Re: [PATCH] libibverbs: Add the use of IBV_SEND_INLINE to example pingpong programs

2013-07-30 Thread Jeff Squyres (jsquyres) 
4th bump...

On Jul 10, 2013, at 4:32 PM, Jeff Squyres jsquy...@cisco.com wrote:

 If the send size is less than the cap.max_inline_data reported by the
 qp, use the IBV_SEND_INLINE flag.  This now only shows the example of
 using ibv_query_qp(), it also reduces the latency time shown by the
 pingpong programs when the sends can be inlined.
 
 Signed-off-by: Jeff Squyres jsquy...@cisco.com
 ---
 examples/rc_pingpong.c  | 18 +-
 examples/srq_pingpong.c | 19 +--
 examples/uc_pingpong.c  | 17 -
 examples/ud_pingpong.c  | 18 +-
 4 files changed, 51 insertions(+), 21 deletions(-)
 
 diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
 index 15494a1..a8637a5 100644
 --- a/examples/rc_pingpong.c
 +++ b/examples/rc_pingpong.c
 @@ -65,6 +65,7 @@ struct pingpong_context {
   struct ibv_qp   *qp;
   void*buf;
   int  size;
 + int  send_flags;
   int  rx_depth;
   int  pending;
   struct ibv_port_attr portinfo;
 @@ -319,8 +320,9 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -367,7 +369,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .cap = {
 @@ -379,11 +382,16 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp = ibv_create_qp(ctx-pd, attr);
 + ctx-qp = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp)  {
   fprintf(stderr, Couldn't create QP\n);
   goto clean_cq;
   }
 +
 + ibv_query_qp(ctx-qp, attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   {
 @@ -508,7 +516,7 @@ static int pp_post_send(struct pingpong_context *ctx)
   .sg_list= list,
   .num_sge= 1,
   .opcode = IBV_WR_SEND,
 - .send_flags = IBV_SEND_SIGNALED,
 + .send_flags = ctx-send_flags,
   };
   struct ibv_send_wr *bad_wr;
 
 diff --git a/examples/srq_pingpong.c b/examples/srq_pingpong.c
 index 6e00f8c..552a144 100644
 --- a/examples/srq_pingpong.c
 +++ b/examples/srq_pingpong.c
 @@ -68,6 +68,7 @@ struct pingpong_context {
   struct ibv_qp   *qp[MAX_QP];
   void*buf;
   int  size;
 + int  send_flags;
   int  num_qp;
   int  rx_depth;
   int  pending[MAX_QP];
 @@ -350,9 +351,10 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-num_qp   = num_qp;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-num_qp = num_qp;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -413,7 +415,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   for (i = 0; i  num_qp; ++i) {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .srq = ctx-srq,
 @@ -424,11 +427,15 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp[i] = ibv_create_qp(ctx-pd, attr);
 + ctx-qp[i] = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp[i])  {
   fprintf(stderr, Couldn't create QP[%d]\n, i);
   goto clean_qps;
   }
 + ibv_query_qp(ctx-qp[i], attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   for (i = 0; i  num_qp; ++i) {
 @@ -568,7 +575,7 @@ static int pp_post_send(struct

Re: [PATCH] libibverbs: Add the use of IBV_SEND_INLINE to example pingpong programs

2013-07-23 Thread Jeff Squyres (jsquyres) 
Bump bump bump.

I know this isn't a huge / important patch, but it is a small thing that does 
decrease the latency reported by these example programs.


On Jul 10, 2013, at 4:32 PM, Jeff Squyres jsquy...@cisco.com wrote:

 If the send size is less than the cap.max_inline_data reported by the
 qp, use the IBV_SEND_INLINE flag.  This not only shows the example of
 using ibv_query_qp(), it also reduces the latency time shown by the
 pingpong programs when the sends can be inlined.
 
 Signed-off-by: Jeff Squyres jsquy...@cisco.com
 ---
 examples/rc_pingpong.c  | 18 +-
 examples/srq_pingpong.c | 19 +--
 examples/uc_pingpong.c  | 17 -
 examples/ud_pingpong.c  | 18 +-
 4 files changed, 51 insertions(+), 21 deletions(-)
 
 diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
 index 15494a1..a8637a5 100644
 --- a/examples/rc_pingpong.c
 +++ b/examples/rc_pingpong.c
 @@ -65,6 +65,7 @@ struct pingpong_context {
   struct ibv_qp   *qp;
   void*buf;
   int  size;
 + int  send_flags;
   int  rx_depth;
   int  pending;
   struct ibv_port_attr portinfo;
 @@ -319,8 +320,9 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -367,7 +369,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .cap = {
 @@ -379,11 +382,16 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp = ibv_create_qp(ctx-pd, attr);
 + ctx-qp = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp)  {
   fprintf(stderr, Couldn't create QP\n);
   goto clean_cq;
   }
 +
 + ibv_query_qp(ctx-qp, attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   {
 @@ -508,7 +516,7 @@ static int pp_post_send(struct pingpong_context *ctx)
   .sg_list= list,
   .num_sge= 1,
   .opcode = IBV_WR_SEND,
 - .send_flags = IBV_SEND_SIGNALED,
 + .send_flags = ctx-send_flags,
   };
   struct ibv_send_wr *bad_wr;
 
 diff --git a/examples/srq_pingpong.c b/examples/srq_pingpong.c
 index 6e00f8c..552a144 100644
 --- a/examples/srq_pingpong.c
 +++ b/examples/srq_pingpong.c
 @@ -68,6 +68,7 @@ struct pingpong_context {
   struct ibv_qp   *qp[MAX_QP];
   void*buf;
   int  size;
 + int  send_flags;
   int  num_qp;
   int  rx_depth;
   int  pending[MAX_QP];
 @@ -350,9 +351,10 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-num_qp   = num_qp;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-num_qp = num_qp;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -413,7 +415,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   for (i = 0; i  num_qp; ++i) {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .srq = ctx-srq,
 @@ -424,11 +427,15 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp[i] = ibv_create_qp(ctx-pd, attr);
 + ctx-qp[i] = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp[i])  {
   fprintf(stderr, Couldn't create QP[%d]\n, i);
   goto clean_qps;
   }
 + ibv_query_qp(ctx-qp[i], attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |=

Re: [PATCH] libibverbs: Add the use of IBV_SEND_INLINE to example pingpong programs

2013-07-19 Thread Jeff Squyres (jsquyres) 
Bump bump.

On Jul 10, 2013, at 4:32 PM, Jeff Squyres jsquy...@cisco.com wrote:

 If the send size is less than the cap.max_inline_data reported by the
 qp, use the IBV_SEND_INLINE flag.  This now only shows the example of
 using ibv_query_qp(), it also reduces the latency time shown by the
 pingpong programs when the sends can be inlined.
 
 Signed-off-by: Jeff Squyres jsquy...@cisco.com
 ---
 examples/rc_pingpong.c  | 18 +-
 examples/srq_pingpong.c | 19 +--
 examples/uc_pingpong.c  | 17 -
 examples/ud_pingpong.c  | 18 +-
 4 files changed, 51 insertions(+), 21 deletions(-)
 
 diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
 index 15494a1..a8637a5 100644
 --- a/examples/rc_pingpong.c
 +++ b/examples/rc_pingpong.c
 @@ -65,6 +65,7 @@ struct pingpong_context {
   struct ibv_qp   *qp;
   void*buf;
   int  size;
 + int  send_flags;
   int  rx_depth;
   int  pending;
   struct ibv_port_attr portinfo;
 @@ -319,8 +320,9 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -367,7 +369,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .cap = {
 @@ -379,11 +382,16 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp = ibv_create_qp(ctx-pd, attr);
 + ctx-qp = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp)  {
   fprintf(stderr, Couldn't create QP\n);
   goto clean_cq;
   }
 +
 + ibv_query_qp(ctx-qp, attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   {
 @@ -508,7 +516,7 @@ static int pp_post_send(struct pingpong_context *ctx)
   .sg_list= list,
   .num_sge= 1,
   .opcode = IBV_WR_SEND,
 - .send_flags = IBV_SEND_SIGNALED,
 + .send_flags = ctx-send_flags,
   };
   struct ibv_send_wr *bad_wr;
 
 diff --git a/examples/srq_pingpong.c b/examples/srq_pingpong.c
 index 6e00f8c..552a144 100644
 --- a/examples/srq_pingpong.c
 +++ b/examples/srq_pingpong.c
 @@ -68,6 +68,7 @@ struct pingpong_context {
   struct ibv_qp   *qp[MAX_QP];
   void*buf;
   int  size;
 + int  send_flags;
   int  num_qp;
   int  rx_depth;
   int  pending[MAX_QP];
 @@ -350,9 +351,10 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-num_qp   = num_qp;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-num_qp = num_qp;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -413,7 +415,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   for (i = 0; i  num_qp; ++i) {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .srq = ctx-srq,
 @@ -424,11 +427,15 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp[i] = ibv_create_qp(ctx-pd, attr);
 + ctx-qp[i] = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp[i])  {
   fprintf(stderr, Couldn't create QP[%d]\n, i);
   goto clean_qps;
   }
 + ibv_query_qp(ctx-qp[i], attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   for (i = 0; i  num_qp; ++i) {
 @@ -568,7 +575,7 @@ static int pp_post_send(struct

Re: [PATCH] libibverbs: Add the use of IBV_SEND_INLINE to example pingpong programs

2013-07-15 Thread Jeff Squyres (jsquyres) 
Bump.

