registering physical memory region

2013-08-21 Thread Eva Mishra
The infiniband specification describes register physical memory region. consumer can request an iova to be returned which can be same or different from the one requested. we provide a physical buffer list (which is list of start physical address of pages) as input to the call that registers

Re: [PATCH 8/8] IB/srp: Make queue size configurable

2013-08-21 Thread Sagi Grimberg
On 8/20/2013 8:43 PM, David Dillow wrote: On Tue, 2013-08-20 at 17:55 +0200, Bart Van Assche wrote: On 08/20/13 17:34, Sagi Grimberg wrote: Question, If srp now will allow larger queues while using a single global FMR pool of size 1024, isn't it more likely now that in stress environment srp

Re: [ceph-users] Help needed porting Ceph to RSockets

2013-08-21 Thread Matthew Anderson
Hi Sean, I tested out the patch and unfortunately had the same results as Andreas. About 50% of the time the rpoll() thread in Ceph still hangs when rshutdown() is called. I saw a similar behaviour when increasing the poll time on the pre-patched version if that's of any relevance. Thanks On

[PATCH V1 libibverbs] XRC - Sample application issues

2013-08-21 Thread Yishai Hadas
Fix sync issue when clients go down, it comes to prevent a case when client misses a response from the daemon then wait forever. Fix typo in error message. Signed-off-by: Yishai Hadas yish...@mellanox.com --- This patch is on top of V9 of XRC series that was already sent. It should be squashed

Re: Helps to Decode rpc_debug Output

2013-08-21 Thread Wendy Cheng
On Thu, Aug 15, 2013 at 11:08 AM, Wendy Cheng s.wendy.ch...@gmail.com wrote: On Thu, Aug 15, 2013 at 5:46 AM, Tom Talpey t...@talpey.com wrote: On 8/14/2013 8:14 PM, Wendy Cheng wrote: Longer version of the question: I'm trying to enable NFS-RDMA on an embedded system (based on 2.6.38

[PATCH 2/2] IB/ipoib: lower NAPI weight

2013-08-21 Thread Michal Schmidt
Since commit 82dc3c63 netif_napi_add() produces an error message if a NAPI poll weight greater than 64 is requested. Use the standard NAPI weight. Signed-off-by: Michal Schmidt mschm...@redhat.com CC: Roland Dreier rol...@kernel.org CC: Sean Hefty sean.he...@intel.com CC: Hal Rosenstock

[PATCH 1/2] IB/nes: lower NAPI weight

2013-08-21 Thread Michal Schmidt
Since commit 82dc3c63 netif_napi_add() produces an error message if a NAPI poll weight greater than 64 is requested. Use the standard NAPI weight. Signed-off-by: Michal Schmidt mschm...@redhat.com CC: Faisal Latif faisal.la...@intel.com CC: Roland Dreier rol...@kernel.org CC: Sean Hefty

[PATCH 0/2] drivers/infiniband: fix too big NAPI weights

2013-08-21 Thread Michal Schmidt
Some drivers request too big NAPI weights and would trigger the error message in netif_napi_add() added in commit 82dc3c63. Let's fix them. Michal Schmidt (2): IB/nes: lower NAPI weight IB/ipoib: lower NAPI weight drivers/infiniband/hw/nes/nes_nic.c | 2 +-

Re: [PATCH perftest] Mod: Allow specification of pkey index

2013-08-21 Thread Coulter, Susan K
Patch modified, please use this one instead. - mod: variable name changed from pkey to pkey_index - mod: check max pkeys allowed on device instead of hard coded limits - new: removed bogus calls to perror, sends confusing error messages Signed-off-by: Susan K. Coulter

[PATCH libibverbs V2] Add new verb: uv_query_port_max_datagram()

2013-08-21 Thread Jeff Squyres
Per lengthy discussion on the linux-rdma list, add a new verb to get max datagram size (in bytes) since the methods for retrieving MTU values are limited to a finite enum set, and are difficult to change for backwards compatibility reasons. Also add corresponding command: