[PATCH 01/14] IB/mad cleanup: Clean up function params -- find_mad_agent

2015-06-06 Thread ira . weiny
From: Ira Weiny find_mad_agent only needs read only access to the MAD header. Update the ib_mad pointer to be const ib_mad_hdr. Adjust call tree. Signed-off-by: Ira Weiny --- drivers/infiniband/core/mad.c | 36 ++-- 1 file changed, 18 insertions(+), 18

[PATCH 08/14] IB/core: Add ability for drivers to report an alternate MAD size.

2015-06-06 Thread ira . weiny
From: Ira Weiny Add max MAD size to the device immutable data set and have all drivers that support MADs report the current IB MAD size (IB_MGMT_MAD_SIZE) to the core. Verify MAD size data in both the MAD core and when reading the immutable data. OPA drivers will report alternate MAD sizes in

[PATCH 04/14] IB/mad: Create a generic helper for DR SMP Send processing

2015-06-06 Thread ira . weiny
From: Ira Weiny IB and OPA SMPs share the same processing algorithm but have different header formats and permissive LID detection. Add a helper function which is generic to processing DR SMP Send messages which can be used by both IB and OPA SMP code. Use this function in the current IB

[PATCH 06/14] IB/mad: Create a generic helper for DR forwarding checks

2015-06-06 Thread ira . weiny
From: Ira Weiny IB and OPA SMPs share the same processing algorithm but have different header formats and permissive LID detection. Add a helper function which is generic to processing the DR forwarding checks which can be used by both IB and OPA SMP code. Use this function in the current IB

[PATCH 05/14] IB/mad: Create a generic helper for DR SMP Recv processing

2015-06-06 Thread ira . weiny
From: Ira Weiny IB and OPA SMPs share the same processing algorithm but have different header formats and permissive LID detection. Add a helper function which is generic to processing DR SMP Recv messages which can be used by both IB and OPA SMP code. Use this function in the current IB

[PATCH 11/14] IB/core: Add OPA MAD core capability flag

2015-06-06 Thread ira . weiny
From: Ira Weiny Add OPA MAD support flags to the core capability immutable flags. In addition add the rdma_cap_opa_mad helper function for core functions to use to detect OPA MAD support. OPA MADs share a common header with IBTA MADs but with some differences for increased performance

[PATCH 13/14] IB/mad: Add partial Intel OPA MAD support

2015-06-06 Thread ira . weiny
From: Ira Weiny Add OPA SMP processing functionality. Define the new OPA SMP format, create support functions for this format using the previously defined helper functions as appropriate. These functions are defined in this patch and used in the final OPA MAD support patch. Signed-off-by: Ira

[PATCH 14/14] IB/mad: Add final OPA MAD processing

2015-06-06 Thread ira . weiny
From: Ira Weiny For devices which support OPA MADs 1) Use previously defined SMP support functions. 2) Pass correct base version to ib_create_send_mad when processing OPA MADs. 3) Process out_mad_key_index returned by agents for a response. This is necessary because OPA SMP

[PATCH 12/14] IB/mad: Add partial Intel OPA MAD support

2015-06-06 Thread ira . weiny
From: Ira Weiny This patch is the first of 3 which adds processing of OPA MADs 1) Add Intel Omni-Path Architecture defines 2) Increase max management version to accommodate OPA 3) update ib_create_send_mad If the device supports OPA MADs and the MAD being sent is the OPA base

[PATCH 09/14] IB/mad: Convert allocations from kmem_cache to kzalloc

2015-06-06 Thread ira . weiny
From: Ira Weiny This patch implements allocating alternate receive MAD buffers within the MAD stack. Support for OPA to send/recv variable sized MADs is implemented later. 1) Convert MAD allocations from kmem_cache to kzalloc kzalloc is more flexible to support devices with

[PATCH 10/14] IB/mad: Add support for additional MAD info to/from drivers

2015-06-06 Thread ira . weiny
From: Ira Weiny In order to support alternate sized MADs (and variable sized MADs on OPA devices) add in/out MAD size parameters to the process_mad core call. In addition, add an out_mad_pkey_index to communicate the pkey index the driver wishes the MAD stack to use when sending OPA MAD

[PATCH 02/14] IB/mad cleanup: Generalize processing of MAD data

2015-06-06 Thread ira . weiny
From: Ira Weiny ib_find_send_mad only needs access to the MAD header not the full IB MAD. Change the local variable to ib_mad_hdr and change the corresponding cast. This allows for clean usage of this function with both IB and OPA MADs because OPA MADs carry the same header as IB MADs. Signed

[PATCH 07/14] IB/mad: Support alternate Base Versions when creating MADs

2015-06-06 Thread ira . weiny
From: Ira Weiny In preparation to support the new OPA MAD Base version, add a base version parameter to ib_create_send_mad and set it to IB_MGMT_BASE_VERSION for current users. Definition of the new base version and it's processing will occur in later patches. Signed-off-by: Ira

