6b93d5a78467e91da9c1ced0b99fbccf0b29c06b
redis\345\223\250\345\205\265\346\250\241\345\274\217\345\234\272\346\231\257\346\265\213\350\257\225.md
| ... | ... | @@ -0,0 +1,388 @@ |
| 1 | +### 集群搭建 |
|
| 2 | +包含1个主节点和2个从节点以及3个哨兵节点的Redis集群，配置如下： |
|
| 3 | + |
|
| 4 | +主节点 redis-master 192.168.184.122 6379，由replication信息可知该节点角色为master，并有两个已经连接的从节点。 |
|
| 5 | + |
|
| 6 | +```bash |
|
| 7 | +> redis-cli -p 6379 -a snest123 info replication |
|
| 8 | + |
|
| 9 | +Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe. |
|
| 10 | +# Replication |
|
| 11 | +role:master # 角色为master |
|
| 12 | +connected_slaves:2 # 有2个从节点 |
|
| 13 | +slave0:ip=192.168.184.122,port=6381,state=online,offset=60270,lag=1 # 第一个从节点信息 |
|
| 14 | +slave1:ip=192.168.184.122,port=6380,state=online,offset=60270,lag=1 # 第二个从节点信息 |
|
| 15 | +master_failover_state:no-failover # 主节点没有故障转移状态 |
|
| 16 | +master_replid:ebd8e552d0ac04310950e95263d63961acf1a51c |
|
| 17 | +master_replid2:0000000000000000000000000000000000000000 |
|
| 18 | +master_repl_offset:60270 |
|
| 19 | +second_repl_offset:-1 |
|
| 20 | +repl_backlog_active:1 |
|
| 21 | +repl_backlog_size:1048576 |
|
| 22 | +repl_backlog_first_byte_offset:1 |
|
| 23 | +repl_backlog_histlen:60270 |
|
| 24 | +```` |
|
| 25 | +2个从节点 redis-slave-1 和 redis-slave-2，ip都是192.168.184.122，端口分别是6381和6380 |
|
| 26 | + |
|
| 27 | +```bash |
|
| 28 | +> redis-cli -p 6380 -a snest123 info replication |
|
| 29 | +Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe. |
|
| 30 | +# Replication |
|
| 31 | +role:slave # 角色为slave |
|
| 32 | +master_host:192.168.184.122 # 主节点IP |
|
| 33 | +master_port:6379 |
|
| 34 | +master_link_status:up |
|
| 35 | +master_last_io_seconds_ago:1 |
|
| 36 | +master_sync_in_progress:0 |
|
| 37 | +slave_read_repl_offset:72389 |
|
| 38 | +slave_repl_offset:72389 |
|
| 39 | +slave_priority:100 |
|
| 40 | +slave_read_only:1 |
|
| 41 | +replica_announced:1 |
|
| 42 | +connected_slaves:0 |
|
| 43 | +master_failover_state:no-failover |
|
| 44 | +master_replid:ebd8e552d0ac04310950e95263d63961acf1a51c |
|
| 45 | +master_replid2:0000000000000000000000000000000000000000 |
|
| 46 | +master_repl_offset:72389 |
|
| 47 | +second_repl_offset:-1 |
|
| 48 | +repl_backlog_active:1 |
|
| 49 | +repl_backlog_size:1048576 |
|
| 50 | +repl_backlog_first_byte_offset:12494 |
|
| 51 | +repl_backlog_histlen:59896 |
|
| 52 | +``` |
|
| 53 | + |
|
| 54 | +3个哨兵节点 redis-sentinel-1、redis-sentinel-2、redis-sentinel-3，ip都是192.168.184.122，端口分别是26379、26380和26381 |
|
| 55 | + |
|
| 56 | +```bash |
|
| 57 | +> redis-cli -p 26379 sentinel masters |
|
| 58 | +1) 1) "name" |
|
| 59 | + 2) "mymaster" |
|
| 60 | + 3) "ip" |
|
| 61 | + 4) "192.168.184.122" # 主节点IP |
|
| 62 | + 5) "port" |
|
| 63 | + 6) "6379" |
|
| 64 | + 7) "runid" |
|
| 65 | + 8) "804b4d520bc6d6bb4673f10084fd59ef9bdd518e" |
|
| 66 | + 9) "flags" |
|
| 67 | + 10) "master" # 主节点标志 |
|
| 68 | + 11) "link-pending-commands" |
|
| 69 | + 12) "0" |
|
| 70 | + 13) "link-refcount" |
|
| 71 | + 14) "1" |
|
| 72 | + 15) "last-ping-sent" |
|
| 73 | + 16) "0" |
|
| 74 | + 17) "last-ok-ping-reply" |
|
| 75 | + 18) "352" |
|
| 76 | + 19) "last-ping-reply" |
|
| 77 | + 20) "352" |
|
| 78 | + 21) "down-after-milliseconds" |
|
| 79 | + 22) "60000" |
|
| 80 | + 23) "info-refresh" |
