Introduce RDMA transport

Main changes in this patch:
* implement *Valkey Over RDMA* protocol, see *Protocol* section in RDMA.md
* implement server side of connection module only, this means we can *NOT*
  compile RDMA support as built-in.
* add necessary information in RDMA.md
* support 'CONFIG SET/GET', for example, 'CONFIG Set rdma.port 6380', then
  check this by 'rdma res show cm_id' and valkey-cli(with RDMA support,
  but not implemented in this patch)
* the full listeners show like():
    listener0:name=tcp,bind=*,bind=-::*,port=6379
    listener1:name=unix,bind=/var/run/valkey.sock
    listener2:name=rdma,bind=xx.xx.xx.xx,bind=yy.yy.yy.yy,port=6379
    listener3:name=tls,bind=*,bind=-::*,port=16379

valgrind test works fine:
valgrind --track-origins=yes --suppressions=./src/valgrind.sup
         --show-reachable=no --show-possibly-lost=no --leak-check=full
         --log-file=err.txt ./src/valkey-server --port 6379
         --loadmodule src/valkey-rdma.so port=6379 bind=xx.xx.xx.xx
         --loglevel verbose --protected-mode no --server_cpulist 2
         --bio_cpulist 3 --aof_rewrite_cpulist 3 --bgsave_cpulist 3
         --appendonly no

performance test:
server side: ./src/valkey-server --port 6379 # TCP port 6379 has no conflict with RDMA port 6379
             --loadmodule src/valkey-rdma.so port=6379 bind=xx.xx.xx.xx bind=yy.yy.yy.yy
             --loglevel verbose --protected-mode no --server_cpulist 2 --bio_cpulist 3
             --aof_rewrite_cpulist 3 --bgsave_cpulist 3 --appendonly no

build a valkey-benchmark with RDMA support(not implemented in this patch), run
on a x86(Intel Platinum 8260) with RoCEv2 interface(Mellanox ConnectX-5):
client side: ./src/valkey-benchmark -h xx.xx.xx.xx -p 6379 -c 30 -n 10000000 --threads 4
             -d 1024 -t ping,get,set --rdma
====== PING_INLINE ======
480561.28 requests per second, 0.060 msec avg latency.

====== PING_MBULK ======
540482.06 requests per second, 0.053 msec avg latency.

====== SET ======
399952.00 requests per second, 0.073 msec avg latency.

====== GET ======
443498.31 requests per second, 0.065 msec avg latency.

Signed-off-by: zhenwei pi <[email protected]>

Author: pizhenwei

RDMA.md

@@ -1,6 +1,43 @@
 RDMA Support
 ============
 
+Getting Started
+---------------
+Note that Valkey Over RDMA is only supported by Linux.
+
+## Building
+
+To build with RDMA support you'll need RDMA development libraries (e.g.
+librdmacm-dev and libibverbs-dev on Debian/Ubuntu).
+
+For now, Valkey only supports RDMA as connection module mode.
+Run `make BUILD_RDMA=module`.
+
+## Running manually
+
+To manually run a Valkey server with RDMA mode:
+
+    ./src/valkey-server --protected-mode no \
+         --loadmodule src/valkey-rdma.so bind=192.168.122.100 port=6379
+
+It's possible to change bind address/port of RDMA by runtime command:
+    10.2.16.101:6379> CONFIG SET rdma-port 6380
+
+It's also possible to have both RDMA and TCP available, and there is no
+conflict of TCP(6379) and RDMA(6379), Ex:
+
+    ./src/valkey-server --protected-mode no \
+         --loadmodule src/valkey-rdma.so bind=192.168.122.100 port=6379 \
+         --port 6379
+
+Note that the network card (192.168.122.100 of this example) should support
+RDMA. To test a server supports RDMA or not:
+
+    ~# rdma res show (a new version iproute2 package)
+Or:
+
+    ~# ibv_devices
+
 Connections
 -----------
 
