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

2010-05-11 Thread Sasha Khapyorsky
On 13:53 Mon 10 May , Ira Weiny wrote: int ibnd_discover_fabric(ibnd_fabric_t **fabric, cosnt char *ca_name, == could we even default this? I would think about ca_name and port_number. And this is of course may have default (NULL, 0). Ok,

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 sas...@voltaire.com 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 default this? I would think

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 sas...@voltaire.com wrote: Hi Ira, On 19:12 Thu 22 Apr , Ira Weiny wrote: On Tue, 13 Apr 2010 16:25:31 +0300 Sasha Khapyorsky sas...@voltaire.com wrote: On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: However see some

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

2010-04-22 Thread Ira Weiny
On Tue, 13 Apr 2010 16:25:31 +0300 Sasha Khapyorsky sas...@voltaire.com wrote: On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: However see some comments and questions below. Another thought. What about API like: ibnd_discover_fabric(cosnt char *ca_name, unsigned port_num,

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

2010-04-14 Thread Sasha Khapyorsky
On 13:30 Tue 13 Apr , Ira Weiny wrote: If we are going to do something like this why not more like a context? Something like this? ibqueryerrors.c query_errors_ibmad_port = mad_rpc_open_port(ibd_ca, ibd_ca_port, mgmt_classes, 4); { ibnd_context_t ctx;

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

2010-04-13 Thread Sasha Khapyorsky
On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: However see some comments and questions below. Another thought. What about API like: ibnd_discover_fabric(cosnt char *ca_name, unsigned port_num, struct ibnd_config *cfg); So libibnetdisc will be

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 sas...@voltaire.com wrote: On 12:49 Thu 18 Feb , Ira Weiny wrote: From: Ira Weiny wei...@llnl.gov Date: Fri, 22 Jan 2010 17:33:30 -0800 Subject: [PATCH] libibnetdisc: Convert to a multi-smp algorithm v3: change

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

2010-04-13 Thread Ira Weiny
On Tue, 13 Apr 2010 20:18:24 +0300 Sasha Khapyorsky sas...@voltaire.com wrote: On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: +static int recv_node_info(smp_engine_t *engine, ibnd_smp_t * smp, + uint8_t *mad, void *cb_data) +{ + ibnd_fabric_t *fabric =

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

2010-04-13 Thread Ira Weiny
On Tue, 13 Apr 2010 16:25:31 +0300 Sasha Khapyorsky sas...@voltaire.com wrote: On 13:46 Tue 13 Apr , Sasha Khapyorsky wrote: However see some comments and questions below. Another thought. What about API like: ibnd_discover_fabric(cosnt char *ca_name, unsigned port_num,

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

2010-02-18 Thread Ira Weiny
From: Ira Weiny wei...@llnl.gov 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