Change default RDMA settings to 128x 129K buffers

129K to leave extra space for the header

The problem with 8x 1M buffers is that the following happens with,
for example, 2 OSDs and 4M T1Q1 write:
- Server posts 8 receives
- Client posts 8 sends
- WRs are processed by the RDMA stack, but the OSD doesn't have the time
  to handle them and doesn't refill buffers
- Client posts 1 more send
- RNR retransmission happens and performance drops to zero

Overall it seems that RDMA support should be reworked to use real 'RDMA'
operations i.e. operations writing into remote memory. This has an
additional advantage of avoiding a copy at the receive side of the OSD.

src/messenger.cpp

@@ -147,13 +147,13 @@ void osd_messenger_t::parse_config(const json11::Json & config)
         this->rdma_max_sge = 128;
     this->rdma_max_send = config["rdma_max_send"].uint64_value();
     if (!this->rdma_max_send)
-        this->rdma_max_send = 32;
+        this->rdma_max_send = 1;
     this->rdma_max_recv = config["rdma_max_recv"].uint64_value();
     if (!this->rdma_max_recv)
-        this->rdma_max_recv = 8;
+        this->rdma_max_recv = 128;
     this->rdma_max_msg = config["rdma_max_msg"].uint64_value();
     if (!this->rdma_max_msg || this->rdma_max_msg > 128*1024*1024)
-        this->rdma_max_msg = 1024*1024;
+        this->rdma_max_msg = 129*1024;
 #endif
     this->receive_buffer_size = (uint32_t)config["tcp_header_buffer_size"].uint64_value();
     if (!this->receive_buffer_size || this->receive_buffer_size > 1024*1024*1024)

src/messenger.h

@@ -133,7 +133,7 @@ protected:
     std::string rdma_device;
     uint64_t rdma_port_num = 1, rdma_gid_index = 0, rdma_mtu = 0;
     msgr_rdma_context_t *rdma_context = NULL;
-    uint64_t rdma_max_sge = 0, rdma_max_send = 0, rdma_max_recv = 8;
+    uint64_t rdma_max_sge = 0, rdma_max_send = 0, rdma_max_recv = 0;
     uint64_t rdma_max_msg = 0;
 #endif