Created
December 13, 2018 16:00
-
-
Save bittusarkar/b0d39f5d38926b180897c73da40c4bd3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
GET _cluster/health | |
{ | |
"cluster_name": "almsearchprodweu2_es5", | |
"status": "yellow", | |
"timed_out": false, | |
"number_of_nodes": 16, | |
"number_of_data_nodes": 10, | |
"active_primary_shards": 3964, | |
"active_shards": 7924, | |
"relocating_shards": 0, | |
"initializing_shards": 10, | |
"unassigned_shards": 118, | |
"delayed_unassigned_shards": 0, | |
"number_of_pending_tasks": 0, | |
"number_of_in_flight_fetch": 0, | |
"task_max_waiting_in_queue_millis": 0, | |
"active_shards_percent_as_number": 98.41033283656234 | |
} | |
=== | |
GET _cat/allocation?v | |
shards disk.indices disk.used disk.avail disk.total disk.percent host ip node | |
1035 558.4gb 562.2gb 3.4tb 3.9tb 13 192.168.0.154 192.168.0.154 es-d04-rm | |
14 468kb 310.8mb 3.9tb 3.9tb 0 192.168.0.160 192.168.0.160 es-d10-rm | |
410 108.1gb 110.2gb 3.8tb 3.9tb 2 192.168.0.155 192.168.0.155 es-d05-rm | |
44 9.6kb 310.3mb 3.9tb 3.9tb 0 192.168.0.158 192.168.0.158 es-d08-rm | |
1902 841.6gb 847.9gb 3.1tb 3.9tb 20 192.168.0.151 192.168.0.151 es-d01-rm | |
1863 917.3gb 925.2gb 3tb 3.9tb 22 192.168.0.152 192.168.0.152 es-d02-rm | |
1994 1tb 1.1tb 2.8tb 3.9tb 27 192.168.0.153 192.168.0.153 es-d03-rm | |
208 21.7gb 22.2gb 3.9tb 3.9tb 0 192.168.0.157 192.168.0.157 es-d07-rm | |
407 98.1gb 99.3gb 3.8tb 3.9tb 2 192.168.0.159 192.168.0.159 es-d09-rm | |
57 12.8kb 311.3mb 3.9tb 3.9tb 0 192.168.0.156 192.168.0.156 es-d06-rm | |
118 UNASSIGNED | |
=== | |
GET _cluster/settings | |
{ | |
"persistent": {}, | |
"transient": { | |
"cluster": { | |
"routing": { | |
"allocation": { | |
"exclude": { | |
"_ip": "192.168.0.151" | |
} | |
} | |
} | |
} | |
} | |
} | |
=== | |
GET _cluster/allocation/explain | |
{ | |
"index": "codesearchshared_8_0", | |
"shard": 33, | |
"primary": false, | |
"current_state": "unassigned", | |
"unassigned_info": { | |
"reason": "MANUAL_ALLOCATION", | |
"at": "2018-12-13T07:28:52.698Z", | |
"details": "failed shard on node [EeSbzForSNeuewm02TeSlA]: failed recovery, failure RecoveryFailedException[[codesearchshared_8_0][33]: Recovery failed from {es-d01-rm}{05PeyBBySq-qL0NVHwdVmw}{fGTsu8lHRNyuDlUglbjAlg}{192.168.0.151}{192.168.0.151:9300}{faultDomain=0, updateDomain=0} into {es-d08-rm}{EeSbzForSNeuewm02TeSlA}{7YAg4GuxRBORgeZ2ND0nDg}{192.168.0.158}{192.168.0.158:9300}{faultDomain=1, updateDomain=2} (no activity after [30m])]; nested: ElasticsearchTimeoutException[no activity after [30m]]; ", | |
"last_allocation_status": "no_attempt" | |
}, | |
"can_allocate": "throttled", | |
"allocate_explanation": "allocation temporarily throttled", | |
"node_allocation_decisions": [ | |
{ | |
"node_id": "0pxsNqEkQ_Kel-CdOUrDqA", | |
"node_name": "es-d10-rm", | |
"transport_address": "192.168.0.160:9300", | |
"node_attributes": { | |
"faultDomain": "1", | |
"updateDomain": "4" | |
}, | |
"node_decision": "throttled", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [0pxsNqEkQ_Kel-CdOUrDqA] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
} | |
] | |
}, | |
{ | |
"node_id": "EeSbzForSNeuewm02TeSlA", | |
"node_name": "es-d08-rm", | |
"transport_address": "192.168.0.158:9300", | |
"node_attributes": { | |
"faultDomain": "1", | |
"updateDomain": "2" | |
}, | |
"node_decision": "throttled", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [EeSbzForSNeuewm02TeSlA] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
} | |
] | |
}, | |
{ | |
"node_id": "p20g3NziScCwW9QaczvXZA", | |
"node_name": "es-d02-rm", | |
"transport_address": "192.168.0.152:9300", | |
"node_attributes": { | |
"faultDomain": "1", | |
"updateDomain": "1" | |
}, | |
"node_decision": "throttled", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [p20g3NziScCwW9QaczvXZA] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
} | |
] | |
}, | |
{ | |
"node_id": "xSBwpjSuSNm-lQrjyb-H1g", | |
"node_name": "es-d04-rm", | |
"transport_address": "192.168.0.154:9300", | |
"node_attributes": { | |
"faultDomain": "1", | |
"updateDomain": "3" | |
}, | |
"node_decision": "throttled", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [xSBwpjSuSNm-lQrjyb-H1g] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