Re: [PATCH v7 5/6] xprtrdma, svcrdma: Switch to generic logging helpers

2015-06-08 Thread ira. weiny
On Mon, Jun 08, 2015 at 11:15:04AM +0300, Sagi Grimberg wrote: > On 6/7/2015 9:00 AM, ira.weiny wrote: > >>@@ -201,9 +202,10 @@ static void qp_event_handler(struct ib_event *event, > >>void *context) > >>case IB_EVENT_QP_ACCESS_ERR: > >>case IB_EVENT_DEVICE_FATAL: > >>default: > >>-

[RESEND PATCH v3 14/14] IB/mad: Add final OPA MAD processing

2015-06-10 Thread ira . weiny
From: Ira Weiny For devices which support OPA MADs 1) Use previously defined SMP support functions. 2) Pass correct base version to ib_create_send_mad when processing OPA MADs. 3) Process out_mad_key_index returned by agents for a response. This is necessary because OPA SMP

Re: [PATCH] opensm/mcast_tbl: set max_mlid_ho as actually configured mlid

2009-10-29 Thread Ira Weiny
p_tbl->mft_depth = mft_depth; > - p_tbl->max_mlid_ho = mft_depth + IB_LID_MCAST_START_HO - 1; > +done: > + p_tbl->max_mlid_ho = mlid_offset + IB_LID_MCAST_START_HO - 1; > return 0; > } > > -- > 1.6.5.1 > > -- > To unsubscribe from this list:

Re: [PATCH] opensm/mcast_tbl: set max_mlid_ho as actually configured mlid

2009-10-29 Thread Ira Weiny
On Fri, 30 Oct 2009 01:02:46 +0200 Sasha Khapyorsky wrote: > Hi Ira, > > Thanks for reporting. > > On 15:44 Thu 29 Oct , Ira Weiny wrote: > > > > OpenSM $ mlid_ho 49152; p_tbl->max_mlid_ho 49152 > > mlid_ho 49154; p_tbl->max_mlid_ho 49153 > > o

Re: [PATCH] opensm/osm_mcast_tbl.c: Fix multicast group removal

2009-10-30 Thread Ira Weiny
> > if (p_tbl->p_mask_tbl && mlid_ho <= p_tbl->max_mlid_ho) { > mlid_offset = mlid_ho - IB_LID_MCAST_START_HO; > + if (mlid_offset >= p_tbl->mft_depth) > + return; > for (i = 0; i <= p_tbl->max_positio

Re: [PATCH] opensm/osm_mcast_tbl.c: Fix multicast group removal

2009-10-30 Thread Ira Weiny
perhaps that should have been +1? Not really thinking today either... ;-) Ira On Fri, 30 Oct 2009 10:26:49 -0700 Ira Weiny wrote: > This patch causes this assert again... > > OpenSM $ opensm: osm_mcast_tbl.c:104: osm_mcast_tbl_set: Assertion `mlid_ho > <= p_tbl->m

Re: [PATCH] infiniband-diags/ibqueryerrors: Fix realloc size to prevent core

2009-11-03 Thread Ira Weiny
gned for any kind of variable and may be different from ptr, > > or NULL if the request fails. > > --- > > > > Al > > > > On Tue, 2009-11-03 at 13:20 -0800, Ira Weiny wrote: > > > From: Ira Weiny > > > Date: Tue, 3 Nov 2009 13:19:33 -0800 > &g

Re: [PATCH V2] infiniband-diags/ibqueryerrors: Fix realloc size to prevent core

2009-11-03 Thread Ira Weiny
On Tue, 03 Nov 2009 13:39:22 -0800 Al Chu wrote: > Need to check for NULL? Manpage says its possible: Good idea; V2 below, Ira From: Ira Weiny Date: Tue, 3 Nov 2009 13:19:33 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Fix realloc size to prevent core Realloc size

[PATCH] infiniband-diags/ibqueryerrors: Fix realloc size to prevent core

2009-11-03 Thread Ira Weiny
From: Ira Weiny Date: Tue, 3 Nov 2009 13:19:33 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Fix realloc size to prevent core Realloc size was wrong causing a core when enough errors were suppressed. Reproduced by running: ibqueryerrors -c -s

[PATCH] infiniband-diags/ibqueryerrors: Fix remote node name printing

2009-11-03 Thread Ira Weiny
From: Ira Weiny Date: Tue, 3 Nov 2009 19:51:32 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Fix remote node name printing "-r" option was reporting the current node name, not the remote node name of the port as it should have been. Signed-off-by:

[PATCH 1/2] infiniband-diags/ibqueryerrors: Change realloc of suppressed fields to a static array

2009-11-03 Thread Ira Weiny
Sasha, 2 clean up patches which apply in order. Ira From: Ira Weiny Date: Tue, 3 Nov 2009 13:19:33 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Change realloc of suppressed fields to a static array Realloc size was wrong causing a core when enough errors were

[PATCH 2/2] infiniband-diags/ibqueryerrors: Properly exit and clean up resources when node info query fails

2009-11-03 Thread Ira Weiny
From: Ira Weiny Date: Tue, 3 Nov 2009 20:17:14 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Properly exit and clean up resources when node info query fails Signed-off-by: Ira Weiny --- infiniband-diags/src/ibqueryerrors.c |7 +-- 1 files changed, 5 insertions(+), 2

[PATCH] infiniband-diags/ibnetdisc.h: Clarify "ports" member of ibnd_node_t with more descriptive comment

2009-11-05 Thread Ira Weiny
From: Ira Weiny Date: Tue, 3 Nov 2009 17:03:15 -0800 Subject: [PATCH] infiniband-diags/ibnetdisc.h: Clarify "ports" member of ibnd_node_t with more descriptive comment Signed-off-by: Ira Weiny --- .../libibnetdisc/include/infiniband/ibnetdisc.h| 11 --- 1 files

[PATCH] OpenSM: Fix unused variable compiler warning.