On Jul 10, 2013, at 4:32 PM, Jeff Squyres jsquy...@cisco.com wrote:

 If the send size is less than the cap.max_inline_data reported by the
 qp, use the IBV_SEND_INLINE flag.  This now only shows the example of
 using ibv_query_qp(), it also reduces the latency time shown by the
 pingpong programs when the sends can be inlined.
 
 Signed-off-by: Jeff Squyres jsquy...@cisco.com
 ---
 examples/rc_pingpong.c  | 18 +-
 examples/srq_pingpong.c | 19 +--
 examples/uc_pingpong.c  | 17 -
 examples/ud_pingpong.c  | 18 +-
 4 files changed, 51 insertions(+), 21 deletions(-)
 
 diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
 index 15494a1..a8637a5 100644
 --- a/examples/rc_pingpong.c
 +++ b/examples/rc_pingpong.c
 @@ -65,6 +65,7 @@ struct pingpong_context {
   struct ibv_qp   *qp;
   void*buf;
   int  size;
 + int  send_flags;
   int  rx_depth;
   int  pending;
   struct ibv_port_attr portinfo;
 @@ -319,8 +320,9 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -367,7 +369,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .cap = {
 @@ -379,11 +382,16 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp = ibv_create_qp(ctx-pd, attr);
 + ctx-qp = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp)  {
   fprintf(stderr, Couldn't create QP\n);
   goto clean_cq;
   }
 +
 + ibv_query_qp(ctx-qp, attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   {
 @@ -508,7 +516,7 @@ static int pp_post_send(struct pingpong_context *ctx)
   .sg_list= list,
   .num_sge= 1,
   .opcode = IBV_WR_SEND,
 - .send_flags = IBV_SEND_SIGNALED,
 + .send_flags = ctx-send_flags,
   };
   struct ibv_send_wr *bad_wr;
 
 diff --git a/examples/srq_pingpong.c b/examples/srq_pingpong.c
 index 6e00f8c..552a144 100644
 --- a/examples/srq_pingpong.c
 +++ b/examples/srq_pingpong.c
 @@ -68,6 +68,7 @@ struct pingpong_context {
   struct ibv_qp   *qp[MAX_QP];
   void*buf;
   int  size;
 + int  send_flags;
   int  num_qp;
   int  rx_depth;
   int  pending[MAX_QP];
 @@ -350,9 +351,10 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   if (!ctx)
   return NULL;
 
 - ctx-size = size;
 - ctx-num_qp   = num_qp;
 - ctx-rx_depth = rx_depth;
 + ctx-size   = size;
 + ctx-send_flags = IBV_SEND_SIGNALED;
 + ctx-num_qp = num_qp;
 + ctx-rx_depth   = rx_depth;
 
   ctx-buf = memalign(page_size, size);
   if (!ctx-buf) {
 @@ -413,7 +415,8 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   }
 
   for (i = 0; i  num_qp; ++i) {
 - struct ibv_qp_init_attr attr = {
 + struct ibv_qp_attr attr;
 + struct ibv_qp_init_attr init_attr = {
   .send_cq = ctx-cq,
   .recv_cq = ctx-cq,
   .srq = ctx-srq,
 @@ -424,11 +427,15 @@ static struct pingpong_context *pp_init_ctx(struct 
 ibv_device *ib_dev, int size,
   .qp_type = IBV_QPT_RC
   };
 
 - ctx-qp[i] = ibv_create_qp(ctx-pd, attr);
 + ctx-qp[i] = ibv_create_qp(ctx-pd, init_attr);
   if (!ctx-qp[i])  {
   fprintf(stderr, Couldn't create QP[%d]\n, i);
   goto clean_qps;
   }
 + ibv_query_qp(ctx-qp[i], attr, IBV_QP_CAP, init_attr);
 + if (init_attr.cap.max_inline_data = size) {
 + ctx-send_flags |= IBV_SEND_INLINE;
 + }
   }
 
   for (i = 0; i  num_qp; ++i) {
 @@ -568,7 +575,7 @@ static int pp_post_send(struct

[PATCH] libibverbs: Add the use of IBV_SEND_INLINE to example pingpong programs

2013-07-10 Thread Jeff Squyres 
If the send size is less than the cap.max_inline_data reported by the
qp, use the IBV_SEND_INLINE flag.  This now only shows the example of
using ibv_query_qp(), it also reduces the latency time shown by the
pingpong programs when the sends can be inlined.

Signed-off-by: Jeff Squyres jsquy...@cisco.com
---
 examples/rc_pingpong.c  | 18 +-
 examples/srq_pingpong.c | 19 +--
 examples/uc_pingpong.c  | 17 -
 examples/ud_pingpong.c  | 18 +-
 4 files changed, 51 insertions(+), 21 deletions(-)

diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
index 15494a1..a8637a5 100644
--- a/examples/rc_pingpong.c
+++ b/examples/rc_pingpong.c
@@ -65,6 +65,7 @@ struct pingpong_context {
struct ibv_qp   *qp;
void*buf;
int  size;
+   int  send_flags;
int  rx_depth;
int  pending;
struct ibv_port_attr portinfo;
@@ -319,8 +320,9 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
if (!ctx)
return NULL;
 
-   ctx-size = size;
-   ctx-rx_depth = rx_depth;
+   ctx-size   = size;
+   ctx-send_flags = IBV_SEND_SIGNALED;
+   ctx-rx_depth   = rx_depth;
 
ctx-buf = memalign(page_size, size);
if (!ctx-buf) {
@@ -367,7 +369,8 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
}
 
{
-   struct ibv_qp_init_attr attr = {
+   struct ibv_qp_attr attr;
+   struct ibv_qp_init_attr init_attr = {
.send_cq = ctx-cq,
.recv_cq = ctx-cq,
.cap = {
@@ -379,11 +382,16 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
.qp_type = IBV_QPT_RC
};
 
-   ctx-qp = ibv_create_qp(ctx-pd, attr);
+   ctx-qp = ibv_create_qp(ctx-pd, init_attr);
if (!ctx-qp)  {
fprintf(stderr, Couldn't create QP\n);
goto clean_cq;
}
+
+   ibv_query_qp(ctx-qp, attr, IBV_QP_CAP, init_attr);
+   if (init_attr.cap.max_inline_data = size) {
+   ctx-send_flags |= IBV_SEND_INLINE;
+   }
}
 
{
@@ -508,7 +516,7 @@ static int pp_post_send(struct pingpong_context *ctx)
.sg_list= list,
.num_sge= 1,
.opcode = IBV_WR_SEND,
-   .send_flags = IBV_SEND_SIGNALED,
+   .send_flags = ctx-send_flags,
};
struct ibv_send_wr *bad_wr;
 
diff --git a/examples/srq_pingpong.c b/examples/srq_pingpong.c
index 6e00f8c..552a144 100644
--- a/examples/srq_pingpong.c
+++ b/examples/srq_pingpong.c
@@ -68,6 +68,7 @@ struct pingpong_context {
struct ibv_qp   *qp[MAX_QP];
void*buf;
int  size;
+   int  send_flags;
int  num_qp;
int  rx_depth;
int  pending[MAX_QP];
@@ -350,9 +351,10 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
if (!ctx)
return NULL;
 
-   ctx-size = size;
-   ctx-num_qp   = num_qp;
-   ctx-rx_depth = rx_depth;
+   ctx-size   = size;
+   ctx-send_flags = IBV_SEND_SIGNALED;
+   ctx-num_qp = num_qp;
+   ctx-rx_depth   = rx_depth;
 
ctx-buf = memalign(page_size, size);
if (!ctx-buf) {
@@ -413,7 +415,8 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
}
 
for (i = 0; i  num_qp; ++i) {
-   struct ibv_qp_init_attr attr = {
+   struct ibv_qp_attr attr;
+   struct ibv_qp_init_attr init_attr = {
.send_cq = ctx-cq,
.recv_cq = ctx-cq,
.srq = ctx-srq,
@@ -424,11 +427,15 @@ static struct pingpong_context *pp_init_ctx(struct 
ibv_device *ib_dev, int size,
.qp_type = IBV_QPT_RC
};
 
-   ctx-qp[i] = ibv_create_qp(ctx-pd, attr);
+   ctx-qp[i] = ibv_create_qp(ctx-pd, init_attr);
if (!ctx-qp[i])  {
fprintf(stderr, Couldn't create QP[%d]\n, i);
goto clean_qps;
}
+   ibv_query_qp(ctx-qp[i], attr, IBV_QP_CAP, init_attr);
+   if (init_attr.cap.max_inline_data = size) {
+   ctx-send_flags |= IBV_SEND_INLINE;
+   }
}
 
for (i = 0; i  num_qp; ++i) {
@@ -568,7 +575,7 @@ static int pp_post_send(struct pingpong_context *ctx, int 
qp_index)