|
| 81 | + 24) "2495" |
|
| 82 | + 25) "role-reported" |
|
| 83 | + 26) "master" |
|
| 84 | + 27) "role-reported-time" |
|
| 85 | + 28) "351514574" |
|
| 86 | + 29) "config-epoch" |
|
| 87 | + 30) "0" |
|
| 88 | + 31) "num-slaves" # 从节点数量 |
|
| 89 | + 32) "2" |
|
| 90 | + 33) "num-other-sentinels" # 其他哨兵数量 |
|
| 91 | + 34) "2" |
|
| 92 | + 35) "quorum" # 哨兵选举的法定人数 |
|
| 93 | + 36) "2" |
|
| 94 | + 37) "failover-timeout" |
|
| 95 | + 38) "180000" |
|
| 96 | + 39) "parallel-syncs" |
|
| 97 | + 40) "1" |
|
| 98 | + ``` |
|
| 99 | + |
|
| 100 | +到这里整个集群已经搭建完成，接下来我们将进行一些redis哨兵模式下的异常测试。 |
|
| 101 | + |
|
| 102 | +### 停止主节点 Redis 进程： |
|
| 103 | + |
|
| 104 | +观察sentinel输出日志： |
|
| 105 | + |
|
| 106 | +```bash |
|
| 107 | +1:X 12 Aug 2025 03:23:12.998 # +sdown master mymaster 192.168.184.122 6379 ---> Sentinel 检测到主节点不可用 |
|
| 108 | +1:X 12 Aug 2025 03:23:13.082 # +odown master mymaster 192.168.184.122 6379 #quorum 2/2 ---> Sentinel 确认主节点不可用 |
|
| 109 | +1:X 12 Aug 2025 03:23:13.082 # +new-epoch 3 |
|
| 110 | +1:X 12 Aug 2025 03:23:13.082 # +try-failover master mymaster 192.168.184.122 6379 ---> Sentinel 尝试进行故障转移 |
|
| 111 | +1:X 12 Aug 2025 03:23:13.093 # Could not rename tmp config file (Device or resource busy) |
|
| 112 | +1:X 12 Aug 2025 03:23:13.093 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 113 | +1:X 12 Aug 2025 03:23:13.093 # +vote-for-leader 247379459a8d917fdf61931a5111f921dfa47408 3 ---> Sentinel 247379459a8d917fdf61931a5111f921dfa47408 投票选举新的主节点 |
|
| 114 | +1:X 12 Aug 2025 03:23:13.116 # e39828966d5ae85ef8292ce9aa085c84ef5d6203 voted for 247379459a8d917fdf61931a5111f921dfa47408 3 |
|
| 115 | +1:X 12 Aug 2025 03:23:13.116 # ef17ddf007aa36aa2d91f5a7896b8141adca2e07 voted for 247379459a8d917fdf61931a5111f921dfa47408 3 |
|
| 116 | +1:X 12 Aug 2025 03:23:13.156 # +elected-leader master mymaster 192.168.184.122 6379 ---> Sentinel 247379459a8d917fdf61931a5111f921dfa47408 成为新的主节点 |
|
| 117 | +1:X 12 Aug 2025 03:23:13.156 # +failover-state-select-slave master mymaster 192.168.184.122 6379 |
|
| 118 | +1:X 12 Aug 2025 03:23:13.247 # +selected-slave slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 |
|
| 119 | +1:X 12 Aug 2025 03:23:13.247 * +failover-state-send-slaveof-noone slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 --> Sentinel 选择了一个从节点作为新的主节点 |
|
| 120 | +1:X 12 Aug 2025 03:23:13.309 * +failover-state-wait-promotion slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 |
|
| 121 | +1:X 12 Aug 2025 03:23:13.339 # Could not rename tmp config file (Device or resource busy) |
|
| 122 | +1:X 12 Aug 2025 03:23:13.339 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 123 | +1:X 12 Aug 2025 03:23:13.339 # +promoted-slave slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 |
|
| 124 | +1:X 12 Aug 2025 03:23:13.339 # +failover-state-reconf-slaves master mymaster 192.168.184.122 6379 |
|
| 125 | +1:X 12 Aug 2025 03:23:13.410 * +slave-reconf-sent slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6379 |
|
| 126 | +1:X 12 Aug 2025 03:23:14.216 # -odown master mymaster 192.168.184.122 6379 |
|
| 127 | +1:X 12 Aug 2025 03:23:14.270 * +slave-reconf-inprog slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6379 |
|
| 128 | +1:X 12 Aug 2025 03:23:14.270 * +slave-reconf-done slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6379 |
|
| 129 | +1:X 12 Aug 2025 03:23:14.322 # +failover-end master mymaster 192.168.184.122 6379 |
|
| 130 | +1:X 12 Aug 2025 03:23:14.322 # +switch-master mymaster 192.168.184.122 6379 192.168.184.122 6380 |
|
| 131 | +1:X 12 Aug 2025 03:23:14.323 * +slave slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6380 |
|
| 132 | +1:X 12 Aug 2025 03:23:14.323 * +slave slave 192.168.184.122:6379 192.168.184.122 6379 @ mymaster 192.168.184.122 6380 |
|
| 133 | +1:X 12 Aug 2025 03:23:14.336 # Could not rename tmp config file (Device or resource busy) |
|
| 134 | +1:X 12 Aug 2025 03:23:14.337 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 135 | +1:X 12 Aug 2025 03:24:14.350 # +sdown slave 192.168.184.122:6379 192.168.184.122 6379 @ mymaster 192.168.184.122 6380 |
|
| 136 | + |
|
| 137 | +``` |
|
| 138 | +查看sentinel 状态： |
|
| 139 | +```bash |
|
| 140 | +> redis-cli -p 26379 sentinel masters |
|
| 141 | +1) 1) "name" |
|
| 142 | + 2) "mymaster" |
|
| 143 | + 3) "ip" |
|
| 144 | + 4) "192.168.184.122" # 主节点IP |
|
| 145 | + 5) "port" |
|
| 146 | + 6) "6380" # 新的主节点端口, 之前的主节点6379已经停止, 现在6380成为新的主节点, 说明故障转移成功 |
|
| 147 | + 7) "runid" |
|
| 148 | + 8) "539781d1f63dd363c26c6e37f632d3ced0a535f5" |
|
| 149 | + 9) "flags" |
|
| 150 | + 10) "master" |
|
| 151 | + 11) "link-pending-commands" |
|
| 152 | + 12) "0" |
|
| 153 | + 13) "link-refcount" |
|
| 154 | + 14) "1" |
|
| 155 | + 15) "last-ping-sent" |
|
| 156 | + 16) "0" |
|
| 157 | + 17) "last-ok-ping-reply" |
|
| 158 | + 18) "302" |
|
| 159 | + 19) "last-ping-reply" |
|
| 160 | + 20) "302" |
|
| 161 | + 21) "down-after-milliseconds" |
|
| 162 | + 22) "60000" |
|
| 163 | + 23) "info-refresh" |
|
| 164 | + 24) "7943" |
|
| 165 | + 25) "role-reported" |
|
| 166 | + 26) "master" |
|
| 167 | + 27) "role-reported-time" |
|
| 168 | + 28) "149174" |
|
| 169 | + 29) "config-epoch" |
|
| 170 | + 30) "3" |
|
| 171 | + 31) "num-slaves" |
|
| 172 | + 32) "2" |
|
| 173 | + 33) "num-other-sentinels" |
|
| 174 | + 34) "2" |
|
| 175 | + 35) "quorum" |
|
| 176 | + 36) "2" |
|
| 177 | + 37) "failover-timeout" |
|
| 178 | + 38) "180000" |
|
| 179 | + 39) "parallel-syncs" |
|
| 180 | + 40) "1" |
|
| 181 | +``` |
|
| 182 | + |
|
| 183 | +进一步验证 192.168.184.122:6380 是否真的成为了新的主节点： |
|
| 184 | +```bash |
|
| 185 | +> redis-cli -p 6380 -a snest123 info replication |
|
| 186 | +Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe. |
|
| 187 | +# Replication |
|
| 188 | +role:master # 确实角色为master |
|
| 189 | +connected_slaves:1 # 现在只有一个从节点 |
|
| 190 | +slave0:ip=192.168.184.122,port=6381,state=online,offset=201890,lag=0 # 之前的从节点6381现在仍然在线，依然作为一个从节点存在 |
|
| 191 | +master_failover_state:no-failover |
|
| 192 | +master_replid:ad6a01d6a123ea956ec35f0d80e3d1e83191bb7b |
|
| 193 | +master_replid2:ebd8e552d0ac04310950e95263d63961acf1a51c |
|
| 194 | +master_repl_offset:202035 |
|
| 195 | +second_repl_offset:154594 |
|
| 196 | +repl_backlog_active:1 |
|
| 197 | +repl_backlog_size:1048576 |
|
| 198 | +repl_backlog_first_byte_offset:12494 |
|
| 199 | +repl_backlog_histlen:189542 |
|
| 200 | +``` |
|
| 201 | + |
|
| 202 | +获取之前master写入的数据测试数据是否还存在： |
|
| 203 | +```bash |
|
| 204 | +redis-cli -p 6380 -a snest123 get foo |