2009-11-10 Thread Ira Weiny
From: Ira Weiny Date: Tue, 10 Nov 2009 10:39:47 -0800 Subject: [PATCH] OpenSM: Fix unused variable compiler warning. Signed-off-by: Ira Weiny --- opensm/opensm/osm_mcast_tbl.c |1 - 1 files changed, 0 insertions(+), 1 deletions(-) diff --git a/opensm/opensm/osm_mcast_tbl.c b/opensm

[PATCH 2/2] infiniband-diags/libibnetdisc: Remove nearly duplicate "get_node_info" function

2009-11-10 Thread Ira Weiny
From: Ira Weiny Date: Tue, 10 Nov 2009 13:51:41 -0800 Subject: [PATCH] infiniband-diags/libibnetdisc: Remove nearly duplicate "get_node_info" function Fold remaining functionality into "query_port_info" Signed-off-by: Ira Weiny --- infiniband-diags/libibnet

[PATCH 1/2] infiniband-diags/libibnetdisc: clean up PortInfo queries

2009-11-10 Thread Ira Weiny
et_port_info" function as it became nearly redundant with query_port_info. Ira From: Ira Weiny Date: Tue, 10 Nov 2009 11:22:03 -0800 Subject: [PATCH] infiniband-diags/libibnetdisc: clean up PortInfo queries remove old "decode_port_info" and replace with new &qu

Re: [PATCH 1/2] infiniband-diags/libibnetdisc: clean up PortInfo queries

2009-11-10 Thread Ira Weiny
Sorry, I clicked "send" on patch 2/2 first so they came out of order... I think you will get the idea... ;-) Ira On Tue, 10 Nov 2009 14:01:37 -0800 Ira Weiny wrote: > Sasha, > > This and the subsequent patch clean up the port info query code to be more > straight for

[PATCH] infiniband-diags/ibqueryerrors: Reformat the output of the xmtdiscard details.

2009-11-10 Thread Ira Weiny
From: Ira Weiny Date: Tue, 3 Nov 2009 13:58:03 -0800 Subject: [PATCH] infiniband-diags/ibqueryerrors: Reformat the output of the xmtdiscard details. Old: Errors for 0x2c9020040fec8 "Infiniscale-IV Mellanox Technologies" GUID 0x2c9020040fec8 port 27: [XmtDiscards ==

Re: [infiniband-diags] [PATCH] [2/2] split out scan specific data from ibnd_node_t

2009-11-12 Thread Ira Weiny
formation about nodes, links, ports, errors, data counters, routing tables, etc. without making him use the MAD layer, or worse yet, umad layer. In this use case he does not care that libibnetdisc does a BFS and creates a nodesdist structure of some sort resulting from that algorithm. Presentin

[PATCH] libibmad: libibumad: Print warnings and errors to stderr not stdout

2009-11-17 Thread Ira Weiny
From: Ira Weiny Date: Tue, 17 Nov 2009 14:39:37 -0800 Subject: [PATCH] libibmad: libibumad: Print warnings and errors to stderr not stdout Signed-off-by: Ira Weiny --- libibmad/include/infiniband/mad.h |4 ++-- libibumad/src/umad.c |2 +- 2 files changed, 3 insertions

Re: [PATCH] infiniband-diags/ibportstate: allow changes to CA portinfo parameters

2009-12-01 Thread Ira Weiny
== 4) { /* Set speed */ > > + mad_set_field(data, 0, IB_PORT_PHYS_STATE_F, 3); > > + break; > > + case DOWN: > > + mad_set_field(data, 0, IB_PORT_STATE_F, 1); > > + break; > > +

SRP issues with OpenSM 3.3.3

2009-12-14 Thread Ira Weiny
d_points if we are heading through a router? I don't think it matters if we are going through a router or not does it? If not, I think the comment needs to be removed in the patch above. Thanks, Ira -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore National Lab 925-423-

Re: SRP issues with OpenSM 3.3.3

2009-12-15 Thread Ira Weiny
On Tue, 15 Dec 2009 10:16:42 -0500 Hal Rosenstock wrote: > Ira, > > On Mon, Dec 14, 2009 at 7:43 PM, Ira Weiny wrote: > > Sasha, Hal, > > > > I have found that the following patch caused our SRP connected storage to > > break. > > What is causing the SR

Re: SRP issues with OpenSM 3.3.3

2009-12-15 Thread Ira Weiny
On Tue, 15 Dec 2009 19:03:17 +0200 Sasha Khapyorsky wrote: > Hi Ira, > > On 16:43 Mon 14 Dec , Ira Weiny wrote: > > > > I have found that the following patch caused our SRP connected storage to > > break. > > > > patch: 3d20f82edd3246879063b

