Opensearch删除了未释放磁盘空间的文档,搜索性能下降



我们使用的是具有elasticsearch v7.10.2的opensearch,我们有一个大索引,定期对数据进行索引,也定期删除数据(一个月前的数据(,但随着时间的推移,我们在查询中的搜索性能下降,我们主要使用has_child查询,我想知道被删除的文档是否仍在我的索引中背诵,是否仍在消耗资源,如果是的话,我该如何删除它们,下面我附上了一些统计数据。

是否获取条/段(_C(?index=segment_index_570de84a4f0d925f98343571&s=文档已删除

我的一些片段也达到了5GB,这里只附上几个片段示例,以更好地理解

segment_index_570de84a4f0d925f98343571 83 r x.x.x.x _36u6 148830  4566709 5083016    4.2gb 292024 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 83 p x.x.x.x _36u6 148830  4566709 5083016    4.2gb 292024 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 84 p x.x.x.x  _37hm 149674  4569844 5127644    4.4gb 290112 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 84 r x.x.x.x _37hm 149674  4569838 5127650    4.4gb 290112 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 40 p x.x.x.x _30oh 140849  3765550 5460181    4.7gb 292616 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 40 r x.x.x.x  _30oh 140849  3765544 5460187    4.7gb 292616 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 29 r x.x.x.x _2ygs 137980  3359481 5519471    4.9gb 287504 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 29 p x.x.x.x  _2ygs 137980  3359481 5519471    4.9gb 287504 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 13 p x.x.x.x  _2u1h 132245  2731374 5565823      4gb 289480 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 13 r x.x.x.x _2u1h 132245  2731372 5565825      4gb 289480 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 57 p x.x.x.x  _3bx3 155415  4144634 5615761    4.5gb 304728 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 57 r x.x.x.x _3bx3 155415  4144620 5615775    4.5gb 304728 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 10 r x.x.x.x  _2yau 137766  3535782 5821903    4.6gb 290072 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 10 p x.x.x.x _2yau 137766  3535778 5821907    4.6gb 290072 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 5  r x.x.x.x _2vsz 134531  3052529 5940943      5gb 287288 true  true  8.7.0 false
segment_index_570de84a4f0d925f98343571 5  p x.x.x.x  _2vsz 134531  3052529 5940943      5gb 287288 true  true  8.7.0 false

获取segment_index_570de84a4f0d925f98343571/_stats

{
"_shards" : {
"total" : 200,
"successful" : 200,
"failed" : 0
},
"_all" : {
"primaries" : {
"docs" : {
"count" : 2764210965,
"deleted" : 768121801
},
"store" : {
"size_in_bytes" : 1882036902899,
"reserved_in_bytes" : 0
},
"indexing" : {
"index_total" : 35049143,
"index_time_in_millis" : 93342006,
"index_current" : 1,
"index_failed" : 7,
"delete_total" : 28158400,
"delete_time_in_millis" : 2241164,
"delete_current" : 0,
"noop_update_total" : 108,
"is_throttled" : false,
"throttle_time_in_millis" : 0
},
"get" : {
"total" : 8272612,
"time_in_millis" : 9407739,
"exists_total" : 7714730,
"exists_time_in_millis" : 6864869,
"missing_total" : 557882,
"missing_time_in_millis" : 2542870,
"current" : 0
},
"search" : {
"open_contexts" : 99,
"query_total" : 781661,
"query_time_in_millis" : 46180985,
"query_current" : 0,
"fetch_total" : 25828,
"fetch_time_in_millis" : 31922549,
"fetch_current" : 0,
"scroll_total" : 150005,
"scroll_time_in_millis" : 3934488045,
"scroll_current" : 99,
"suggest_total" : 0,
"suggest_time_in_millis" : 0,
"suggest_current" : 0
},
"merges" : {
"current" : 0,
"current_docs" : 0,
"current_size_in_bytes" : 0,
"total" : 5069,
"total_time_in_millis" : 15670663,
"total_docs" : 232287891,
"total_size_in_bytes" : 144734357228,
"total_stopped_time_in_millis" : 0,
"total_throttled_time_in_millis" : 3012035,
"total_auto_throttle_in_bytes" : 1635281344
},
"refresh" : {
"total" : 26258,
"total_time_in_millis" : 24294337,
"external_total" : 23116,
"external_total_time_in_millis" : 51934585,
"listeners" : 0
},
"flush" : {
"total" : 129,
"periodic" : 29,
"total_time_in_millis" : 83553
},
"warmer" : {
"current" : 0,
"total" : 23099,
"total_time_in_millis" : 28150896
},
"query_cache" : {
"memory_size_in_bytes" : 1971367836,
"total_count" : 5941141,
"hit_count" : 1281540,
"miss_count" : 4659601,
"cache_size" : 34136,
"cache_count" : 34655,
"evictions" : 519
},
"fielddata" : {
"memory_size_in_bytes" : 2270860360,
"evictions" : 0
},
"completion" : {
"size_in_bytes" : 0
},
"segments" : {
"count" : 3062,
"memory_in_bytes" : 686053834,
"terms_memory_in_bytes" : 583830952,
"stored_fields_memory_in_bytes" : 2159936,
"term_vectors_memory_in_bytes" : 0,
"norms_memory_in_bytes" : 84022720,
"points_memory_in_bytes" : 0,
"doc_values_memory_in_bytes" : 16040226,
"index_writer_memory_in_bytes" : 3083169874,
"version_map_memory_in_bytes" : 14212574,
"fixed_bit_set_memory_in_bytes" : 441678080,
"max_unsafe_auto_id_timestamp" : -1,
"file_sizes" : { }
},
"translog" : {
"operations" : 1145991,
"size_in_bytes" : 1862599220,
"uncommitted_operations" : 1145991,
"uncommitted_size_in_bytes" : 1862599220,
"earliest_last_modified_age" : 10
},
"request_cache" : {
"memory_size_in_bytes" : 0,
"evictions" : 0,
"hit_count" : 692,
"miss_count" : 7824
},
"recovery" : {
"current_as_source" : 0,
"current_as_target" : 0,
"throttle_time_in_millis" : 146589584
}
},
"total" : {
"docs" : {
"count" : 5528419715,
"deleted" : 1568758887
},
"store" : {
"size_in_bytes" : 3779599075512,
"reserved_in_bytes" : 0
},
"indexing" : {
"index_total" : 65246167,
"index_time_in_millis" : 116379853,
"index_current" : 2,
"index_failed" : 7,
"delete_total" : 56316800,
"delete_time_in_millis" : 4569453,
"delete_current" : 0,
"noop_update_total" : 108,
"is_throttled" : false,
"throttle_time_in_millis" : 0
},
"get" : {
"total" : 8279717,
"time_in_millis" : 9461541,
"exists_total" : 7721681,
"exists_time_in_millis" : 6917878,
"missing_total" : 558036,
"missing_time_in_millis" : 2543663,
"current" : 0
},
"search" : {
"open_contexts" : 200,
"query_total" : 1421264,
"query_time_in_millis" : 84711977,
"query_current" : 0,
"fetch_total" : 47121,
"fetch_time_in_millis" : 55494456,
"fetch_current" : 2,
"scroll_total" : 282690,
"scroll_time_in_millis" : 6909135621,
"scroll_current" : 200,
"suggest_total" : 0,
"suggest_time_in_millis" : 0,
