RE: [Q] How to tranfer a file which is over 2GB(2^31) size in RDMA network?

-Original Message- From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma- ow...@vger.kernel.org] On Behalf Of Hiroyuki Sato Sent: Monday, July 02, 2012 7:20 PM To: linux-rdma Subject: [Q] How to tranfer a file which is over 2GB(2^31) size in RDMA network? Dear developers.

Re: Linux DMA address

Hi, thanks for your quick answer. Let me stress this once again... 1.) Is it possible/allowed to call ib_dma_map_single() on Linux, same buffer address, size and dma_data direction, for two different ib devices? For the data transmission we will have controls in place that not both devices write

Re: Linux DMA address

Let me stress this once again... 1.) Is it possible/allowed to call ib_dma_map_single() on Linux, same buffer address, size and dma_data direction, for two different ib devices? For the data transmission we will have controls in place that not both devices write at the same time into that

Re: Linux DMA address

On Tue, Jul 3, 2012 at 6:37 AM, Klaus Wacker klaus.wac...@de.ibm.com wrote: 1.) Is it possible/allowed to call ib_dma_map_single() on Linux, same buffer address, size and dma_data direction, for two different ib devices? Yes, this should be no problem. 2.) If this is possible, will the

[PATCH V2] libibumad: update umad_recv man page.

Document the umad_recv length parameter better. Changes since V1: add comments from Hal Signed-off-by: Ira Weiny wei...@llnl.gov --- man/umad_recv.3 | 18 +- 1 files changed, 17 insertions(+), 1 deletions(-) diff --git a/man/umad_recv.3 b/man/umad_recv.3 index

Re: [Q] How to tranfer a file which is over 2GB(2^31) size in RDMA network?

Hello Parav.Pandit Thank you for your advice. I'll try it. -- Hiroyuki Sato 2012/7/3 parav.pan...@emulex.com: -Original Message- From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma- ow...@vger.kernel.org] On Behalf Of Hiroyuki Sato Sent: Monday, July 02, 2012 7:20 PM To:

RE: [Q] How to tranfer a file which is over 2GB(2^31) size in RDMA network?

Hello Parav.Pandit Thank you for your advice. I'll try it. You can also look at rsockets in the latest librdmacm library. You'd need to download and build the library yourself, since rsockets is not yet available in any release. But there's a sample program (rcopy) that will copy a

Re: [Q] How to tranfer a file which is over 2GB(2^31) size in RDMA network?

Hello Sean Thank you for your information. I'll try it. P.S. I'm reading rockets(librdmacm) commit log for study Infiniband. :-) 2012/7/4 Hefty, Sean sean.he...@intel.com: Hello Parav.Pandit Thank you for your advice. I'll try it. You can also look at rsockets in the latest librdmacm

[PATCH 0/10] Performance Manager cleanups.

The following 10 patches fix a couple of bugs and add some console options which make it easier to see the internal data of the performance manager. 0001-opensm-perfmgr-Add-config-option-to-ignore-Channel-A.patch 0002-opensm-console-protect-against-0-entered-for-the-per.patch

[PATCH 01/10] opensm/perfmgr: Add config option to ignore Channel Adapters.

On many fabrics nodes have monitoring software which can querry counters on the nodes (CA's) themselves. In this case it may be more efficient to keep this perfmgr traffic off the subnet. Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr.h |1 +

[PATCH 02/10] opensm/console: protect against 0 entered for the perfmgr sweep_time

The config file already has a check for 0. This adds the same check to the console perfmgr sweep_time command. Signed-off-by: Ira Weiny wei...@llnl.gov --- opensm/osm_console.c | 15 --- 1 files changed, 12 insertions(+), 3 deletions(-) diff --git a/opensm/osm_console.c

[PATCH 03/10] opensm: perfmgr fix dump_counters

Mark ports in the DB as invalid until data arrives. Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr_db.h |1 + opensm/osm_perfmgr_db.c | 18 ++ 2 files changed, 19 insertions(+), 0 deletions(-) diff --git a/include/opensm/osm_perfmgr_db.h