|
| 205 | +Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe. |
|
| 206 | +"bar" # 数据仍然存在 |
|
| 207 | +``` |
|
| 208 | +由上述测试结果可以看出，Redis哨兵模式下的故障转移功能正常工作，新的主节点成功接管了之前主节点的角色，并且数据保持一致性。 |
|
| 209 | + |
|
| 210 | +重新启动之前的主节点 Redis 进程，作为6380的slave而存在： |
|
| 211 | + |
|
| 212 | +```bash |
|
| 213 | +1:X 12 Aug 2025 03:24:14.350 # +sdown slave 192.168.184.122:6379 192.168.184.122 6379 @ mymaster 192.168.184.122 6380 |
|
| 214 | +1:X 12 Aug 2025 03:30:50.866 # -sdown slave 192.168.184.122:6379 192.168.184.122 6379 @ mymaster 192.168.184.122 6380 |
|
| 215 | +1:X 12 Aug 2025 03:31:00.799 * +convert-to-slave slave 192.168.184.122:6379 192.168.184.122 6379 @ mymaster 192.168.184.122 6380 |
|
| 216 | +``` |
|
| 217 | +### 模拟哨兵节点故障 |
|
| 218 | + |
|
| 219 | +停止其中一个哨兵节点 redis-sentinel-1 进程，观察另外两个哨兵节点的日志输出，发现没输出任何关于故障的日志信息。 |
|
| 220 | + |
|
| 221 | + |
|
| 222 | + |
|
| 223 | +停掉2个哨兵节点 redis-sentinel-1 和 redis-sentinel-2 进程，观察剩余一个哨兵节点 redis-sentinel-3 的日志输出： |
|
| 224 | + |
|
| 225 | +```bash |
|
| 226 | + |
|
| 227 | +1:X 12 Aug 2025 03:38:08.991 # +sdown sentinel e39828966d5ae85ef8292ce9aa085c84ef5d6203 192.168.184.122 26381 @ mymaster 192.168.184.122 6380 |
|
| 228 | +1:X 12 Aug 2025 03:38:44.972 # +sdown sentinel ef17ddf007aa36aa2d91f5a7896b8141adca2e07 192.168.184.122 26380 @ mymaster 192.168.184.122 6380 |
|
| 229 | +1:X 12 Aug 2025 03:39:05.514 # +sdown master mymaster 192.168.184.122 6380 |
|
| 230 | + |
|
| 231 | +``` |
|
| 232 | + |
|
| 233 | +此时在程序中尝试连接redis集群，观察连接情况： |
|
| 234 | + |
|
| 235 | +```bash |
|
| 236 | +redis: 2025/08/12 11:43:54 sentinel.go:770: sentinel: selected addr=192.168.184.122:26379 masterAddr=192.168.184.122:6380 |
|
| 237 | +redis: 2025/08/12 11:43:54 sentinel.go:759: sentinel: GetMasterAddrByName addr=192.168.184.122:26381, master="mymaster" failed: context canceled |
|
| 238 | +redis: 2025/08/12 11:43:54 sentinel.go:759: sentinel: GetMasterAddrByName addr=192.168.184.122:26380, master="mymaster" failed: context canceled |
|
| 239 | +redis: 2025/08/12 11:43:54 sentinel.go:920: sentinel: new master="mymaster" addr="192.168.184.122:6380" |
|
| 240 | +panic: dial tcp 192.168.184.122:6380: connectex: No connection could be made because the target machine actively refused it. |
|
| 241 | + |
|
| 242 | +``` |
|
| 243 | +发现在半数以上哨兵节点故障时，程序无法连接到Redis集群的主节点，导致panic错误。这是因为哨兵节点的故障导致无法获取主节点的地址，从而无法建立连接。 |
|
| 244 | + |
|
| 245 | +### 恢复哨兵节点 |
|
| 246 | + |
|
| 247 | +重新启动之前停止的哨兵节点 redis-sentinel-1 和 redis-sentinel-2 进程，观察日志输出： |
|
| 248 | + |
|
| 249 | +```bash |
|
| 250 | +1:X 12 Aug 2025 03:47:09.266 # -sdown sentinel ef17ddf007aa36aa2d91f5a7896b8141adca2e07 192.168.184.122 26380 @ mymaster 192.168.184.122 6380 |
|
| 251 | +1:X 12 Aug 2025 03:47:11.234 * +sentinel-invalid-addr sentinel ef17ddf007aa36aa2d91f5a7896b8141adca2e07 192.168.184.122 26380 @ mymaster 192.168.184.122 6380 |
|
| 252 | +1:X 12 Aug 2025 03:47:11.234 * +sentinel sentinel 96ac7bcab8868b94de33ab08a10761545b6d42c6 192.168.184.122 26380 @ mymaster 192.168.184.122 6380 |
|
| 253 | +1:X 12 Aug 2025 03:47:11.242 # Could not rename tmp config file (Device or resource busy) |
|
| 254 | +1:X 12 Aug 2025 03:47:11.242 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 255 | +1:X 12 Aug 2025 03:48:09.284 # Could not rename tmp config file (Device or resource busy) |