"suggest_current" : 0
},
"merges" : {
"current" : 0,
"current_docs" : 0,
"current_size_in_bytes" : 0,
"total" : 8563,
"total_time_in_millis" : 30676821,
"total_docs" : 452795172,
"total_size_in_bytes" : 273814327525,
"total_stopped_time_in_millis" : 0,
"total_throttled_time_in_millis" : 6337362,
"total_auto_throttle_in_bytes" : 3305840977
},
"refresh" : {
"total" : 47329,
"total_time_in_millis" : 46367778,
"external_total" : 43783,
"external_total_time_in_millis" : 98641382,
"listeners" : 0
},
"flush" : {
"total" : 298,
"periodic" : 98,
"total_time_in_millis" : 210368
},
"warmer" : {
"current" : 0,
"total" : 43760,
"total_time_in_millis" : 52941301
},
"query_cache" : {
"memory_size_in_bytes" : 3882183058,
"total_count" : 10826442,
"hit_count" : 2195511,
"miss_count" : 8630931,
"cache_size" : 66063,
"cache_count" : 66884,
"evictions" : 821
},
"fielddata" : {
"memory_size_in_bytes" : 4524309840,
"evictions" : 0
},
"completion" : {
"size_in_bytes" : 0
},
"segments" : {
"count" : 6121,
"memory_in_bytes" : 1359222728,
"terms_memory_in_bytes" : 1155693088,
"stored_fields_memory_in_bytes" : 4324024,
"term_vectors_memory_in_bytes" : 0,
"norms_memory_in_bytes" : 166294144,
"points_memory_in_bytes" : 0,
"doc_values_memory_in_bytes" : 32911472,
"index_writer_memory_in_bytes" : 5666776518,
"version_map_memory_in_bytes" : 26231773,
"fixed_bit_set_memory_in_bytes" : 887417576,
"max_unsafe_auto_id_timestamp" : -1,
"file_sizes" : { }
},
"translog" : {
"operations" : 31206542,
"size_in_bytes" : 28262050766,
"uncommitted_operations" : 31206542,
"uncommitted_size_in_bytes" : 28262050766,
"earliest_last_modified_age" : 10
},
"request_cache" : {
"memory_size_in_bytes" : 0,
"evictions" : 0,
"hit_count" : 1296,
"miss_count" : 13655
},
"recovery" : {
"current_as_source" : 0,
"current_as_target" : 0,
"throttle_time_in_millis" : 229545608
}
}
},
"indices" : {
"segment_index_570de84a4f0d925f98343571" : {
"uuid" : "fhZUqTwfSeum3hHlyFaILw",
"primaries" : {
"docs" : {
"count" : 2764210965,
"deleted" : 768121801
},
"store" : {
"size_in_bytes" : 1882036902899,
"reserved_in_bytes" : 0
},
"indexing" : {
"index_total" : 35049143,
"index_time_in_millis" : 93342006,
"index_current" : 1,
"index_failed" : 7,
"delete_total" : 28158400,
"delete_time_in_millis" : 2241164,
"delete_current" : 0,
"noop_update_total" : 108,
"is_throttled" : false,
"throttle_time_in_millis" : 0
},
"get" : {
"total" : 8272612,
"time_in_millis" : 9407739,
"exists_total" : 7714730,
"exists_time_in_millis" : 6864869,
"missing_total" : 557882,
"missing_time_in_millis" : 2542870,
"current" : 0
},
"search" : {
"open_contexts" : 99,
"query_total" : 781661,
"query_time_in_millis" : 46180985,
"query_current" : 0,
"fetch_total" : 25828,
"fetch_time_in_millis" : 31922549,
"fetch_current" : 0,
"scroll_total" : 150005,
"scroll_time_in_millis" : 3934488045,
"scroll_current" : 99,
"suggest_total" : 0,
"suggest_time_in_millis" : 0,
"suggest_current" : 0
},
"merges" : {
"current" : 0,
"current_docs" : 0,
"current_size_in_bytes" : 0,
"total" : 5069,
"total_time_in_millis" : 15670663,
"total_docs" : 232287891,
"total_size_in_bytes" : 144734357228,
"total_stopped_time_in_millis" : 0,
"total_throttled_time_in_millis" : 3012035,
"total_auto_throttle_in_bytes" : 1635281344
},
"refresh" : {
"total" : 26258,
"total_time_in_millis" : 24294337,
"external_total" : 23116,
"external_total_time_in_millis" : 51934585,
"listeners" : 0
},
"flush" : {
"total" : 129,
"periodic" : 29,
"total_time_in_millis" : 83553
},
"warmer" : {
"current" : 0,
"total" : 23099,
"total_time_in_millis" : 28150896
},
"query_cache" : {
"memory_size_in_bytes" : 1971367836,
"total_count" : 5941141,
"hit_count" : 1281540,
"miss_count" : 4659601,
"cache_size" : 34136,
"cache_count" : 34655,
"evictions" : 519
},
"fielddata" : {
"memory_size_in_bytes" : 2270860360,
"evictions" : 0
},
"completion" : {
"size_in_bytes" : 0
