2015-10-15 05:23:13 -04:00
|
|
|
proc log_file_matches {log pattern} {
|
|
|
|
set fp [open $log r]
|
|
|
|
set content [read $fp]
|
|
|
|
close $fp
|
|
|
|
string match $pattern $content
|
|
|
|
}
|
|
|
|
|
|
|
|
start_server {tags {"repl"}} {
|
|
|
|
set slave [srv 0 client]
|
|
|
|
set slave_host [srv 0 host]
|
|
|
|
set slave_port [srv 0 port]
|
|
|
|
set slave_log [srv 0 stdout]
|
|
|
|
start_server {} {
|
|
|
|
set master [srv 0 client]
|
|
|
|
set master_host [srv 0 host]
|
|
|
|
set master_port [srv 0 port]
|
|
|
|
|
|
|
|
# Configure the master in order to hang waiting for the BGSAVE
|
|
|
|
# operation, so that the slave remains in the handshake state.
|
|
|
|
$master config set repl-diskless-sync yes
|
|
|
|
$master config set repl-diskless-sync-delay 1000
|
|
|
|
|
|
|
|
# Use a short replication timeout on the slave, so that if there
|
|
|
|
# are no bugs the timeout is triggered in a reasonable amount
|
|
|
|
# of time.
|
|
|
|
$slave config set repl-timeout 5
|
|
|
|
|
|
|
|
# Start the replication process...
|
|
|
|
$slave slaveof $master_host $master_port
|
|
|
|
|
|
|
|
test {Slave enters handshake} {
|
|
|
|
wait_for_condition 50 1000 {
|
|
|
|
[string match *handshake* [$slave role]]
|
|
|
|
} else {
|
|
|
|
fail "Slave does not enter handshake state"
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
# But make the master unable to send
|
|
|
|
# the periodic newlines to refresh the connection. The slave
|
|
|
|
# should detect the timeout.
|
|
|
|
$master debug sleep 10
|
|
|
|
|
|
|
|
test {Slave is able to detect timeout during handshake} {
|
|
|
|
wait_for_condition 50 1000 {
|
|
|
|
[log_file_matches $slave_log "*Timeout connecting to the MASTER*"]
|
|
|
|
} else {
|
|
|
|
fail "Slave is not able to detect timeout"
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-07-06 11:24:00 -04:00
|
|
|
start_server {tags {"repl"}} {
|
2015-03-27 07:10:46 -04:00
|
|
|
set A [srv 0 client]
|
|
|
|
set A_host [srv 0 host]
|
|
|
|
set A_port [srv 0 port]
|
2010-07-06 11:24:00 -04:00
|
|
|
start_server {} {
|
2015-03-27 07:10:46 -04:00
|
|
|
set B [srv 0 client]
|
|
|
|
set B_host [srv 0 host]
|
|
|
|
set B_port [srv 0 port]
|
|
|
|
|
|
|
|
test {Set instance A as slave of B} {
|
|
|
|
$A slaveof $B_host $B_port
|
2012-04-30 04:55:03 -04:00
|
|
|
wait_for_condition 50 100 {
|
2015-03-27 07:10:46 -04:00
|
|
|
[lindex [$A role] 0] eq {slave} &&
|
|
|
|
[string match {*master_link_status:up*} [$A info replication]]
|
2012-04-30 04:55:03 -04:00
|
|
|
} else {
|
|
|
|
fail "Can't turn the instance into a slave"
|
|
|
|
}
|
|
|
|
}
|
2010-07-06 11:24:00 -04:00
|
|
|
|
2011-06-20 11:07:18 -04:00
|
|
|
test {BRPOPLPUSH replication, when blocking against empty list} {
|
|
|
|
set rd [redis_deferring_client]
|
|
|
|
$rd brpoplpush a b 5
|
|
|
|
r lpush a foo
|
2012-04-26 05:25:13 -04:00
|
|
|
wait_for_condition 50 100 {
|
2015-03-27 07:10:46 -04:00
|
|
|
[$A debug digest] eq [$B debug digest]
|
2012-04-26 05:25:13 -04:00
|
|
|
} else {
|
2015-03-27 07:10:46 -04:00
|
|
|
fail "Master and slave have different digest: [$A debug digest] VS [$B debug digest]"
|
2012-04-26 05:25:13 -04:00
|
|
|
}
|
2011-06-20 11:07:18 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
test {BRPOPLPUSH replication, list exists} {
|
|
|
|
set rd [redis_deferring_client]
|
|
|
|
r lpush c 1
|
|
|
|
r lpush c 2
|
|
|
|
r lpush c 3
|
|
|
|
$rd brpoplpush c d 5
|
|
|
|
after 1000
|
2015-03-27 07:10:46 -04:00
|
|
|
assert_equal [$A debug digest] [$B debug digest]
|
|
|
|
}
|
|
|
|
|
|
|
|
test {BLPOP followed by role change, issue #2473} {
|
|
|
|
set rd [redis_deferring_client]
|
|
|
|
$rd blpop foo 0 ; # Block while B is a master
|
|
|
|
|
|
|
|
# Turn B into master of A
|
|
|
|
$A slaveof no one
|
|
|
|
$B slaveof $A_host $A_port
|
|
|
|
wait_for_condition 50 100 {
|
|
|
|
[lindex [$B role] 0] eq {slave} &&
|
|
|
|
[string match {*master_link_status:up*} [$B info replication]]
|
|
|
|
} else {
|
|
|
|
fail "Can't turn the instance into a slave"