[PATCH 04/10] opensm: perfmgr delete inactive nodes from the DB

When a node drops from the fabric the default behavior was to leave the node data in the PerfMgr DB. Add the option (with default set to TRUE) to delete these inactive or missing nodes from the DB. Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr.h| 11 +++

[PATCH 05/10] opensm: perfmgr mark inactive nodes in perfmgr db

When missing nodes are not removed by default mark them as inactive. In addition, add a console option to remove them. Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr.h|7 include/opensm/osm_perfmgr_db.h |5 +++ opensm/osm_console.c|8

[PATCH 06/10] opensm/console: add print all to print_counters console command

Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr_db.h |1 + opensm/osm_console.c| 12 opensm/osm_perfmgr.c| 15 +-- opensm/osm_perfmgr_db.c | 19 +++ 4 files changed, 33 insertions(+), 14

[PATCH 07/10] opensm/console; add port option to perfmgr print_counters

Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr.h|3 ++- include/opensm/osm_perfmgr_db.h |6 -- opensm/osm_console.c| 20 +--- opensm/osm_perfmgr.c|7 --- opensm/osm_perfmgr_db.c | 33

[PATCH 08/10] opensm/console: add abreviations for perfmgr commands

Add: pm for perfmgr pc for print_counters Signed-off-by: Ira Weiny wei...@llnl.gov --- opensm/osm_console.c | 16 ++-- 1 files changed, 14 insertions(+), 2 deletions(-) diff --git a/opensm/osm_console.c b/opensm/osm_console.c index af32b51..cd41286 100644 ---

[PATCH 09/10] opensm/console: Add human readable output for perfmgr data counters

Signed-off-by: Ira Weiny wei...@llnl.gov --- opensm/osm_perfmgr_db.c | 93 ++- 1 files changed, 76 insertions(+), 17 deletions(-) diff --git a/opensm/osm_perfmgr_db.c b/opensm/osm_perfmgr_db.c index 6f9c1ab..ea6fe19 100644 ---

[PATCH 10/10] opensm/console: add perfmgr print_errors (pe) console command.

Only print ports with error counters 0 Signed-off-by: Ira Weiny wei...@llnl.gov --- include/opensm/osm_perfmgr.h|2 +- include/opensm/osm_perfmgr_db.h |6 +- opensm/osm_console.c| 14 +- opensm/osm_perfmgr.c| 10 ++-- opensm/osm_perfmgr_db.c

Re: [PATCH 0/8] opensm: Improved mkey support

I'm sending new versions of patches 1 and 3 to the list, which correct merge/build issues introduced by other recently accepted patches. They will be marked as V1.1. Jim On Mon, 2012-06-25 at 17:54 -0700, Jim Foraker wrote: I'm about to post a set of patches intended to improve mkey

[PATCH V1.1 1/8] opensm: Add guid2mkey cache file support

Adds support for a guid2mkey file, and uses the database to select which mkey to use in outgoing SMPs. Signed-off-by: Jim Foraker forak...@llnl.gov --- include/opensm/osm_db.h |7 +- include/opensm/osm_db_pack.h | 144 ++

[PATCH V1.1 3/8] Add locking where necessary around osm_req_*

Grabs plock for reading in the places where one did not already exist when osm_req_get/osm_req_set are called. Signed-off-by: Jim Foraker forak...@llnl.gov --- opensm/osm_perfmgr.c |6 ++ opensm/osm_sm_state_mgr.c |2 ++ opensm/osm_state_mgr.c|8

Re: [PATCH] infiniband-diags/ibnetdiscover: fix no port 0 info segmentation fault

On Thu, 28 Jun 2012 13:13:07 -0400 Hal Rosenstock h...@dev.mellanox.co.il wrote: Fix ibnetdiscover egmentation fault when it reaches a switch that does not respond to a PortInfo Get for port 0. Note: When ibnetdiscover can't read the port capabilites field from switch port 0, '???' is