Re: SRP issues with OpenSM 3.3.3

2009-12-15 Thread Ira Weiny
c somewhere? The follow on would be that if they specify a DGID in the PathRecord query and the result is subnet local they must still use a GRH even if the packet is going to stay local? I think this makes sense but I wonder if __everyone__ is following that? Ira > > Jason -- Ira W

Re: SRP issues with OpenSM 3.3.3

2009-12-15 Thread Ira Weiny
> hop limit to 0 unless the DLID was a router port. Ok, then I think we need a new way to tell if we are hitting a router port in pr_rcv_build_pr. I don't think having a non-zero GID is the definition of going through a router port. Ira > > Jason -- Ira Weiny Math Programmer/Comput

[RFC PATCH] Set HopLimit based on off subnet Re: SRP issues with OpenSM 3.3.3

2009-12-15 Thread Ira Weiny
On Tue, 15 Dec 2009 12:59:11 -0500 Hal Rosenstock wrote: > On Tue, Dec 15, 2009 at 12:18 PM, Ira Weiny wrote: [snip] > > > The follow on would be that if they specify a > > DGID in the PathRecord query and the result is subnet local they must still > > use a GRH eve

Re: [RFC PATCH] Set HopLimit based on off subnet Re: SRP issues with OpenSM 3.3.3

2009-12-17 Thread Ira Weiny
On Wed, 16 Dec 2009 08:29:43 -0500 Hal Rosenstock wrote: > On Tue, Dec 15, 2009 at 9:55 PM, Ira Weiny wrote: [snip] > > > > diff --git a/opensm/opensm/osm_sa_path_record.c > > b/opensm/opensm/osm_sa_path_record.c > > index be0cd71..1fa83a1 100644 > > --- a/o

Re: [PATCH] tests/subnet_discover: discover test utility

2010-01-21 Thread Ira Weiny
systems which are having trouble. OpenSM is trying to discover and route. We are running diags trying to figure out what is going on. There is hardware going up and down; bad switches or nodes which are booting/rebooting. I plan to go forward with this but having an option for outstanding MAD&

Found one reason libibnetdisc is slower than subnet_discover

2010-01-21 Thread Ira Weiny
; new real0m2.625s user0m0.057s sys 0m0.570s 18:15:49 > diff old new 2c2 < # Topology file: generated on Thu Jan 21 18:15:42 2010 --- > # Topology file: generated on Thu Jan 21 18:15:49 2010 Ira >From 53a3f1936e0ec954a3c470cc5436ce4fd6be3b3e Mon Sep 17 00:00:00 2001 From: Ira

And I found the other reason (Re: Found one reason libibnetdisc is slower than subnet_discover)

2010-01-22 Thread Ira Weiny
m0.185s Therefore, it appears that having just 2 outstanding MAD's on the wire is a huge improvement. Ira On Thu, 21 Jan 2010 18:14:18 -0800 Ira Weiny wrote: > Sasha, > > Here is a patch which speeds up libibnetdisc by about 17%. I am not going to > pursue this much because I t

Re: Found one reason libibnetdisc is slower than subnet_discover

2010-01-25 Thread Ira Weiny
Hey Sasha, On Mon, 25 Jan 2010 17:19:28 +0200 Sasha Khapyorsky wrote: > On 18:14 Thu 21 Jan , Ira Weiny wrote: > > From: Ira Weiny > > Date: Thu, 21 Jan 2010 17:13:37 -0800 > > Subject: [PATCH] optimize query_node > > > >recognize when we have found a

Re: Found one reason libibnetdisc is slower than subnet_discover

2010-01-25 Thread Ira Weiny
On Mon, 25 Jan 2010 19:28:22 +0200 Sasha Khapyorsky wrote: > Hi Ira, > > On 09:09 Mon 25 Jan , Ira Weiny wrote: > > > > I did not pursue this further because all this code is changed with your > > algorithm. So I did not clean this patch up further. As I said

[PATCH 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-02 Thread Ira Weiny
However, I have done some extensive diffing of the output of ibnetdiscover and things look good. 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"

[PATCH 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-02-02 Thread Ira Weiny
From: Ira Weiny Date: Fri, 22 Jan 2010 17:33:30 -0800 Subject: [PATCH] libibnetdisc: Convert to a multi-smp algorithm Allow for multiple SMP's to be on the wire at a single time. This algorithm splits the processing of SMP's to a small smp engine which may be

[PATCH 2/2] libibnetdisc: add ibnd_set_max_smps_on_wire call

2010-02-02 Thread Ira Weiny
From: Ira Weiny Date: Tue, 2 Feb 2010 14:06:03 -0800 Subject: [PATCH] libibnetdisc: add ibnd_set_max_smps_on_wire call In addition update ibnetdiscover, iblinkinfo, and ibqueryerrors to use this function. Signed-off-by: Ira Weiny --- .../libibnetdisc/include/infiniband/ibnetdisc.h