|
|
|
|
}
|
|
|
|
|
|
|
|
# Push elements into the "foo" list of the new slave.
|
|
|
|
# If the client is still attached to the instance, we'll get
|
|
|
|
# a desync between the two instances.
|
|
|
|
$A rpush foo a b c
|
|
|
|
after 100
|
|
|
|
|
|
|
|
wait_for_condition 50 100 {
|
|
|
|
[$A debug digest] eq [$B debug digest] &&
|
|
|
|
[$A lrange foo 0 -1] eq {a b c} &&
|
|
|
|
[$B lrange foo 0 -1] eq {a b c}
|
|
|
|
} else {
|
|
|
|
fail "Master and slave have different digest: [$A debug digest] VS [$B debug digest]"
|
|
|
|
}
|
2011-06-20 11:07:18 -04:00
|
|
|
}
|
2010-07-06 11:24:00 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-06-02 17:14:55 -04:00
|
|
|
start_server {tags {"repl"}} {
|
2010-05-14 14:50:58 -04:00
|
|
|
r set mykey foo
|
2014-07-31 14:39:49 -04:00
|
|
|
|
2010-06-02 16:23:52 -04:00
|
|
|
start_server {} {
|
2010-05-14 14:50:58 -04:00
|
|
|
test {Second server should have role master at first} {
|
|
|
|
s role
|
|
|
|
} {master}
|
2014-07-31 14:39:49 -04:00
|
|
|
|
2010-05-14 14:50:58 -04:00
|
|
|
test {SLAVEOF should start with link status "down"} {
|
|
|
|
r slaveof [srv -1 host] [srv -1 port]
|
|
|
|
s master_link_status
|
|
|
|
} {down}
|
2014-07-31 14:39:49 -04:00
|
|
|
|
2010-05-14 14:50:58 -04:00
|
|
|
test {The role should immediately be changed to "slave"} {
|
|
|
|
s role
|
|
|
|
} {slave}
|
|
|
|
|
|
|
|
wait_for_sync r
|
|
|
|
test {Sync should have transferred keys from master} {
|
|
|
|
r get mykey
|
|
|
|
} {foo}
|
2014-07-31 14:39:49 -04:00
|
|
|
|
2010-05-14 14:50:58 -04:00
|
|
|
test {The link status should be up} {
|
|
|
|
s master_link_status
|
|
|
|
} {up}
|
2014-07-31 14:39:49 -04:00
|
|
|
|
2010-05-14 14:50:58 -04:00
|
|
|
test {SET on the master should immediately propagate} {
|
|
|
|
r -1 set mykey bar
|
A reimplementation of blocking operation internals.
Redis provides support for blocking operations such as BLPOP or BRPOP.
This operations are identical to normal LPOP and RPOP operations as long
as there are elements in the target list, but if the list is empty they
block waiting for new data to arrive to the list.
All the clients blocked waiting for th same list are served in a FIFO
way, so the first that blocked is the first to be served when there is
more data pushed by another client into the list.
The previous implementation of blocking operations was conceived to
serve clients in the context of push operations. For for instance:
1) There is a client "A" blocked on list "foo".
2) The client "B" performs `LPUSH foo somevalue`.
3) The client "A" is served in the context of the "B" LPUSH,
synchronously.
