From 0dacd68163bd5454e0108e7dd02826624b775fb7 Mon Sep 17 00:00:00 2001 From: christianEQ Date: Thu, 11 Nov 2021 01:41:28 +0000 Subject: [PATCH] added tests for flash psync Former-commit-id: 79f7376a4fea2de9bd06c06d96f3f98ee7308874 --- tests/integration/replication-psync-flash.tcl | 135 ++++++++++++++++++ tests/test_helper.tcl | 1 + 2 files changed, 136 insertions(+) create mode 100644 tests/integration/replication-psync-flash.tcl diff --git a/tests/integration/replication-psync-flash.tcl b/tests/integration/replication-psync-flash.tcl new file mode 100644 index 000000000..5cad127f3 --- /dev/null +++ b/tests/integration/replication-psync-flash.tcl @@ -0,0 +1,135 @@ +# Creates a master-slave pair and breaks the link continuously to force +# partial resyncs attempts, all this while flooding the master with +# write queries. +# +# You can specify backlog size, ttl, delay before reconnection, test duration +# in seconds, and an additional condition to verify at the end. +# +# If reconnect is > 0, the test actually try to break the connection and +# reconnect with the master, otherwise just the initial synchronization is +# checked for consistency. +proc test_psync {descr duration backlog_size backlog_ttl delay cond mdl sdl reconnect} { + start_server {tags {"repl"}} { + start_server [list tags {flash} overrides [list storage-provider {flash ./rocks.db} delete-on-evict no storage-flush-period 10]] { + + set master [srv -1 client] + set master_host [srv -1 host] + set master_port [srv -1 port] + set slave [srv 0 client] + + set load_handle0 [start_bg_complex_data $master_host $master_port 9 100000] + set load_handle1 [start_bg_complex_data $master_host $master_port 11 100000] + set load_handle2 [start_bg_complex_data $master_host $master_port 12 100000] + + test {Slave should be able to synchronize with the master} { + $slave slaveof $master_host $master_port + wait_for_condition 50 100 { + [lindex [r role] 0] eq {slave} && + [lindex [r role] 3] eq {connected} + } else { + fail "Replication not started." + } + } + + # Check that the background clients are actually writing. + test {Detect write load to master} { + wait_for_condition 50 1000 { + [$master dbsize] > 100 + } else { + fail "Can't detect write load from background clients." + } + } + + test "Test replication partial resync: $descr (diskless: $mdl, $sdl, reconnect: $reconnect)" { + # Now while the clients are writing data, break the maste-slave + # link multiple times. + if ($reconnect) { + for {set j 0} {$j < $duration*10} {incr j} { + after 100 + # catch {puts "MASTER [$master dbsize] keys, REPLICA [$slave dbsize] keys"} + + if {($j % 20) == 0} { + catch { + $slave debug restart + } + } + } + } + stop_bg_complex_data $load_handle0 + stop_bg_complex_data $load_handle1 + stop_bg_complex_data $load_handle2 + + # Wait for the slave to reach the "online" + # state from the POV of the master. + set retry 5000 + while {$retry} { + set info [$master info] + if {[string match {*slave0:*state=online*} $info]} { + break + } else { + incr retry -1 + after 100 + } + } + if {$retry == 0} { + error "assertion:Slave not correctly synchronized" + } + + # Wait that slave acknowledge it is online so + # we are sure that DBSIZE and DEBUG DIGEST will not + # fail because of timing issues. (-LOADING error) + wait_for_condition 5000 100 { + [lindex [$slave role] 3] eq {connected} + } else { + fail "Slave still not connected after some time" + } + + set retry 10 + while {$retry && ([$master debug digest] ne [$slave debug digest])}\ + { + after 1000 + incr retry -1 + } + assert {[$master dbsize] > 0} + + if {[$master debug digest] ne [$slave debug digest]} { + set csv1 [csvdump r] + set csv2 [csvdump {r -1}] + set fd [open /tmp/repldump1.txt w] + puts -nonewline $fd $csv1 + close $fd + set fd [open /tmp/repldump2.txt w] + puts -nonewline $fd $csv2 + close $fd + puts "Master - Replica inconsistency" + puts "Run diff -u against /tmp/repldump*.txt for more info" + } + assert_equal [r debug digest] [r -1 debug digest] + eval $cond + } + } + } +} + +foreach mdl {no yes} { + foreach sdl {disabled swapdb} { + test_psync {no reconnection, just sync} 6 1000000 3600 0 { + } $mdl $sdl 0 + + test_psync {ok psync} 6 100000000 3600 0 { + assert {[s -1 sync_partial_ok] > 0} + } $mdl $sdl 1 + + test_psync {no backlog} 6 100 3600 0.5 { + assert {[s -1 sync_partial_err] > 0} + } $mdl $sdl 1 + + test_psync {ok after delay} 3 100000000 3600 3 { + assert {[s -1 sync_partial_ok] > 0} + } $mdl $sdl 1 + + test_psync {backlog expired} 3 100000000 1 3 { + assert {[s -1 sync_partial_err] > 0} + } $mdl $sdl 1 + } +} diff --git a/tests/test_helper.tcl b/tests/test_helper.tcl index 2e200c35a..2ac904d20 100644 --- a/tests/test_helper.tcl +++ b/tests/test_helper.tcl @@ -47,6 +47,7 @@ set ::all_tests { integration/replication-3 integration/replication-4 integration/replication-psync + integration/replication-psync-flash integration/replication-active integration/replication-multimaster integration/replication-multimaster-connect