|
| 256 | +1:X 12 Aug 2025 03:48:09.284 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 257 | +1:X 12 Aug 2025 03:48:09.284 # +new-epoch 4 |
|
| 258 | +1:X 12 Aug 2025 03:48:09.291 # Could not rename tmp config file (Device or resource busy) |
|
| 259 | +1:X 12 Aug 2025 03:48:09.292 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 260 | +1:X 12 Aug 2025 03:48:09.292 # +vote-for-leader 96ac7bcab8868b94de33ab08a10761545b6d42c6 4 |
|
| 261 | +1:X 12 Aug 2025 03:48:09.497 # +odown master mymaster 192.168.184.122 6380 #quorum 2/2 |
|
| 262 | +1:X 12 Aug 2025 03:48:09.497 # Next failover delay: I will not start a failover before Tue Aug 12 03:54:09 2025 |
|
| 263 | +1:X 12 Aug 2025 03:48:09.633 # +config-update-from sentinel 96ac7bcab8868b94de33ab08a10761545b6d42c6 192.168.184.122 26380 @ mymaster 192.168.184.122 6380 |
|
| 264 | +1:X 12 Aug 2025 03:48:09.633 # +switch-master mymaster 192.168.184.122 6380 192.168.184.122 6379 |
|
| 265 | +1:X 12 Aug 2025 03:48:09.633 * +slave slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6379 |
|
| 266 | +1:X 12 Aug 2025 03:48:09.633 * +slave slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 |
|
| 267 | +1:X 12 Aug 2025 03:48:09.640 # Could not rename tmp config file (Device or resource busy) |
|
| 268 | +1:X 12 Aug 2025 03:48:09.640 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 269 | +``` |
|
| 270 | + |
|
| 271 | +发现哨兵节点重新启动后，能够自动检测到主节点的变化，并进行相应的配置更新和故障转移操作。此时，Redis集群恢复了正常的工作状态。 |
|
| 272 | +再次尝试在程序中连接Redis集群，都能正常访问。 |
|
| 273 | + |
|
| 274 | +继续全部恢复所有redis节点，重新启动之前停止的主节点 redis-master 进程： |
|
| 275 | + |
|
| 276 | +```bash |
|
| 277 | +1:X 12 Aug 2025 03:50:14.541 # -sdown slave 192.168.184.122:6380 192.168.184.122 6380 @ mymaster 192.168.184.122 6379 |
|
| 278 | +1:X 12 Aug 2025 03:50:20.838 * +reboot master mymaster 192.168.184.122 6379 |
|
| 279 | +1:X 12 Aug 2025 03:50:36.213 # -sdown sentinel e39828966d5ae85ef8292ce9aa085c84ef5d6203 192.168.184.122 26381 @ mymaster 192.168.184.122 6379 |
|
| 280 | +1:X 12 Aug 2025 03:50:37.284 * +sentinel-invalid-addr sentinel e39828966d5ae85ef8292ce9aa085c84ef5d6203 192.168.184.122 26381 @ mymaster 192.168.184.122 6379 |
|
| 281 | +1:X 12 Aug 2025 03:50:37.284 * +sentinel sentinel e4213f7cc46cbac21727dd4ec930e65cd2c1dba2 192.168.184.122 26381 @ mymaster 192.168.184.122 6379 |
|
| 282 | +1:X 12 Aug 2025 03:50:37.293 # Could not rename tmp config file (Device or resource busy) |
|
| 283 | +1:X 12 Aug 2025 03:50:37.293 # WARNING: Sentinel was not able to save the new configuration on disk!!!: Device or resource busy |
|
| 284 | +1:X 12 Aug 2025 03:51:16.272 * +fix-slave-config slave 192.168.184.122:6381 192.168.184.122 6381 @ mymaster 192.168.184.122 6379 |
|
| 285 | +``` |
|
| 286 | +可以发现一切都恢复正常，Redis集群的主节点、从节点和哨兵节点都能够正常工作。 |
|
| 287 | + |
|
| 288 | +到此，Redis哨兵模式下的异常测试已经完成。通过这些测试，我们验证了Redis哨兵在主节点故障、从节点故障以及哨兵节点故障等情况下的自动恢复和故障转移能力。 |
|
| 289 | +下面继续测试业务逻辑的异常情况。 |
|
| 290 | + |
|
| 291 | +### 业务异常 |
|
| 292 | + |
|
| 293 | +跑了大概一天，没有发现redisson连接异常的日志。 |
|
| 294 | + |
|
| 295 | +### 场景1：主从切换 |
|
| 296 | +步骤： |
|
| 297 | +哨兵Redis停止master节点，模拟主从切换。 |
|
| 298 | +之后更新APP，查看元模型能否被消费。 |
|
| 299 | +验证结果： |
|
| 300 | +使用Topic检查文档（我之前提供的文档），检查对应的客户端能否正常及时消费 |
|
| 301 | +检查slowlog是否有超过200ms的执行命令 |
|
| 302 | + |
|
| 303 | + |
|
| 304 | +### 场景2：初次安装 |
|
| 305 | +**步骤**： |
|
| 306 | +清空Redis中 final_meta* 下的内容，重启所有后端容器，检查元模型能否被正常消费 |
|
| 307 | +**验证结果**： |
|
| 308 | +使用Topic检查文档（我之前提供的文档），检查对应的客户端能否正常及时消费 |
|
| 309 | +检查slowlog是否有超过200ms的执行命令 |
|
| 310 | + |
|
| 311 | +**实际验证结果**： |
|
| 312 | +能够正常消费，没有发现消费延迟的情况。 |
|
| 313 | + |
|
| 314 | +消费topic详情如下： |
|
| 315 | + |
|
| 316 | +```bash |
|
| 317 | + |
|
| 318 | +2025/08/13 15:57:34 收到消息 ID=1755071850670-0, 内容=map[key:OppmMonthTarget source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 319 | +2025/08/13 15:57:35 收到消息 ID=1755071850700-0, 内容=map[key:OppmProLine source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 320 | +2025/08/13 15:57:35 收到消息 ID=1755071852169-0, 内容=map[key:demo_role,data_source_test,crud_ds_test,tenant_ds_test,OppmCustomerArchive,a_app_model,buss_store,ops_trace_log,OppmOpportunity,test_order,sql_template_test,TestTest1,shard_year_test,ops_tracking_user_model,TestTest2,test_order_ref,OppmCompanyReport,TestUser,demo_product,service_node source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 321 | +2025/08/13 15:57:35 收到消息 ID=1755071852244-0, 内容=map[key:group_by_test,sie_order,OppmProLine,apiOrderService,OppmCrmOpportunityLog,OppmCrmOpportunity,test_eam_maintenance_task,OppmOpportunityThisWeek,wf_process_policy_user,test_data_auth_vo,install_app,demoUserSendVariables,wf_service_method_hook,TestOrderOrg,wf_process_model_view,worker_job_info,seed_ds_test,TestOrg,shard_list_test,seed_test source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 322 | +2025/08/13 15:57:35 收到消息 ID=1755071852292-0, 内容=map[key:er_a,test_eam_maintenance_document,worker_instance_info,demo_order,main_ds_test,host_node,demo_product_b,demo_product_c,TestDataSource,base_model_test,test_eam_maintenance_other_expenses,OppmIndustry,inherit_model_test,OppmRefProLineOrg,demoUserReceiverVariables,demo_supplier,TestRole,TestTest,MetaPropertyVm,wf_process_test source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 323 | +2025/08/13 15:57:36 收到消息 ID=1755071852382-0, 内容=map[key:test_eam_fault_maintenance_order,OppmMonthTarget,normal_scene_test,many_to_many_c,test_eam_maintenance_item,broadcast_test,buss_order,base_importexportexcel,crud_ds_test_ref,test_eam_maintenance_working_hours,worker_registration_info,sie_order_item,host_node_vm,UserVm,buss_ds_test,test_eam_maintenance_information,er_d,MetaAppVm,er_b,test_data_auth source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 324 | +2025/08/13 15:57:36 收到消息 ID=1755071852424-0, 内容=map[key:product_ds_test,OppmRefOrgAccount,OppmAreaSalesManager,buss_wallet,OppmOpportunityNextWeek,receiverVariables,shard_month_test,TestRule,ops_trace_handle_service,demo_user,senderVariables,OppmAreaReport,ops_tracking_service_model source:47d7894f-070b-47d9-8a75-94c242440260 type:update] |
|
| 325 | + |
|
| 326 | +``` |
|
| 327 | + |
|
| 328 | +### 场景3：安装、更新、卸载 |
|
| 329 | +**步骤**： |
|
| 330 | +测试正常的安装、更新、卸载在哨兵模式下的效果 |
|
| 331 | +**验证方式**： |
|
| 332 | +使用Topic检查文档（我之前提供的文档），检查对应的客户端能否正常及时消费 |
|
| 333 | +检查slowlog是否有超过200ms的执行命令 |
|
| 334 | + |
|
| 335 | +**实际验证结果**： |
|
| 336 | +能够正常消费，没有发现消费延迟的情况。 |
|
| 337 | +能够正常安装、更新、卸载。安装卸载、更新、卸载后，元模型都能被正常消费。但是出现一些单个的stream事件，而且是不相干的元模型事件。 |