} | |
] | |
}, | |
{ | |
"node_id": "05PeyBBySq-qL0NVHwdVmw", | |
"node_name": "es-d01-rm", | |
"transport_address": "192.168.0.151:9300", | |
"node_attributes": { | |
"faultDomain": "0", | |
"updateDomain": "0" | |
}, | |
"node_decision": "no", | |
"store": { | |
"matching_sync_id": true | |
}, | |
"deciders": [ | |
{ | |
"decider": "filter", | |
"decision": "NO", | |
"explanation": """node matches cluster setting [cluster.routing.allocation.exclude] filters [_ip:"192.168.0.151"]""" | |
}, | |
{ | |
"decider": "same_shard", | |
"decision": "NO", | |
"explanation": "the shard cannot be allocated to the same node on which a copy of the shard already exists [[codesearchshared_8_0][33], node[05PeyBBySq-qL0NVHwdVmw], [P], s[STARTED], a[id=53jHddp9RUmBs2zL0KGauQ]]" | |
}, | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [05PeyBBySq-qL0NVHwdVmw] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [updateDomain], there are [2] total configured shard copies for this shard id and [9] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
}, | |
{ | |
"node_id": "54R6JMXNT0KHWRTkrKOzpg", | |
"node_name": "es-d06-rm", | |
"transport_address": "192.168.0.156:9300", | |
"node_attributes": { | |
"faultDomain": "1", | |
"updateDomain": "0" | |
}, | |
"node_decision": "no", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [54R6JMXNT0KHWRTkrKOzpg] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [updateDomain], there are [2] total configured shard copies for this shard id and [9] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
}, | |
{ | |
"node_id": "HNSZGsRASyaTCfZONDmtIw", | |
"node_name": "es-d09-rm", | |
"transport_address": "192.168.0.159:9300", | |
"node_attributes": { | |
"faultDomain": "0", | |
"updateDomain": "3" | |
}, | |
"node_decision": "no", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [HNSZGsRASyaTCfZONDmtIw] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [faultDomain], there are [2] total configured shard copies for this shard id and [3] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
}, | |
{ | |
"node_id": "m-dZa9fLT1-EBP4S5KW9yQ", | |
"node_name": "es-d07-rm", | |
"transport_address": "192.168.0.157:9300", | |
"node_attributes": { | |
"faultDomain": "0", | |
"updateDomain": "1" | |
}, | |
"node_decision": "no", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [m-dZa9fLT1-EBP4S5KW9yQ] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [faultDomain], there are [2] total configured shard copies for this shard id and [3] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
}, | |
{ | |
"node_id": "ox2cTQ3BQw6e6q78DihFdg", | |
"node_name": "es-d05-rm", | |
"transport_address": "192.168.0.155:9300", | |
"node_attributes": { | |
"faultDomain": "0", | |
"updateDomain": "4" | |
}, | |
"node_decision": "no", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [ox2cTQ3BQw6e6q78DihFdg] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [faultDomain], there are [2] total configured shard copies for this shard id and [3] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
}, | |
{ | |
"node_id": "xmCfM_q6Saqf-xCyiao3Uw", | |
"node_name": "es-d03-rm", | |
"transport_address": "192.168.0.153:9300", | |
"node_attributes": { | |
"faultDomain": "0", | |
"updateDomain": "2" | |
}, | |
"node_decision": "no", | |
"deciders": [ | |
{ | |
"decider": "throttling", | |
"decision": "THROTTLE", | |
"explanation": "reached the limit of outgoing shard recoveries [10] on the node [xmCfM_q6Saqf-xCyiao3Uw] which holds the primary, cluster setting [cluster.routing.allocation.node_concurrent_outgoing_recoveries=10] (can also be set via [cluster.routing.allocation.node_concurrent_recoveries])" | |
}, | |
{ | |
"decider": "awareness", | |
"decision": "NO", | |
"explanation": "there are too many copies of the shard allocated to nodes with attribute [faultDomain], there are [2] total configured shard copies for this shard id and [3] total attribute values, expected the allocated shard count per attribute [2] to be less than or equal to the upper bound of the required number of shards per attribute [1]" | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment