From 90f3856fd5a1c7d30bf4450772923bf4a16993b6 Mon Sep 17 00:00:00 2001 From: Oran Agra Date: Thu, 28 May 2020 08:21:24 +0300 Subject: [PATCH] revive meaningful offset tests --- tests/integration/psync2-pingoff.tcl | 212 +++++++++++++++++++++++++++ tests/test_helper.tcl | 1 + 2 files changed, 213 insertions(+) create mode 100644 tests/integration/psync2-pingoff.tcl diff --git a/tests/integration/psync2-pingoff.tcl b/tests/integration/psync2-pingoff.tcl new file mode 100644 index 000000000..5d8459a92 --- /dev/null +++ b/tests/integration/psync2-pingoff.tcl @@ -0,0 +1,212 @@ +# Test the meaningful offset implementation to make sure masters +# are able to PSYNC with replicas even if the replication stream +# has pending PINGs at the end. + +start_server {tags {"psync2"}} { +start_server {} { + # Config + set debug_msg 0 ; # Enable additional debug messages + + for {set j 0} {$j < 2} {incr j} { + set R($j) [srv [expr 0-$j] client] + set R_host($j) [srv [expr 0-$j] host] + set R_port($j) [srv [expr 0-$j] port] + $R($j) CONFIG SET repl-ping-replica-period 1 + if {$debug_msg} {puts "Log file: [srv [expr 0-$j] stdout]"} + } + + # Setup replication + test "PSYNC2 meaningful offset: setup" { + $R(1) replicaof $R_host(0) $R_port(0) + $R(0) set foo bar + wait_for_condition 50 1000 { + [status $R(1) master_link_status] == "up" && + [$R(0) dbsize] == 1 && [$R(1) dbsize] == 1 + } else { + fail "Replicas not replicating from master" + } + } + + test "PSYNC2 meaningful offset: write and wait replication" { + $R(0) INCR counter + $R(0) INCR counter + $R(0) INCR counter + wait_for_condition 50 1000 { + [$R(0) GET counter] eq [$R(1) GET counter] + } else { + fail "Master and replica don't agree about counter" + } + } + + # In this test we'll make sure the replica will get stuck, but with + # an active connection: this way the master will continue to send PINGs + # every second (we modified the PING period earlier) + test "PSYNC2 meaningful offset: pause replica and promote it" { + $R(1) MULTI + $R(1) DEBUG SLEEP 5 + $R(1) SLAVEOF NO ONE + $R(1) EXEC + $R(1) ping ; # Wait for it to return back available + } + + test "Make the old master a replica of the new one and check conditions" { + set sync_partial [status $R(1) sync_partial_ok] + assert {$sync_partial == 0} + $R(0) REPLICAOF $R_host(1) $R_port(1) + wait_for_condition 50 1000 { + [status $R(1) sync_partial_ok] == 1 + } else { + fail "The new master was not able to partial sync" + } + } +}} + + +start_server {tags {"psync2"}} { +start_server {} { +start_server {} { +start_server {} { +start_server {} { + test {pings at the end of replication stream are ignored for psync} { + set master [srv -4 client] + set master_host [srv -4 host] + set master_port [srv -4 port] + set replica1 [srv -3 client] + set replica2 [srv -2 client] + set replica3 [srv -1 client] + set replica4 [srv -0 client] + + $replica1 replicaof $master_host $master_port + $replica2 replicaof $master_host $master_port + $replica3 replicaof $master_host $master_port + $replica4 replicaof $master_host $master_port + wait_for_condition 50 1000 { + [status $master connected_slaves] == 4 + } else { + fail "replicas didn't connect" + } + + $master incr x + wait_for_condition 50 1000 { + [$replica1 get x] == 1 && [$replica2 get x] == 1 && + [$replica3 get x] == 1 && [$replica4 get x] == 1 + } else { + fail "replicas didn't get incr" + } + + # disconnect replica1 and replica2 + # and wait for the master to send a ping to replica3 and replica4 + $replica1 replicaof no one + $replica2 replicaof 127.0.0.1 1 ;# we can't promote it to master since that will cycle the replication id + $master config set repl-ping-replica-period 1 + after 1500 + + # make everyone sync from the replica1 that didn't get the last ping from the old master + # replica4 will keep syncing from the old master which now syncs from replica1 + # and replica2 will re-connect to the old master (which went back in time) + set new_master_host [srv -3 host] + set new_master_port [srv -3 port] + $replica3 replicaof $new_master_host $new_master_port + $master replicaof $new_master_host $new_master_port + $replica2 replicaof $master_host $master_port + wait_for_condition 50 1000 { + [status $replica2 master_link_status] == "up" && + [status $replica3 master_link_status] == "up" && + [status $replica4 master_link_status] == "up" && + [status $master master_link_status] == "up" + } else { + fail "replicas didn't connect" + } + + # make sure replication is still alive and kicking + $replica1 incr x + wait_for_condition 50 1000 { + [$replica2 get x] == 2 && + [$replica3 get x] == 2 && + [$replica4 get x] == 2 && + [$master get x] == 2 + } else { + fail "replicas didn't get incr" + } + + # make sure there are full syncs other than the initial ones + assert_equal [status $master sync_full] 4 + assert_equal [status $replica1 sync_full] 0 + assert_equal [status $replica2 sync_full] 0 + assert_equal [status $replica3 sync_full] 0 + assert_equal [status $replica4 sync_full] 0 + + # force psync + $master client kill type master + $replica2 client kill type master + $replica3 client kill type master + $replica4 client kill type master + + # make sure replication is still alive and kicking + $replica1 incr x + wait_for_condition 50 1000 { + [$replica2 get x] == 3 && + [$replica3 get x] == 3 && + [$replica4 get x] == 3 && + [$master get x] == 3 + } else { + fail "replicas didn't get incr" + } + + # make sure there are full syncs other than the initial ones + assert_equal [status $master sync_full] 4 + assert_equal [status $replica1 sync_full] 0 + assert_equal [status $replica2 sync_full] 0 + assert_equal [status $replica3 sync_full] 0 + assert_equal [status $replica4 sync_full] 0 +} +}}}}} + +start_server {tags {"psync2"}} { +start_server {} { +start_server {} { + + for {set j 0} {$j < 3} {incr j} { + set R($j) [srv [expr 0-$j] client] + set R_host($j) [srv [expr 0-$j] host] + set R_port($j) [srv [expr 0-$j] port] + $R($j) CONFIG SET repl-ping-replica-period 1 + } + + test "Chained replicas disconnect when replica re-connect with the same master" { + # Add a second replica as a chained replica of the current replica + $R(1) replicaof $R_host(0) $R_port(0) + $R(2) replicaof $R_host(1) $R_port(1) + wait_for_condition 50 1000 { + [status $R(2) master_link_status] == "up" + } else { + fail "Chained replica not replicating from its master" + } + + # Do a write on the master, and wait for 3 seconds for the master to + # send some PINGs to its replica + $R(0) INCR counter2 + after 2000 + set sync_partial_master [status $R(0) sync_partial_ok] + set sync_partial_replica [status $R(1) sync_partial_ok] + $R(0) CONFIG SET repl-ping-replica-period 100 + + # Disconnect the master's direct replica + $R(0) client kill type replica + wait_for_condition 50 1000 { + [status $R(1) master_link_status] == "up" && + [status $R(2) master_link_status] == "up" && + [status $R(0) sync_partial_ok] == $sync_partial_master + 1 && + [status $R(1) sync_partial_ok] == $sync_partial_replica + 1 + } else { + fail "Disconnected replica failed to PSYNC with master" + } + + # Verify that the replica and its replica's meaningful and real + # offsets match with the master + assert_equal [status $R(0) master_repl_offset] [status $R(1) master_repl_offset] + assert_equal [status $R(0) master_repl_offset] [status $R(2) master_repl_offset] + assert_equal [status $R(0) master_repl_meaningful_offset] [status $R(1) master_repl_meaningful_offset] + assert_equal [status $R(0) master_repl_meaningful_offset] [status $R(2) master_repl_meaningful_offset] + } +}}} diff --git a/tests/test_helper.tcl b/tests/test_helper.tcl index 05e45b999..de0a64728 100644 --- a/tests/test_helper.tcl +++ b/tests/test_helper.tcl @@ -47,6 +47,7 @@ set ::all_tests { integration/logging integration/psync2 integration/psync2-reg + integration/psync2-pingoff unit/pubsub unit/slowlog unit/scripting