|
| 338 | + |
|
| 339 | + |
|
| 340 | +安装app后消费详情如下： |
|
| 341 | + |
|
| 342 | +```bash |
|
| 343 | + |
|
| 344 | +2025/08/13 16:07:34 收到消息 ID=1755072452966-0, 内容=map[key:OppmMonthTarget source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 345 | +2025/08/13 16:07:34 收到消息 ID=1755072452994-0, 内容=map[key:OppmProLine source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 346 | +2025/08/13 16:07:37 收到消息 ID=1755072455636-0, 内容=map[key:demo_role,data_source_test,crud_ds_test,tenant_ds_test,OppmCustomerArchive,a_app_model,buss_store,ops_trace_log,OppmOpportunity,test_order,sql_template_test,TestTest1,shard_year_test,ops_tracking_user_model,TestTest2,test_order_ref,OppmCompanyReport,TestUser,demo_product,service_node source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 347 | +2025/08/13 16:07:37 收到消息 ID=1755072455733-0, 内容=map[key:group_by_test,sie_order,OppmProLine,apiOrderService,OppmCrmOpportunityLog,OppmCrmOpportunity,test_eam_maintenance_task,OppmOpportunityThisWeek,wf_process_policy_user,test_data_auth_vo,install_app,demoUserSendVariables,wf_service_method_hook,TestOrderOrg,wf_process_model_view,worker_job_info,seed_ds_test,TestOrg,shard_list_test,seed_test source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 348 | +2025/08/13 16:07:37 收到消息 ID=1755072455783-0, 内容=map[key:er_a,test_eam_maintenance_document,worker_instance_info,demo_order,main_ds_test,host_node,demo_product_b,demo_product_c,TestDataSource,base_model_test,test_eam_maintenance_other_expenses,OppmIndustry,inherit_model_test,OppmRefProLineOrg,demoUserReceiverVariables,demo_supplier,TestRole,TestTest,MetaPropertyVm,wf_process_test source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 349 | +2025/08/13 16:07:37 收到消息 ID=1755072455881-0, 内容=map[key:test_eam_fault_maintenance_order,OppmMonthTarget,normal_scene_test,many_to_many_c,test_eam_maintenance_item,broadcast_test,buss_order,base_importexportexcel,crud_ds_test_ref,test_eam_maintenance_working_hours,worker_registration_info,sie_order_item,host_node_vm,UserVm,buss_ds_test,test_eam_maintenance_information,er_d,MetaAppVm,er_b,test_data_auth source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 350 | +2025/08/13 16:07:37 收到消息 ID=1755072455909-0, 内容=map[key:product_ds_test,OppmRefOrgAccount,OppmAreaSalesManager,buss_wallet,OppmOpportunityNextWeek,receiverVariables,shard_month_test,TestRule,ops_trace_handle_service,demo_user,senderVariables,OppmAreaReport,ops_tracking_service_model source:97f97547-d38c-4f10-ab4e-4099f96a718f type:update] |
|
| 351 | + |
|
| 352 | +``` |
|
| 353 | +卸载消费详情如下： |
|
| 354 | + |
|
| 355 | +```bash |
|
| 356 | + |
|
| 357 | +2025/08/13 16:02:14 收到消息 ID=1755072133153-0, 内容=map[key:test_eam_maintenance_document,TestTest,TestUser,TestDataSource,test_eam_maintenance_other_expenses,TestTest1,TestTest2,TestRole,test_order_ref,test_order,MetaPropertyVm,TestOrderOrg,test_eam_maintenance_information,test_eam_fault_maintenance_order,test_eam_maintenance_item,test_eam_maintenance_working_hours,UserVm,MetaAppVm,test_data_auth,base_importexportexcel,TestRule,TestOrg,test_data_auth_vo,test_eam_maintenance_task source:bb0ab662-2b19-4b9b-9ffe-0d8b5e9d9223 type:remove] |
|
| 358 | + |
|
| 359 | +``` |
|
| 360 | +更新后消费详情如下： |
