CLD replication (WIP)

PATCH Superseded Jeff Garzik 1 participant 2 messages Jul 31, 2009 – Aug 6, 2009

lore

Share & tools

lore

Jeff Garzik

author

2009-07-31 11:15 UTC #0 lore raw

PATCH 1/1 CLD replication (WIP)

[resend #1... not sure where first try went]

Attached is the current CLD replication patch, which takes CLD from being a single-node service to a fully replicated, highly available service.

The server implementation should be complete.

The current merge blocker is needed code in libcldc, which does not yet properly "hunt" for a master, among a group of peer CLD replicas in a CLD cell.

This will be a big milestone for CLD, when merged. The next milestone will be adding the needed strict-cache-coherence caching semantics to CLD server and client lib.

This patch was generated against git commit 511b8dafb233ee85e60ddf7eda212f87963e150c.

Quoted 10 lines

 server/cld.h      |   20 +++
 server/cldb.c     |   69 +++++++++++--
 server/cldb.h     |    9 +
 server/cldbadm.c  |    8 -
 server/server.c   |  286 +++++++++++++++++++++++++++++++++++++++++++++++++++---
 test/pid-exists   |   13 +-
 test/prep-db	   |   19 ++-
 test/start-daemon |   26 ++++
 test/stop-daemon  |   32 ++++--
 9 files changed, 428 insertions(+), 54 deletions(-)

server/cld.h +20 -0

index 21f103d..08e6b12 100644
@@ -91,6 +91,15 @@ struct msg_params {
 	size_t			msg_len;
 };
 
+enum st_cldb {
+	ST_CLDB_INIT,
+	ST_CLDB_OPEN,
+	ST_CLDB_ACTIVE,
+	ST_CLDB_MASTER,
+	ST_CLDB_SLAVE,
+	ST_CLDBNUM
+};
+
 struct server_stats {
 	unsigned long		poll;		/* number polls */
 	unsigned long		event;		/* events dispatched */

@@ -114,6 +123,17 @@ struct server {
 	int			pid_fd;
 
 	char			*port;		/* bind port */
+	unsigned short		rep_port;	/* db4 replication port */
+
+	char			*myhost;
+	char			*force_myhost;
+	GList			*rep_remotes;
+
+	unsigned int		n_peers;	/* total peers in cell */
+
+	int			rep_pipe[2];
+
+	enum st_cldb		state_cldb, state_cldb_new;
 
 	struct cldb		cldb;		/* database info */

server/cldb.c +61 -8

119 lines not on this page · raw message

server/cldb.h +8 -1

index d28f732..f8f26db 100644
@@ -107,6 +107,11 @@ enum db_event {
 	CLDB_EV_NONE, CLDB_EV_CLIENT, CLDB_EV_MASTER, CLDB_EV_ELECTED
 };
 
+struct db_remote {	/* remotes for cldb_init */
+	char		*host;
+	unsigned short	port;
+};
+
 struct cldb {
 	bool		is_master;
 	bool		keyed;			/* using encryption? */

@@ -133,7 +138,9 @@ struct cldb {
 
 extern int cldb_init(struct cldb *cldb, const char *db_home, const char *db_password,
 	      unsigned int env_flags, const char *errpfx, bool do_syslog,
-	      unsigned int flags, void (*cb)(enum db_event));
+	      GList *remotes, char *rep_host, unsigned short rep_port,
+	      int n_peers, void (*cb)(enum db_event));
+extern int cldb_up(struct cldb *cldb, unsigned int flags);
 extern void cldb_down(struct cldb *cldb);
 extern void cldb_fini(struct cldb *cldb);

server/cldbadm.c +5 -3

index 37e8e36..9342f66 100644
@@ -78,7 +78,8 @@ int main(int argc, char *argv[])
 	}
 
 	if (cldb_init(&cld_adm.cldb, cld_adm.data_dir, NULL,
-		      DB_RECOVER, "cldbadm", false, 0, NULL))
+		      DB_RECOVER, "cldbadm", false,
+		      NULL, NULL, 0, 0, NULL))
 		goto err_dbopen;
 