[PATCH] libibnetdisc: fix typo in man page for ibnd_show_progress

2010-02-02 Thread Ira Weiny
From: Ira Weiny Date: Tue, 2 Feb 2010 17:43:20 -0800 Subject: [PATCH] libibnetdisc: fix typo in man page for ibnd_show_progress Signed-off-by: Ira Weiny --- .../libibnetdisc/man/ibnd_discover_fabric.3|2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/infiniband

Re: [PATCH 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-04 Thread Ira Weiny
On Thu, 4 Feb 2010 09:19:39 -0500 Hal Rosenstock wrote: > On Tue, Feb 2, 2010 at 7:45 PM, Ira Weiny wrote: > > Sasha, > > > > Following up on our thread regarding having multiple outstanding SMP's in > > libibnetdisc. > > > > These 2 patches impleme

Re: [PATCH 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-04 Thread Ira Weiny
On Thu, 4 Feb 2010 15:01:32 -0500 Hal Rosenstock wrote: > On Thu, Feb 4, 2010 at 1:00 PM, Ira Weiny wrote: > > On Thu, 4 Feb 2010 09:19:39 -0500 > > Hal Rosenstock wrote: > > > >> On Tue, Feb 2, 2010 at 7:45 PM, Ira Weiny wrote: > >> > Sasha, >

Re: [PATCH 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-04 Thread Ira Weiny
On Thu, 4 Feb 2010 16:13:25 -0800 Ira Weiny wrote: > On Thu, 4 Feb 2010 15:01:32 -0500 > Hal Rosenstock wrote: > > > On Thu, Feb 4, 2010 at 1:00 PM, Ira Weiny wrote: > > > On Thu, 4 Feb 2010 09:19:39 -0500 > > > Hal Rosenstock wrote: > > > > &

Re: [PATCH 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-05 Thread Ira Weiny
>> Ira > >> > >> > > >> > -- Hal > >> > > >> > > Ira > >> > > > >> > >> > >> > >> -- Hal > >> > >> > >> > >> > > >> > >> > The fi

[PATCH v3 0/2] Using multi-smps on the wire in libibnetdisc

2010-02-18 Thread Ira Weiny
After the discussion with Hal I decided it would be safer to just limit the number of outstanding MAD's to 2. This v3 version changes that. Patch 2/2 remains the same but I am just sending it to be complete. Thanks, Ira -- To unsubscribe from this list: send the line "unsubscribe linux-rdma"

[PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-02-18 Thread Ira Weiny
From: Ira Weiny Date: Fri, 22 Jan 2010 17:33:30 -0800 Subject: [PATCH] libibnetdisc: Convert to a multi-smp algorithm v3: change DEFAULT_MAX_SMP_ON_WIRE to 2 Allow for multiple SMP's to be on the wire at a single time. This algorithm splits the processing of SMP's

[PATCH v3 2/2] libibnetdisc: add ibnd_set_max_smps_on_wire call

2010-02-18 Thread Ira Weiny
From: Ira Weiny Date: Tue, 2 Feb 2010 14:06:03 -0800 Subject: [PATCH] libibnetdisc: add ibnd_set_max_smps_on_wire call In addition update ibnetdiscover, iblinkinfo, and ibqueryerrors to use this function. Signed-off-by: Ira Weiny --- .../libibnetdisc/include/infiniband/ibnetdisc.h

[PATCH] libibnetdisc: fix typo in man page for ibnd_show_progress

2010-02-18 Thread Ira Weiny
From: Ira Weiny Date: Tue, 2 Feb 2010 17:43:20 -0800 Subject: [PATCH] libibnetdisc: fix typo in man page for ibnd_show_progress Signed-off-by: Ira Weiny --- .../libibnetdisc/man/ibnd_discover_fabric.3|2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/infiniband

Re: how to force opensmd to recalculate all paths?

2010-02-19 Thread Ira Weiny
erformance Systems Division > Lawrence Livermore National Laboratory > > -- > 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.h

Re: looking for opensm mailing list

2010-02-26 Thread Ira Weiny
> Tom Ammon > Network Engineer > Office: 801.587.0976 > Mobile: 801.674.9273 > > Center for High Performance Computing > University of Utah > http://*www.*chpc.utah.edu > > -- > To unsubscribe from this list: send the line "unsubscribe linux-

[PATCH] infiniband-diags: Ignore PortInfo data on down port.

2010-03-19 Thread Ira Weiny
From: Ira Weiny Date: Thu, 18 Mar 2010 18:35:34 -0700 Subject: [PATCH] infiniband-diags: Ignore PortInfo data on down port. According to C14-24.2.1: If PortInfo:PortState == Down then only PortInfo:PortState and PortInfo:PortPhysicalState _must_ be valid. Other fields may be invalid depending

Re: ibstat stuck in state initialized after reboot

2010-03-24 Thread Ira Weiny
u can restart the SM on the switch I would try that first. Otherwise yes rebooting the switch is probably your best bet, and yes it will affect the fabric, although I can't say how much without knowing the topology. Ira > > Thanks, > Mike Robbert > -- > To unsubscribe from this

Re: ibstat stuck in state initialized after reboot

2010-03-24 Thread Ira Weiny
On Wed, 24 Mar 2010 11:34:02 -0600 Michael Robbert wrote: > Interesting note! The 7024 is our large switch where all the hosts are > connected, but I was told that we were sold the 7000D because the 7024 > didn't have a subnet manager. Unfortunately the 7000D has a different CLI > and that comman

Re: ibstat stuck in state initialized after reboot

2010-03-24 Thread Ira Weiny
ith you! :-D Ira > > Thanks, > Mike > > On Mar 24, 2010, at 12:25 PM, Ira Weiny wrote: > > > On Wed, 24 Mar 2010 11:34:02 -0600 > > Michael Robbert wrote: > > > >> Interesting note! The 7024 is our large switch where all the hosts are > >&

Re: [PATCH v3 0/2] Using multi-smps on the wire in libibnetdisc

2010-04-02 Thread Ira Weiny
Sasha, Have you had a chance to look at this yet? If you want I can resend the latest version of the patches. Thanks, Ira On Thu, 18 Feb 2010 12:49:31 -0800 Ira Weiny wrote: > After the discussion with Hal I decided it would be safer to just limit the > number of outstanding MAD&

Re: [PATCH v2 38/51] IB/qib: Add qib_sysfs.c

2010-04-08 Thread Ira Weiny
-- > 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 Nati

Re: [PATCH v2 38/51] IB/qib: Add qib_sysfs.c

2010-04-08 Thread Ira Weiny
t, I would like to see these counters included as they give valuable information about what is going on in a cluster. Ira * OFED MUST die! > > - R. > > -- > Roland Dreier || For corporate legal information go to: > http://*www.*cisco.com/web/about/doing_business/legal/cri/index.

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-04-13 Thread Ira Weiny
On Tue, 13 Apr 2010 13:46:58 +0300 Sasha Khapyorsky wrote: > On 12:49 Thu 18 Feb , Ira Weiny wrote: > > > > From: Ira Weiny > > Date: Fri, 22 Jan 2010 17:33:30 -0800 > > Subject: [PATCH] libibnetdisc: Convert to a multi-smp algorithm > > > >

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-04-13 Thread Ira Weiny
>ports[rem_port_num]); > } > > - if (!node_is_new) > - return 0; > - > - query_node_desc(engine, &smp->path, node); > - > - if (node->type == IB_NODE_SWITCH) > - query_switch_info(engine, &smp->path, node); &

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-04-13 Thread Ira Weiny
ctx.hops = hops; fabric = ibnd_discover_fabric(&ctx); /* opens it's own ibmad_port */ } ... Ira > > Sasha -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore National Lab 925-423-8008 wei...@llnl.gov -- To unsubscribe from this list: send the lin

Re: [PATCH] libibnetdisc: fix outstanding SMPs countung

2010-04-13 Thread Ira Weiny
engine); > } > -- > 1.7.0.4 > > -- > 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 M

Re: [PATCH] libibnetdisc: fix outstanding SMPs countung

2010-04-13 Thread Ira Weiny
On Tue, 13 Apr 2010 13:38:26 -0700 Ira Weiny wrote: > This changes the logic. "num_smps_outstanding" is NOT the number on the > wire, but it appears you have made it so. This is the number which will > cause process_smp_queue to continue being called. > > If you are

Re: [PATCH] libibnetdisc: fix outstanding SMPs countung

2010-04-14 Thread Ira Weiny
On Apr 14, 2010, at 3:23 AM, Sasha Khapyorsky wrote: On 13:44 Tue 13 Apr , Ira Weiny wrote: This changes the logic. "num_smps_outstanding" is NOT the number on the wire, but it appears you have made it so. Actually yes, it made it so. This is the number which

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-04-22 Thread Ira Weiny
libibmad thread safe would be very beneficial, if not necessary. For example handling RMPP and redirection is already in libibmad. Why make people reimplement it on their own if they want concurrent execution of any kind? -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore Na

Re: [ewg] ibcheckerrors "Port All FAILED" reported

2010-05-05 Thread Ira Weiny
: OK > Error check on lid 3 (cst-linux HCA-1) port 1: OK > > ## Summary: 17 nodes checked, 0 bad nodes found > ## 32 ports checked, 0 ports have errors beyond threshold > ___ > ewg mailing list > e...@lists.openfabrics.org > http://*lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg > -- Ira Weiny -- 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

Re: [ewg] ibcheckerrors "Port All FAILED" reported

2010-05-05 Thread Ira Weiny
Nevermind, I am wrong about the below. However, there is an option to "emulate" the all ports when it is not supported. That is a way to fix this I believe. Ira On Wed, 5 May 2010 18:09:43 -0700 Ira Weiny wrote: > Interesting... > > I have a switch which does this as wel

[PATCH] infiniband-diags/scripts/ibcheckerrs.in: emulate all ports if necessary.

2010-05-05 Thread Ira Weiny
From: Ira Weiny Date: Wed, 5 May 2010 19:49:37 -0700 Subject: [PATCH] infiniband-diags/scripts/ibcheckerrs.in: emulate all ports if necessary. Signed-off-by: Ira Weiny --- infiniband-diags/scripts/ibcheckerrs.in |2 +- infiniband-diags/src/perfquery.c|6 +++--- 2 files

Re: [ewg] ibcheckerrors "Port All FAILED" reported

2010-05-06 Thread Ira Weiny
> -Original Message- > From: linux-rdma-ow...@vger.kernel.org > [mailto:linux-rdma-ow...@vger.kernel.org] On Behalf Of Ira Weiny > Sent: Wednesday, May 05, 2010 9:10 PM > To: Woodruff, Robert J; linux-rdma@vger.kernel.org > Cc: EWG; tzipo...@mellanox.co.il > Subject: Re: [e

Re: [PATCH] infiniband-diags/scripts/ibcheckerrs.in: emulate all ports if necessary.

2010-05-06 Thread Ira Weiny
double read for each port which will kill ibcheckerrors performance on a large cluster. Sasha, what is the status of Mikes patch? Ira On Wed, 5 May 2010 19:47:20 -0700 Ira Weiny wrote: > > From: Ira Weiny > Date: Wed, 5 May 2010 19:49:37 -0700 > Subject: [PATCH] infiniband-d

Re: [ewg] ibcheckerrors "Port All FAILED" reported

2010-05-06 Thread Ira Weiny
On Thu, 6 May 2010 14:11:24 -0700 Sasha Khapyorsky wrote: > On 18:09 Wed 05 May , Ira Weiny wrote: > > > > 14:29:03 > ./perfquery 40 255 > > ./perfquery: iberror: failed: AllPortSelect not supported > > > > It seems there is an issue with the Capab

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-05-10 Thread Ira Weiny
On Fri, 7 May 2010 13:50:53 -0700 Sasha Khapyorsky wrote: > Hi Ira, > > On 19:12 Thu 22 Apr , Ira Weiny wrote: > > On Tue, 13 Apr 2010 16:25:31 +0300 > > Sasha Khapyorsky wrote: > > > > > On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: > >

Re: [PATCH v3 1/2] libibnetdisc: Convert to a multi-smp algorithm

2010-05-11 Thread Ira Weiny
On Tue, 11 May 2010 09:42:34 -0700 Sasha Khapyorsky wrote: > On 13:53 Mon 10 May , Ira Weiny wrote: > > > > > > > >int ibnd_discover_fabric(ibnd_fabric_t **fabric, > > > > cosnt char *ca_name, <== could we even

[PATCH] ibnetdisc: Separate calls to umad and mad layer to avoid race condition on response MAD's

2010-05-11 Thread Ira Weiny
From: Ira Weiny Date: Tue, 11 May 2010 15:36:08 -0700 Subject: [PATCH] ibnetdisc: Separate calls to umad and mad layer to avoid race condition on response MAD's Specify CA/Port to use which allows parallel scanning to other operations. Signed-off-by: Ira Weiny --- .../libibne

Re: [PATCH] ibnetdisc: Separate calls to umad and mad layer to avoid race condition on response MAD's

2010-05-25 Thread Ira Weiny
On Sat, 22 May 2010 07:40:10 -0700 Sasha Khapyorsky wrote: > On 16:48 Tue 11 May , Ira Weiny wrote: > > > > From: Ira Weiny > > Date: Tue, 11 May 2010 15:36:08 -0700 > > Subject: [PATCH] ibnetdisc: Separate calls to umad and mad layer to avoid > >

[PATCH] libibnetdisc: move ibmad_port out of smp_engine

2010-05-25 Thread Ira Weiny
From: Ira Weiny Date: Tue, 25 May 2010 13:32:18 -0700 Subject: [PATCH] libibnetdisc: move ibmad_port out of smp_engine Signed-off-by: Ira Weiny --- infiniband-diags/libibnetdisc/src/ibnetdisc.c | 15 ++- infiniband-diags/libibnetdisc/src/internal.h |2 +- infiniband-diags

Re: [PATCH v2] IB/util madeye.c

2010-05-27 Thread Ira Weiny
On Thu, 27 May 2010 09:31:46 -0700 "Hefty, Sean" wrote: > > Madeye is a debugging/monitoring tool for infiniband fabrics. When loaded, > > by default it will log copies of all MAD traffic to the system log. In > > addition, it can be configured to log only those MADs which have a > > particular c

[PATCH] opensm/osm_perfmgr.c: Remove unnecessary lock reference from Performance Manager object

2010-06-01 Thread Ira Weiny
From: Ira Weiny Date: Mon, 22 Dec 2008 11:03:59 -0800 Subject: [PATCH] opensm/osm_perfmgr.c: Remove unnecessary lock reference from Performance Manager object Signed-off-by: Ira Weiny --- opensm/include/opensm/osm_perfmgr.h |1 - opensm/opensm/osm_perfmgr.c | 25

[PATCH] staging/rdma: Kconfig change STAGING_RDMA to be tristate.

2015-09-24 Thread ira . weiny
From: Ira Weiny STAGING_RDMA was failing to build when INFINIBAND was set to 'm' and STAGING_RDMA was set to 'y'. Making this a tristate properly inherits the 'm' from the INFINIBAND setting. Reviewed-by: Dalessandro, Dennis Reviewed-by: John, Jubin Reviewed-by

[PATCH RESEND] staging/rdma: Kconfig change STAGING_RDMA to be tristate.