Processing things in a synchronous way was useful as if "A" pushes a
value that is served by "B", from the point of view of the database is a
NOP (no operation) thing, that is, nothing is replicated, nothing is
written in the AOF file, and so forth.
However later we implemented two things:
1) Variadic LPUSH that could add multiple values to a list in the
context of a single call.
2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH"
side effect when receiving data.
This forced us to make the synchronous implementation more complex. If
client "B" is waiting for data, and "A" pushes three elemnents in a
single call, we needed to propagate an LPUSH with a missing argument
in the AOF and replication link. We also needed to make sure to
replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not
happened to serve another blocking client into another list ;)
This were complex but with a few of mutually recursive functions
everything worked as expected... until one day we introduced scripting
in Redis.
Scripting + synchronous blocking operations = Issue #614.
Basically you can't "rewrite" a script to have just a partial effect on
the replicas and AOF file if the script happened to serve a few blocked
clients.
The solution to all this problems, implemented by this commit, is to
change the way we serve blocked clients. Instead of serving the blocked
clients synchronously, in the context of the command performing the PUSH
operation, it is now an asynchronous and iterative process:
1) If a key that has clients blocked waiting for data is the subject of
a list push operation, We simply mark keys as "ready" and put it into a
queue.
2) Every command pushing stuff on lists, as a variadic LPUSH, a script,
or whatever it is, is replicated verbatim without any rewriting.
3) Every time a Redis command, a MULTI/EXEC block, or a script,
completed its execution, we run the list of keys ready to serve blocked
clients (as more data arrived), and process this list serving the
blocked clients.
4) As a result of "3" maybe more keys are ready again for other clients
(as a result of BRPOPLPUSH we may have push operations), so we iterate
back to step "3" if it's needed.
The new code has a much simpler semantics, and a simpler to understand
implementation, with the disadvantage of not being able to "optmize out"
a PUSH+BPOP as a No OP.
This commit will be tested with care before the final merge, more tests
will be added likely.
2012-09-04 04:37:49 -04:00
|
|
|
|
|
|
|
wait_for_condition 500 100 {
|
|
|
|
[r 0 get mykey] eq {bar}
|
|
|
|
} else {
|
|
|
|
fail "SET on master did not propagated on slave"
|
|
|
|
}
|
|
|
|
}
|
2011-10-17 04:40:11 -04:00
|
|
|
|
|
|
|
test {FLUSHALL should replicate} {
|
|
|
|
r -1 flushall
|
|
|
|
if {$::valgrind} {after 2000}
|
|
|
|
list [r -1 dbsize] [r 0 dbsize]
|
|
|
|
} {0 0}
|
2014-06-23 03:08:51 -04:00
|
|
|
|
|
|
|
test {ROLE in master reports master with a slave} {
|
|
|
|
set res [r -1 role]
|
|
|
|
lassign $res role offset slaves
|
|
|
|
assert {$role eq {master}}
|
|
|
|
assert {$offset > 0}
|
|
|
|
assert {[llength $slaves] == 1}
|
|
|
|
lassign [lindex $slaves 0] master_host master_port slave_offset
|
2014-06-26 16:13:46 -04:00
|
|
|
assert {$slave_offset <= $offset}
|
2014-06-23 03:08:51 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
test {ROLE in slave reports slave in connected state} {
|
|
|
|
set res [r role]
|
|
|
|
lassign $res role master_host master_port slave_state slave_offset
|
|
|
|
assert {$role eq {slave}}
|
|
|
|
assert {$slave_state eq {connected}}
|
|
|
|
}
|
2010-05-14 14:50:58 -04:00
|
|
|
}
|
|
|
|
}
|
2012-01-06 11:28:40 -05:00
|
|
|
|
2014-10-24 03:49:22 -04:00
|
|
|
foreach dl {no yes} {
|
|
|
|
start_server {tags {"repl"}} {
|
|
|
|
set master [srv 0 client]
|
|
|
|
$master config set repl-diskless-sync $dl
|
|
|
|
set master_host [srv 0 host]
|
|
|
|
set master_port [srv 0 port]
|
|
|
|
set slaves {}
|
|
|
|
set load_handle0 [start_write_load $master_host $master_port 3]
|
|
|
|
set load_handle1 [start_write_load $master_host $master_port 5]
|
|
|
|
set load_handle2 [start_write_load $master_host $master_port 20]
|
|
|
|
set load_handle3 [start_write_load $master_host $master_port 8]
|
|
|
|
set load_handle4 [start_write_load $master_host $master_port 4]
|
2012-01-06 11:28:40 -05:00
|
|
|
start_server {} {
|
|
|
|
lappend slaves [srv 0 client]
|
|
|
|
start_server {} {
|
|
|
|
lappend slaves [srv 0 client]
|
2014-10-24 03:49:22 -04:00
|
|
|
start_server {} {
|
|
|
|
lappend slaves [srv 0 client]
|
|
|
|
test "Connect multiple slaves at the same time (issue #141), diskless=$dl" {
|
2015-03-27 07:10:46 -04:00
|
|
|
# Send SLAVEOF commands to slaves
|
2014-10-24 03:49:22 -04:00
|
|
|
[lindex $slaves 0] slaveof $master_host $master_port
|
|
|
|
[lindex $slaves 1] slaveof $master_host $master_port
|
|
|
|
[lindex $slaves 2] slaveof $master_host $master_port
|
|
|
|
|
2014-11-24 05:54:53 -05:00
|
|
|
# Wait for all the three slaves to reach the "online"
|
|
|
|
# state from the POV of the master.
|
2014-10-24 03:49:22 -04:00
|
|
|
set retry 500
|
|
|
|
while {$retry} {
|
|
|
|
set info [r -3 info]
|
|
|
|
if {[string match {*slave0:*state=online*slave1:*state=online*slave2:*state=online*} $info]} {
|
|
|
|
break
|
|
|
|
} else {
|
|
|
|
incr retry -1
|
|
|
|
after 100
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if {$retry == 0} {
|
|
|
|
error "assertion:Slaves not correctly synchronized"
|
|
|
|
}
|
|
|
|
|
2014-11-24 05:54:53 -05:00
|
|
|
# Wait that slaves acknowledge they are online so
|
|
|
|
# we are sure that DBSIZE and DEBUG DIGEST will not
|
|
|
|
# fail because of timing issues.
|
|
|
|
wait_for_condition 500 100 {
|
|
|
|
[lindex [[lindex $slaves 0] role] 3] eq {connected} &&
|
|
|
|
[lindex [[lindex $slaves 1] role] 3] eq {connected} &&
|
|
|
|
[lindex [[lindex $slaves 2] role] 3] eq {connected}
|
|
|
|
} else {
|
|
|
|
fail "Slaves still not connected after some time"
|
|
|
|
}
|
|
|
|
|
2014-10-24 03:49:22 -04:00
|
|
|
# Stop the write load
|
|
|
|
stop_write_load $load_handle0
|
|
|
|
stop_write_load $load_handle1
|
|
|
|
stop_write_load $load_handle2
|
|
|
|
stop_write_load $load_handle3
|
|
|
|
stop_write_load $load_handle4
|
|
|
|
|
2014-11-24 05:54:53 -05:00
|
|
|
# Make sure that slaves and master have same
|
|
|
|
# number of keys
|
2014-10-24 03:49:22 -04:00
|
|
|
wait_for_condition 500 100 {
|
|
|
|
[$master dbsize] == [[lindex $slaves 0] dbsize] &&
|
|
|
|
[$master dbsize] == [[lindex $slaves 1] dbsize] &&
|
|
|
|
[$master dbsize] == [[lindex $slaves 2] dbsize]
|
|
|
|
} else {
|
|
|
|
fail "Different number of keys between masted and slave after too long time."
|
|
|
|
}
|
2012-04-28 09:39:00 -04:00
|
|
|
|
2014-10-24 03:49:22 -04:00
|
|
|
# Check digests
|
|
|
|
set digest [$master debug digest]
|
|
|
|
set digest0 [[lindex $slaves 0] debug digest]
|
|
|
|
set digest1 [[lindex $slaves 1] debug digest]
|
|
|
|
set digest2 [[lindex $slaves 2] debug digest]
|
|
|
|
assert {$digest ne 0000000000000000000000000000000000000000}
|
|
|
|
assert {$digest eq $digest0}
|
|
|
|
assert {$digest eq $digest1}
|
|
|
|
assert {$digest eq $digest2}
|
2012-04-28 09:39:00 -04:00
|
|
|
}
|
2014-10-24 03:49:22 -04:00
|
|
|
}
|
|
|
|
}
|
2012-01-06 11:28:40 -05:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|