 	switch (cld_adm.mode) {

@@ -142,8 +143,9 @@ static error_t parse_opt(int key, char *arg, struct argp_state *state)
  * Stubs for contents of cldb.c
  */
 int cldb_init(struct cldb *cldb, const char *db_home, const char *db_password,
-	      unsigned int env_flags, const char *errpfx, bool do_syslog,
-	      unsigned int flags, void (*cb)(enum db_event))
+              unsigned int env_flags, const char *errpfx, bool do_syslog,
+              GList *remotes, char *rep_host, unsigned short rep_port,
+              int n_peers, void (*cb)(enum db_event))
 {
 
 	return 0;

server/server.c +271 ~~-15~~

404 lines not on this page · raw message

test/pid-exists +8 -5

index 351b4f1..4fa2275 100755
@@ -1,9 +1,12 @@
 #!/bin/sh
 
-if [ ! -f cld.pid ]
-then
-	echo "pid file not found."
-	exit 1
-fi
+for n in 1 2 3
+do
+	if [ ! -f cld$n.pid ]
+	then
+		echo "cld$n.pid not found."
+		exit 1
+	fi
+done
 
 exit 0

test/prep-db +11 -8

index 353ca4a..3e4fb60 100755
@@ -2,13 +2,16 @@
 
 DATADIR=data
 
-mkdir -p $DATADIR
-
-if [ ! -d $DATADIR ]
-then
-	rm -rf $DATADIR
-	echo "test database dir not found."
-	exit 1
-fi
+for n in 1 2 3
+do
+	mkdir -p $DATADIR/n$n/data
+
+	if [ ! -d $DATADIR/n$n/data ]
+	then
+		rm -rf $DATADIR
+		echo "test database dir for node $n not found."
+		exit 1
+	fi
+done
 
 exit 0

test/start-daemon +22 -4

index 4cb9fd7..06b3250 100755
@@ -1,13 +1,31 @@
 #!/bin/sh
 
-if [ -f cld.pid ]
+if [ -f cld1.pid -o -f cld2.pid -o -f cld3.pid ]
 then
-	echo "pid file found.  daemon still running?"
+	echo "pid file found.  daemons still running?"
 	exit 1
 fi
 
-../server/cld -P cld.pid -d "$PWD/data" -p 18181 -E
+../server/cld -d "$PWD/data/n1/data" -p 18181 -r 19181 -P cld1.pid -E	\
+	-D 2 -S 3			\
+	-m localhost.localdomain	\
+	-R localhost.localdomain:19182	\
+	-R localhost.localdomain:19183
 
-sleep 3
+../server/cld -d "$PWD/data/n2/data" -p 18182 -r 19182 -P cld2.pid -E	\
+	-D 2 -S 3			\
+	-m localhost.localdomain	\
+	-R localhost.localdomain:19181	\
+	-R localhost.localdomain:19183
+
+../server/cld -d "$PWD/data/n3/data" -p 18183 -r 19183 -P cld3.pid -E	\
+	-D 2 -S 3			\
+	-m localhost.localdomain	\
+	-R localhost.localdomain:19181	\
+	-R localhost.localdomain:19182
+sleep 1
+
+echo "      start-daemon: Waiting 20s, for daemons to start up..."
+sleep 20
 
 exit 0

test/stop-daemon +22 ~~-10~~

index 221dc46..d00fda6 100755
@@ -1,23 +1,35 @@
 #!/bin/sh
 
-if [ ! -f cld.pid ]
-then
-	echo no daemon pid file found.
-	exit 1
-fi
+for n in 1 2 3
+do
+	if [ ! -f cld$n.pid ]
+	then
+		echo "      stop-daemon: cld$n.pid not found."
+		exit 1
+	fi
+done
+
 
-kill `cat cld.pid`
+kill `cat cld1.pid cld2.pid cld3.pid`
 
 for ((n = 0; n < 10; n++))
 do
-	if [ ! -f cld.pid ]
+	if [ -f cld1.pid -o -f cld2.pid -o -f cld3.pid ]
 	then
+		sleep 1
+	else
 		exit 0
 	fi
 
-	sleep 1
 done
 
-echo "PID file not removed, after signal sent."
-rm -f cld.pid
+for n in 1 2 3
+do
+	if [ -f cld$n.pid ]
+	then
+		echo "      stop-daemon: cld$n.pid found, after signal sent."
+	fi
+done
+
+rm -f cld?.pid
 exit 1