@@ -121,3 +158,17 @@ setup TX buffer
                 -------------------RDMA disconnect----------------->
                 <------------------RDMA disconnect------------------
 ```
+
+
+## Event handling
+There is no POLLOUT event of RDMA comp channel:
+   1, if TX is not full, it's always writable.
+   2, if TX is full, should wait a 'RegisterLocalAddr' message to refresh
+      'TX buffer'.
+
+To-Do List
+----------
+- [ ] hiredis
+- [ ] rdma client & benchmark
+- [ ] POLLOUT event emulation for hiredis
+- [ ] auto-test suite is not implemented currently

src/Makefile

@@ -332,6 +332,21 @@ ifeq ($(BUILD_TLS),module)
 	TLS_MODULE_CFLAGS+=-DUSE_OPENSSL=$(BUILD_MODULE) $(OPENSSL_CFLAGS) -DBUILD_TLS_MODULE=$(BUILD_MODULE)
 endif
 
+RDMA_MODULE=
+RDMA_MODULE_NAME:=valkey-rdma$(PROG_SUFFIX).so
+RDMA_MODULE_CFLAGS:=$(FINAL_CFLAGS)
+ifeq ($(BUILD_RDMA),module)
+	FINAL_CFLAGS+=-DUSE_RDMA=$(BUILD_MODULE)
+	RDMA_PKGCONFIG := $(shell $(PKG_CONFIG) --exists librdmacm libibverbs && echo $$?)
+ifeq ($(RDMA_PKGCONFIG),0)
+	RDMA_LIBS=$(shell $(PKG_CONFIG) --libs librdmacm libibverbs)
+else
+	RDMA_LIBS=-lrdmacm -libverbs
+endif
+	RDMA_MODULE=$(RDMA_MODULE_NAME)
+	RDMA_MODULE_CFLAGS+=-DUSE_RDMA=$(BUILD_YES) -DBUILD_RDMA_MODULE $(RDMA_LIBS)
+endif
+
 ifndef V
     define MAKE_INSTALL
         @printf '    %b %b\n' $(LINKCOLOR)INSTALL$(ENDCOLOR) $(BINCOLOR)$(1)$(ENDCOLOR) 1>&2
@@ -409,7 +424,7 @@ ENGINE_TEST_OBJ:=$(sort $(patsubst unit/%.c,unit/%.o,$(ENGINE_TEST_FILES)))
 ENGINE_UNIT_TESTS:=$(ENGINE_NAME)-unit-tests$(PROG_SUFFIX)
 ALL_SOURCES=$(sort $(patsubst %.o,%.c,$(ENGINE_SERVER_OBJ) $(ENGINE_CLI_OBJ) $(ENGINE_BENCHMARK_OBJ)))
 
-all: $(SERVER_NAME) $(ENGINE_SENTINEL_NAME) $(ENGINE_CLI_NAME) $(ENGINE_BENCHMARK_NAME) $(ENGINE_CHECK_RDB_NAME) $(ENGINE_CHECK_AOF_NAME) $(TLS_MODULE)
+all: $(SERVER_NAME) $(ENGINE_SENTINEL_NAME) $(ENGINE_CLI_NAME) $(ENGINE_BENCHMARK_NAME) $(ENGINE_CHECK_RDB_NAME) $(ENGINE_CHECK_AOF_NAME) $(TLS_MODULE) $(RDMA_MODULE)
 	@echo ""
 	@echo "Hint: It's a good idea to run 'make test' ;)"
 	@echo ""
@@ -432,6 +447,7 @@ persist-settings: distclean
 	echo OPT=$(OPT) >> .make-settings
 	echo MALLOC=$(MALLOC) >> .make-settings
 	echo BUILD_TLS=$(BUILD_TLS) >> .make-settings
+	echo BUILD_RDMA=$(BUILD_RDMA) >> .make-settings
 	echo USE_SYSTEMD=$(USE_SYSTEMD) >> .make-settings
 	echo CFLAGS=$(CFLAGS) >> .make-settings
 	echo LDFLAGS=$(LDFLAGS) >> .make-settings
@@ -484,6 +500,10 @@ $(ENGINE_CHECK_AOF_NAME): $(SERVER_NAME)
 $(TLS_MODULE_NAME): $(SERVER_NAME)
 	$(QUIET_CC)$(CC) -o $@ tls.c -shared -fPIC $(TLS_MODULE_CFLAGS) $(TLS_CLIENT_LIBS)
 
+# valkey-rdma.so
+$(RDMA_MODULE_NAME): $(REDIS_SERVER_NAME)
+	$(QUIET_CC)$(CC) -o $@ rdma.c -shared -fPIC $(RDMA_MODULE_CFLAGS)
+
 # valkey-cli
 $(ENGINE_CLI_NAME): $(ENGINE_CLI_OBJ)
 	$(SERVER_LD) -o $@ $^ ../deps/hiredis/libhiredis.a ../deps/linenoise/linenoise.o $(FINAL_LIBS) $(TLS_CLIENT_LIBS)