|
| 361 | + |
|
| 362 | +```bash |
|
| 363 | + |
|
| 364 | +2025/08/13 17:08:56 收到消息 ID=1755076134622-0, 内容=map[key:OppmMonthTarget source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 365 | +2025/08/13 17:08:56 收到消息 ID=1755076134667-0, 内容=map[key:OppmProLine source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 366 | +2025/08/13 17:08:59 收到消息 ID=1755076137980-0, 内容=map[key:demo_role,data_source_test,crud_ds_test,tenant_ds_test,OppmCustomerArchive,a_app_model,buss_store,ops_trace_log,OppmOpportunity,test_order,sql_template_test,TestTest1,shard_year_test,ops_tracking_user_model,TestTest2,test_order_ref,worker_job_info,TestUser,demo_product,service_node source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 367 | +2025/08/13 17:08:59 收到消息 ID=1755076138058-0, 内容=map[key:group_by_test,sie_order,OppmProLine,apiOrderService,OppmCrmOpportunityLog,OppmCrmOpportunity,test_eam_maintenance_task,OppmOpportunityThisWeek,wf_process_policy_user,test_data_auth_vo,install_app,demoUserSendVariables,wf_service_method_hook,TestOrderOrg,wf_process_model_view,OppmCompanyReport,seed_ds_test,TestOrg,shard_list_test,seed_test source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 368 | +2025/08/13 17:08:59 收到消息 ID=1755076138108-0, 内容=map[key:er_a,test_eam_maintenance_document,worker_instance_info,demo_order,main_ds_test,host_node,demo_product_b,demo_product_c,TestDataSource,base_model_test,test_eam_maintenance_other_expenses,OppmIndustry,inherit_model_test,OppmRefProLineOrg,demoUserReceiverVariables,demo_supplier,TestRole,TestTest,MetaPropertyVm,wf_process_test source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 369 | +2025/08/13 17:08:59 收到消息 ID=1755076138218-0, 内容=map[key:test_eam_fault_maintenance_order,OppmMonthTarget,normal_scene_test,many_to_many_c,test_eam_maintenance_item,broadcast_test,buss_order,base_importexportexcel,crud_ds_test_ref,test_eam_maintenance_working_hours,worker_registration_info,sie_order_item,host_node_vm,UserVm,buss_ds_test,test_eam_maintenance_information,er_d,MetaAppVm,er_b,test_data_auth source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 370 | +2025/08/13 17:08:59 收到消息 ID=1755076138267-0, 内容=map[key:product_ds_test,OppmRefOrgAccount,OppmAreaSalesManager,buss_wallet,OppmOpportunityNextWeek,receiverVariables,shard_month_test,TestRule,ops_trace_handle_service,demo_user,senderVariables,OppmAreaReport,ops_tracking_service_model source:9c408177-4c1f-45ea-90e7-3194c04f0aef type:update] |
|
| 371 | +2025/08/13 17:09:01 收到消息 ID=1755076140128-0, 内容=map[key:OppmMonthTarget source:4abda77c-aedb-4f48-9186-8f65fded6840 type:update] |
|
| 372 | +2025/08/13 17:09:01 收到消息 ID=1755076140163-0, 内容=map[key:OppmProLine source:4abda77c-aedb-4f48-9186-8f65fded6840 type:update] |
|
| 373 | + |
|
| 374 | +``` |
|
| 375 | + |
|
| 376 | +### 场景4：模拟大量卸载安装 |
|
| 377 | +**步骤**： |
|
| 378 | +用脚本进行一晚的安装卸载APP，测试是否有问题 |
|
| 379 | +**验证方式**： |
|
| 380 | +使用Topic检查文档（我之前提供的文档），检查对应的客户端能否正常及时消费 |
|
| 381 | +检查slowlog是否有超过200ms的执行命令 |
|
| 382 | + |
|
| 383 | +### 场景5：模拟长时间运行 |
|
| 384 | +**步骤**： |
|
| 385 | +不停止Redis和后端，测试运行一星期的效果 |
|
| 386 | +**验证方式**： |
|
| 387 | +使用Topic检查文档（我之前提供的文档），检查对应的客户端能否正常及时消费 |
|
| 388 | +检查slowlog是否有超过200ms的执行命令 |
|
| ... | ... | \ No newline at end of file |