},
"segments" : {
"count" : 3062,
"memory_in_bytes" : 686053834,
"terms_memory_in_bytes" : 583830952,
"stored_fields_memory_in_bytes" : 2159936,
"term_vectors_memory_in_bytes" : 0,
"norms_memory_in_bytes" : 84022720,
"points_memory_in_bytes" : 0,
"doc_values_memory_in_bytes" : 16040226,
"index_writer_memory_in_bytes" : 3083169874,
"version_map_memory_in_bytes" : 14212574,
"fixed_bit_set_memory_in_bytes" : 441678080,
"max_unsafe_auto_id_timestamp" : -1,
"file_sizes" : { }
},
"translog" : {
"operations" : 1145991,
"size_in_bytes" : 1862599220,
"uncommitted_operations" : 1145991,
"uncommitted_size_in_bytes" : 1862599220,
"earliest_last_modified_age" : 10
},
"request_cache" : {
"memory_size_in_bytes" : 0,
"evictions" : 0,
"hit_count" : 692,
"miss_count" : 7824
},
"recovery" : {
"current_as_source" : 0,
"current_as_target" : 0,
"throttle_time_in_millis" : 146589584
}
},
"total" : {
"docs" : {
"count" : 5528419715,
"deleted" : 1568758887
},
"store" : {
"size_in_bytes" : 3779599075512,
"reserved_in_bytes" : 0
},
"indexing" : {
"index_total" : 65246167,
"index_time_in_millis" : 116379853,
"index_current" : 2,
"index_failed" : 7,
"delete_total" : 56316800,
"delete_time_in_millis" : 4569453,
"delete_current" : 0,
"noop_update_total" : 108,
"is_throttled" : false,
"throttle_time_in_millis" : 0
},
"get" : {
"total" : 8279717,
"time_in_millis" : 9461541,
"exists_total" : 7721681,
"exists_time_in_millis" : 6917878,
"missing_total" : 558036,
"missing_time_in_millis" : 2543663,
"current" : 0
},
"search" : {
"open_contexts" : 200,
"query_total" : 1421264,
"query_time_in_millis" : 84711977,
"query_current" : 0,
"fetch_total" : 47121,
"fetch_time_in_millis" : 55494456,
"fetch_current" : 2,
"scroll_total" : 282690,
"scroll_time_in_millis" : 6909135621,
"scroll_current" : 200,
"suggest_total" : 0,
"suggest_time_in_millis" : 0,
"suggest_current" : 0
},
"merges" : {
"current" : 0,
"current_docs" : 0,
"current_size_in_bytes" : 0,
"total" : 8563,
"total_time_in_millis" : 30676821,
"total_docs" : 452795172,
"total_size_in_bytes" : 273814327525,
"total_stopped_time_in_millis" : 0,
"total_throttled_time_in_millis" : 6337362,
"total_auto_throttle_in_bytes" : 3305840977
},
"refresh" : {
"total" : 47329,
"total_time_in_millis" : 46367778,
"external_total" : 43783,
"external_total_time_in_millis" : 98641382,
"listeners" : 0
},
"flush" : {
"total" : 298,
"periodic" : 98,
"total_time_in_millis" : 210368
},
"warmer" : {
"current" : 0,
"total" : 43760,
"total_time_in_millis" : 52941301
},
"query_cache" : {
"memory_size_in_bytes" : 3882183058,
"total_count" : 10826442,
"hit_count" : 2195511,
"miss_count" : 8630931,
"cache_size" : 66063,
"cache_count" : 66884,
"evictions" : 821
},
"fielddata" : {
"memory_size_in_bytes" : 4524309840,
"evictions" : 0
},
"completion" : {
"size_in_bytes" : 0
},
"segments" : {
"count" : 6121,
"memory_in_bytes" : 1359222728,
"terms_memory_in_bytes" : 1155693088,
"stored_fields_memory_in_bytes" : 4324024,
"term_vectors_memory_in_bytes" : 0,
"norms_memory_in_bytes" : 166294144,
"points_memory_in_bytes" : 0,
"doc_values_memory_in_bytes" : 32911472,
"index_writer_memory_in_bytes" : 5666776518,
"version_map_memory_in_bytes" : 26231773,
"fixed_bit_set_memory_in_bytes" : 887417576,
"max_unsafe_auto_id_timestamp" : -1,
"file_sizes" : { }
},
"translog" : {
"operations" : 31206542,
"size_in_bytes" : 28262050766,
"uncommitted_operations" : 31206542,
"uncommitted_size_in_bytes" : 28262050766,
"earliest_last_modified_age" : 10
},
"request_cache" : {
"memory_size_in_bytes" : 0,
"evictions" : 0,
"hit_count" : 1296,
"miss_count" : 13655
},
"recovery" : {
"current_as_source" : 0,
"current_as_target" : 0,
"throttle_time_in_millis" : 229545608
}
}
}
}
}

请指导我采取适当的方法来处理这一问题并优化的搜索性能

在这种情况下,我通常会运行forcemerge,只删除已删除的文档

POST _forcemerge?only_expunge_deletes=true

由于删除的文档/总文档的比例约为30%,因此应该可以让您重新获得一些空间。。。

先在一个索引上试试。记录前后的大小,你应该会看到一些空间。

最新更新