
> -- Hal
f links at 1, 4, or 12X. I then leave it up to the sys
admin to know if their cluster is homo or heterogenious and how many links
should be at what speeds. They can then use iblinkinfo to identify which links
are incorrect for their particular installation.
Ira
>
> -
> Keshetti Mahe
/iblinkinfo -l | grep Disable
real0m3.041s
user0m0.026s
sys 0m0.039s
Eli, If you have data for this being slow on a larger cluster I would be
interested to know.
Ira
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscrib
From: Ira Weiny
Date: Wed, 23 Sep 2009 14:26:55 -0700
Subject: [PATCH] infiniband-diags/src/ibqueryerrors.c: fix bug when attempting
a sub-fabric scan
Also ibd_sm_id is never valid in this tool as the "-s" option is used
for "suppress"
Signed-off-by: Ira We
From: Ira Weiny
Date: Wed, 23 Sep 2009 11:38:11 -0700
Subject: [PATCH] infiniband-diags/src/ibqueryerrors.c: Remove --all option and
replace it with --switch, --ca, --router
By default ibqueryerrors should print errors for all node types.
Adding the other options allows for the
dist = 0; dist <= max_hops; dist++) {
>
> --
> 1.5.5
>
> ___
> general mailing list
> gene...@lists.openfabrics.org
> http://*lists.openfabrics.org/cgi-bin/mailman/listinfo/general
>
> To unsubscribe, please visit
> http://*openib.org/mailman/listinfo/openib-general
>
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
wei...@llnl.gov
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, 29 Sep 2009 17:41:45 +0200
Sasha Khapyorsky wrote:
> On 14:45 Wed 23 Sep , Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Wed, 23 Sep 2009 14:26:55 -0700
> > Subject: [PATCH] infiniband-diags/src/ibqueryerrors.c: fix bug when
> > attempting a
On Tue, 29 Sep 2009 17:49:49 +0200
Sasha Khapyorsky wrote:
> Hi Ira,
>
> On 15:09 Wed 23 Sep , Ira Weiny wrote:
> >
> > From: Ira Weiny
> > Date: Wed, 23 Sep 2009 11:38:11 -0700
> > Subject: [PATCH] infiniband-diags/src/ibqueryerrors.c: Remove --al
On Tue, 29 Sep 2009 18:16:21 +0200
"Eli Dorfman (Voltaire)" wrote:
> Ira Weiny wrote:
> > Eli,
> >
> > On Wed, 26 Aug 2009 17:37:30 +0300
> > "Eli Dorfman (Voltaire)" wrote:
> >
> >> Subject: [PATCH] Fix IB network discovery fro
The only difference is that this now applies to the current master.
There were a couple of changes you made to the previous patches I submitted so
I thought I would make it easy on you and send a version which applies cleanly.
Thanks,
Ira
From: Ira Weiny
Date: Thu, 24 Sep 2009 20:39:29 -0700
On Fri, 25 Sep 2009 16:09:08 +0300
Sasha Khapyorsky wrote:
> On 13:20 Thu 17 Sep , Ira Weiny wrote:
> >
> > Sasha, would you be willing to accept such a patch? First move ib_types.h
> > to umad and then move the long inline functions into the lib and separate
> &g
On Wed, 30 Sep 2009 20:57:52 -0600
Jason Gunthorpe wrote:
> On Wed, Sep 30, 2009 at 06:31:26PM -0700, Ira Weiny wrote:
>
> > > Now I likely would agree with Ira that moving ib_types.h to libibumad
> > > is a least painful option. Do we have a better ideas?
> >
&g
sion has digressed. But I don't think we should dive
into breaking up (or moving) ib_types just to move things around. I think
Sasha is right we need to have a plan for where things _should_ end up. As I
look for homes for all the items of ib_types I find that it is not just one
place. :-
On Thu, 1 Oct 2009 17:39:15 -0600
Jason Gunthorpe wrote:
> On Thu, Oct 01, 2009 at 03:50:07PM -0700, Ira Weiny wrote:
> > On Wed, 30 Sep 2009 20:57:52 -0600
> > Jason Gunthorpe wrote:
> >
> > > On Wed, Sep 30, 2009 at 06:31:26PM -0700, Ira Weiny wrote:
> > &
o have the SM send these Set's. Perhaps there is broken hardware out
there?
Ira
>
> Thanks,
> Eli
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at h
Sasha,
Perhaps you missed this patch the first time around. Eli, verified that it
worked for him on the switch as well as works for me. This applies to current
master as is.
Eli, I added you as signing off on this.
Thanks guys,
Ira
From: Ira Weiny
Date: Tue, 22 Sep 2009 11:08:28 -0700
On Mon, 12 Oct 2009 11:47:37 +0200
"Eli Dorfman (Voltaire)" wrote:
> Ira Weiny wrote:
> > On Tue, 06 Oct 2009 17:56:01 +0200
> > "Eli Dorfman (Voltaire)" wrote:
> >
> >> Hi,
> >>
> >> Is there a reason for setting default forc
On Tue, 13 Oct 2009 09:39:08 -0400
Hal Rosenstock wrote:
> On Mon, Oct 12, 2009 at 5:35 PM, Ira Weiny wrote:
> > On Mon, 12 Oct 2009 11:47:37 +0200
> > "Eli Dorfman (Voltaire)" wrote:
> >
> >> Ira Weiny wrote:
> >> > On Tue, 06 Oct 2009 1
From: Ira Weiny
Date: Wed, 14 Oct 2009 17:05:53 -0700
Subject: [PATCH] opensm/opensm/osm_subnet.c: adjust buffer to ensure a '\n' is
printed
When printing cached options strings which fill the print buffer.
Adjust the length so the final snprintf(..., "\n
Sasha,
Hal caught that I am not freeing the force_link_speed_except_guids on shutdown.
V2 coming shortly.
Ira
On Thu, 15 Oct 2009 13:26:50 -0700
Ira Weiny wrote:
>
> From: Ira Weiny
> Date: Wed, 14 Oct 2009 16:09:25 -0700
> Subject: [PATCH] opensm: add force_link_speed_file c
From: Ira Weiny
Date: Wed, 14 Oct 2009 16:09:25 -0700
Subject: [PATCH] opensm: add force_link_speed_file config option.
From the config file help:
# Optional file used to override individual port GUIDs and speeds to be
forced.
# Port GUIDs which are _not_ listed in
From: Ira Weiny
Date: Wed, 14 Oct 2009 16:09:25 -0700
Subject: [PATCH] opensm: add force_link_speed_file config option.
From the config file help:
# Optional file used to override individual port GUIDs and speeds to be
forced.
# Port GUIDs which are _not_ listed in
701 - 800 of 1033 matches
Mail list logo
