1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
|
# Cluster helper functions
# Check if cluster configuration is consistent.
proc cluster_config_consistent {} {
for {set j 0} {$j < [llength $::servers]} {incr j} {
if {$j == 0} {
set base_cfg [R $j cluster slots]
set base_secret [R $j debug internal_secret]
} else {
if {[R $j cluster slots] != $base_cfg || [R $j debug internal_secret] != $base_secret} {
return 0
}
}
}
return 1
}
# Check if cluster size is consistent.
proc cluster_size_consistent {cluster_size} {
for {set j 0} {$j < $cluster_size} {incr j} {
if {[CI $j cluster_known_nodes] ne $cluster_size} {
return 0
}
}
return 1
}
# Wait for cluster configuration to propagate and be consistent across nodes.
proc wait_for_cluster_propagation {} {
wait_for_condition 50 100 {
[cluster_config_consistent] eq 1
} else {
fail "cluster config did not reach a consistent state"
}
}
# Wait for cluster size to be consistent across nodes.
proc wait_for_cluster_size {cluster_size} {
wait_for_condition 1000 50 {
[cluster_size_consistent $cluster_size] eq 1
} else {
fail "cluster size did not reach a consistent size $cluster_size"
}
}
# Check that cluster nodes agree about "state", or raise an error.
proc wait_for_cluster_state {state} {
for {set j 0} {$j < [llength $::servers]} {incr j} {
wait_for_condition 100 50 {
[CI $j cluster_state] eq $state
} else {
fail "Cluster node $j cluster_state:[CI $j cluster_state]"
}
}
}
# Default slot allocation for clusters, each master has a continuous block
# and approximately equal number of slots.
proc continuous_slot_allocation {masters} {
set avg [expr double(16384) / $masters]
set slot_start 0
for {set j 0} {$j < $masters} {incr j} {
set slot_end [expr int(ceil(($j + 1) * $avg) - 1)]
R $j cluster addslotsrange $slot_start $slot_end
set slot_start [expr $slot_end + 1]
}
}
# Setup method to be executed to configure the cluster before the
# tests run.
proc cluster_setup {masters node_count slot_allocator code} {
# Have all nodes meet
if {$::tls} {
set tls_cluster [lindex [R 0 CONFIG GET tls-cluster] 1]
}
if {$::tls && !$tls_cluster} {
for {set i 1} {$i < $node_count} {incr i} {
R 0 CLUSTER MEET [srv -$i host] [srv -$i pport]
}
} else {
for {set i 1} {$i < $node_count} {incr i} {
R 0 CLUSTER MEET [srv -$i host] [srv -$i port]
}
}
$slot_allocator $masters
wait_for_cluster_propagation
# Setup master/replica relationships
for {set i 0} {$i < $masters} {incr i} {
set nodeid [R $i CLUSTER MYID]
for {set j [expr $i + $masters]} {$j < $node_count} {incr j $masters} {
R $j CLUSTER REPLICATE $nodeid
}
}
wait_for_cluster_propagation
wait_for_cluster_state "ok"
uplevel 1 $code
}
# Start a cluster with the given number of masters and replicas. Replicas
# will be allocated to masters by round robin.
proc start_cluster {masters replicas options code {slot_allocator continuous_slot_allocation}} {
set node_count [expr $masters + $replicas]
# Set the final code to be the tests + cluster setup
set code [list cluster_setup $masters $node_count $slot_allocator $code]
# Configure the starting of multiple servers. Set cluster node timeout
# aggressively since many tests depend on ping/pong messages.
set cluster_options [list overrides [list cluster-enabled yes cluster-ping-interval 100 cluster-node-timeout 3000]]
set options [concat $cluster_options $options]
# Cluster mode only supports a single database, so before executing the tests
# it needs to be configured correctly and needs to be reset after the tests.
set old_singledb $::singledb
set ::singledb 1
start_multiple_servers $node_count $options $code
set ::singledb $old_singledb
}
# Test node for flag.
proc cluster_has_flag {node flag} {
expr {[lsearch -exact [dict get $node flags] $flag] != -1}
}
# Returns the parsed "myself" node entry as a dictionary.
proc cluster_get_myself id {
set nodes [get_cluster_nodes $id]
foreach n $nodes {
if {[cluster_has_flag $n myself]} {return $n}
}
return {}
}
# Returns a parsed CLUSTER NODES output as a list of dictionaries.
proc get_cluster_nodes id {
set lines [split [R $id cluster nodes] "\r\n"]
set nodes {}
foreach l $lines {
set l [string trim $l]
if {$l eq {}} continue
set args [split $l]
set node [dict create \
id [lindex $args 0] \
addr [lindex $args 1] \
flags [split [lindex $args 2] ,] \
slaveof [lindex $args 3] \
ping_sent [lindex $args 4] \
pong_recv [lindex $args 5] \
config_epoch [lindex $args 6] \
linkstate [lindex $args 7] \
slots [lrange $args 8 end] \
]
lappend nodes $node
}
return $nodes
}
# Returns 1 if no node knows node_id, 0 if any node knows it.
proc node_is_forgotten {node_id} {
for {set j 0} {$j < [llength $::servers]} {incr j} {
set cluster_nodes [R $j CLUSTER NODES]
if { [string match "*$node_id*" $cluster_nodes] } {
return 0
}
}
return 1
}
# Isolate a node from the cluster and give it a new nodeid
proc isolate_node {id} {
set node_id [R $id CLUSTER MYID]
R $id CLUSTER RESET HARD
# Here we additionally test that CLUSTER FORGET propagates to all nodes.
set other_id [expr $id == 0 ? 1 : 0]
R $other_id CLUSTER FORGET $node_id
wait_for_condition 50 100 {
[node_is_forgotten $node_id]
} else {
fail "CLUSTER FORGET was not propagated to all nodes"
}
}
# Check if cluster's view of hostnames is consistent
proc are_hostnames_propagated {match_string} {
for {set j 0} {$j < [llength $::servers]} {incr j} {
set cfg [R $j cluster slots]
foreach node $cfg {
for {set i 2} {$i < [llength $node]} {incr i} {
if {! [string match $match_string [lindex [lindex [lindex $node $i] 3] 1]] } {
return 0
}
}
}
}
return 1
}
proc wait_node_marked_fail {ref_node_index instance_id_to_check} {
wait_for_condition 1000 50 {
[check_cluster_node_mark fail $ref_node_index $instance_id_to_check]
} else {
fail "Replica node never marked as FAIL ('fail')"
}
}
proc wait_node_marked_pfail {ref_node_index instance_id_to_check} {
wait_for_condition 1000 50 {
[check_cluster_node_mark fail\? $ref_node_index $instance_id_to_check]
} else {
fail "Replica node never marked as PFAIL ('fail?')"
}
}
proc check_cluster_node_mark {flag ref_node_index instance_id_to_check} {
set nodes [get_cluster_nodes $ref_node_index]
foreach n $nodes {
if {[dict get $n id] eq $instance_id_to_check} {
return [cluster_has_flag $n $flag]
}
}
fail "Unable to find instance id in cluster nodes. ID: $instance_id_to_check"
}
|