2015-09-28 Thread ira . weiny
From: Ira Weiny STAGING_RDMA was failing to build when INFINIBAND was set to 'm' and STAGING_RDMA was set to 'y'. Making this a tristate properly inherits the 'm' from the INFINIBAND setting. Reviewed-by: Dalessandro, Dennis Reviewed-by: John, Jubin Reviewed-by

[PATCH RFC] IB/mad: remove obsolete snoop interface

2015-09-29 Thread ira . weiny
From: Ira Weiny This interface has no current users and is obsolete. Signed-off-by: Ira Weiny --- This has undergone a medium level of testing. I have run it against mlx4, qib, and OPA hardware and it does not seem to cause any regressions. drivers/infiniband/core/mad.c | 226

[PATCH 0/5 RFC] IB/mad: Add kernel trace to umad/mad

2015-09-30 Thread ira . weiny
From: Ira Weiny This has mild testing and still has some FIXMEs etc. I'm submitting to help decide if we wish to remove the MAD snooping infrastructure. I believe this to be a more efficient debugging mechanism as it is most always available (if debugfs is available) and should have li

[PATCH 2/5 RFC] IB/MAD: add recv path trace point

2015-09-30 Thread ira . weiny
From: Ira Weiny Signed-off-by: Ira Weiny --- drivers/infiniband/core/mad.c | 10 +++ include/trace/events/ib_mad.h | 63 +++ 2 files changed, 73 insertions(+) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index

[PATCH 1/5 RFC] IB/MAD: add send path trace points

2015-09-30 Thread ira . weiny
From: Ira Weiny Signed-off-by: Ira Weiny --- drivers/infiniband/core/mad.c | 51 +++ include/trace/events/ib_mad.h | 191 ++ 2 files changed, 242 insertions(+) create mode 100644 include/trace/events/ib_mad.h diff --git a/drivers/infiniband

[PATCH 4/5 RFC] IB/mad: Add umad trace points

2015-09-30 Thread ira . weiny
From: Ira Weiny This could potentially benefit from a read trace point. Signed-off-by: Ira Weiny --- drivers/infiniband/core/user_mad.c | 5 + include/trace/events/ib_umad.h | 312 + 2 files changed, 317 insertions(+) create mode 100644 include/trace

[PATCH 5/5 RFC] IB/mad: Add SMP tracing

2015-09-30 Thread ira . weiny
From: Ira Weiny Signed-off-by: Ira Weiny --- drivers/infiniband/core/mad.c | 8 include/trace/events/ib_mad.h | 90 +++ 2 files changed, 98 insertions(+) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 189404194470

[PATCH 3/5 RFC] IB/MAD Add agent trace points

2015-09-30 Thread ira . weiny
From: Ira Weiny Signed-off-by: Ira Weiny --- drivers/infiniband/core/mad.c | 3 +++ include/trace/events/ib_mad.h | 41 + 2 files changed, 44 insertions(+) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 0dc0ae78d313

[PATCH 02/23] staging/rdma/hfi1: Reset ASIC CSRs on FLR, and once per ASIC

2015-10-19 Thread ira . weiny
-by: Ira Weiny --- drivers/staging/rdma/hfi1/chip.c | 35 +++ drivers/staging/rdma/hfi1/firmware.c | 4 2 files changed, 19 insertions(+), 20 deletions(-) diff --git a/drivers/staging/rdma/hfi1/chip.c b/drivers/staging/rdma/hfi1/chip.c index 11523596ca57

[PATCH 01/23] staging/rdma/hfi1: inline clear_ahg()

2015-10-19 Thread ira . weiny
routine to qp.h for scope reasons. Reviewed-by: Dennis Dalessandro Signed-off-by: Mike Marciniszyn Signed-off-by: Ira Weiny --- drivers/staging/rdma/hfi1/qp.h| 15 +++ drivers/staging/rdma/hfi1/ruc.c | 13 - drivers/staging/rdma/hfi1/verbs.h | 2 -- 3 files

[PATCH 00/23] Update driver to 0.9-294

2015-10-19 Thread ira . weiny
From: Ira Weiny The following series has bug fixes and updates to the staging hfi1 driver. Arthur Kepner (1): staging/rdma/hfi1: optionally prescan rx queue for {B,F}ECNs - UC, RC Caz Yokoyama (1): staging/rdma/hfi1: Reset firmware instead of reloading Sbus Dean Luick (4): staging/rdma

[PATCH 05/23] staging/rdma/hfi1: Remove QSFP_ENABLED from HFI capability mask

2015-10-19 Thread ira . weiny
From: Easwar Hariharan The QSFP interface code has been running without issues and the flag is never set to off. This patch removes the QSFP_ENABLED bit from HFI1_CAP. Reviewed-by: Mike Marciniszyn Signed-off-by: Easwar Hariharan Signed-off-by: Ira Weiny --- drivers/staging/rdma/hfi1/chip.c

<    1   2   3   4   5   6   7   8   9   10   >