Introduce Valkey Over RDMA transport (experimental) (#477)

Adds an option to build RDMA support as a module:

    make BUILD_RDMA=module

To start valkey-server with RDMA, use a command line like the following:

    ./src/valkey-server --loadmodule src/valkey-rdma.so \
        port=6379 bind=xx.xx.xx.xx

* Implement server side of connection module only, this means we can
*NOT*
  compile RDMA support as built-in.

* Add necessary information in README.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

Because the lack of RDMA support from TCL, use a simple C program to
test
Valkey Over RDMA (under tests/rdma/). This is a quite raw version with
basic
library dependence: libpthread, libibverbs, librdmacm. Run using the
script:

    ./runtest-rdma [ OPTIONS ]

To run RDMA in GitHub actions, a kernel module RXE for emulated soft
RDMA, needs
to be installed. The kernel module source code is fetched a repo
containing only
the RXE kernel driver from the Linux kernel, but stored in an separate
repo to
avoid cloning the whole Linux kernel repo.

----

Since 2021/06, I created a
[PR](redis/redis#9161) for *Redis Over RDMA*
proposal. Then I did some work to [fully abstract connection and make
TLS dynamically loadable](redis/redis#9320), a
new connection type could be built into Redis statically, or a separated
shared library(loaded by Redis on startup) since Redis 7.2.0.

Base on the new connection framework, I created a new
[PR](redis/redis#11182), some
guys(@xiezhq-hermann @zhangyiming1201 @JSpewock @uvletter @FujiZ)
noticed, played and tested this PR. However, because of the lack of time
and knowledge from the maintainers, this PR has been pending about 2
years.

Related doc: [Introduce *Valkey Over RDMA*
specification](valkey-io/valkey-doc#123). (same
as Redis, and this should be same)

Changes in this PR:
- implement *Valkey Over RDMA*. (compact the Valkey style)

Finally, if this feature is considered to merge, I volunteer to maintain
it.

---------

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

.github/workflows/ci.yml

@@ -44,6 +44,26 @@ jobs:
       - name: module api test
         run: CFLAGS='-Werror' ./runtest-moduleapi --verbose --dump-logs
 
+  test-rdma:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+      - name: make
+        run: |
+          sudo apt-get install librdmacm-dev libibverbs-dev
+          make BUILD_RDMA=module
+      - name: clone-rxe-kmod
+        run: |
+          mkdir -p tests/rdma/rxe
+          git clone https://github.com/pizhenwei/rxe.git tests/rdma/rxe
+          make -C tests/rdma/rxe
+      - name: clear-kernel-log
+        run: sudo dmesg -c > /dev/null
+      - name: test
+        run: sudo ./runtest-rdma --install-rxe
+      - name: show-kernel-log
+        run: sudo dmesg -c
+
   build-debian-old:
     runs-on: ubuntu-latest
     container: debian:buster

.gitignore

@@ -47,3 +47,4 @@ redis.code-workspace
 .swp
 nodes*.conf
 tests/cluster/tmp/*
+tests/rdma/rdma-test

README.md

@@ -31,6 +31,12 @@ libssl-dev on Debian/Ubuntu) and run:
 
     % make BUILD_TLS=yes
 
+To build with experimental 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
+
 To build with systemd support, you'll need systemd development libraries (such 
 as libsystemd-dev on Debian/Ubuntu or systemd-devel on CentOS) and run:
 
@@ -155,6 +161,38 @@ Running Valkey with TLS:
 Please consult the [TLS.md](TLS.md) file for more information on
 how to use Valkey with TLS.
 
+Running Valkey with RDMA:
+------------------
+
+Note that Valkey Over RDMA is an experimental feature.
+It may be changed or removed in any minor or major version.
+Currently, it is only supported on Linux.
+
+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:
+
+    192.168.122.100:6379> 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
+
+
 Playing with Valkey
 ------------------
 

runtest-rdma

@@ -0,0 +1 @@
+./tests/rdma/run.py $*

src/Makefile

@@ -337,6 +337,28 @@ ifeq ($(BUILD_TLS),module)
 	TLS_MODULE_CFLAGS+=-DUSE_OPENSSL=$(BUILD_MODULE) $(OPENSSL_CFLAGS) -DBUILD_TLS_MODULE=$(BUILD_MODULE)
 endif
 
+BUILD_RDMA:=no
+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 $(RDMA_LIBS)
+else
+ifeq ($(BUILD_RDMA),no)
+    # disable RDMA, do nothing
+else
+    $(error "RDMA is only supported as module (BUILD_RDMA=module), or disabled (BUILD_RDMA=no)")
+endif
+endif
+
 ifndef V
     define MAKE_INSTALL
         @printf '    %b %b\n' $(LINKCOLOR)INSTALL$(ENDCOLOR) $(BINCOLOR)$(1)$(ENDCOLOR) 1>&2
@@ -414,7 +436,7 @@ ENGINE_TEST_OBJ:=$(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) $(RDMA_MODULE)
 	@echo ""
 	@echo "Hint: It's a good idea to run 'make test' ;)"
 	@echo ""
@@ -437,6 +459,7 @@ persist-settings: distclean
 	echo OPT=$(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
@@ -489,6 +512,10 @@ $(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)