ElasticSearch output of _nodes/stats?pretty -- for analysis of why heap needs to be over 2GB.

gistfile1.json

{
  "cluster_name" : "elasticsearch",
  "nodes" : {
    "REDACTED" : {
      "timestamp" : 1421060315273,
      "name" : "monitoring-02",
      "transport_address" : "inet[/REDACTED:9300]",
      "host" : "monitoring-02",
      "ip" : [ "inet[/REDACTED:9300]", "NONE" ],
      "indices" : {
        "docs" : {
          "count" : 33572665,
          "deleted" : 0
        },
        "store" : {
          "size_in_bytes" : 35325488265,
          "throttle_time_in_millis" : 1001644
        },
        "indexing" : {
          "index_total" : 2385254,
          "index_time_in_millis" : 1056177,
          "index_current" : 0,
          "delete_total" : 0,
          "delete_time_in_millis" : 0,
          "delete_current" : 0
        },
        "get" : {
          "total" : 2,
          "time_in_millis" : 1,
          "exists_total" : 2,
          "exists_time_in_millis" : 1,
          "missing_total" : 0,
          "missing_time_in_millis" : 0,
          "current" : 0
        },
        "search" : {
          "open_contexts" : 0,
          "query_total" : 5980,
          "query_time_in_millis" : 23715,
          "query_current" : 0,
          "fetch_total" : 686,
          "fetch_time_in_millis" : 1142,
          "fetch_current" : 0
        },
        "merges" : {
          "current" : 0,
          "current_docs" : 0,
          "current_size_in_bytes" : 0,
          "total" : 25591,
          "total_time_in_millis" : 8145961,
          "total_docs" : 89042897,
          "total_size_in_bytes" : 105938452318
        },
        "refresh" : {
          "total" : 235568,
          "total_time_in_millis" : 2608859
        },
        "flush" : {
          "total" : 841,
          "total_time_in_millis" : 519917
        },
        "warmer" : {
          "current" : 0,
          "total" : 492264,
          "total_time_in_millis" : 115589
        },
        "filter_cache" : {
          "memory_size_in_bytes" : 100688,
          "evictions" : 0
        },
        "id_cache" : {
          "memory_size_in_bytes" : 0
        },
        "fielddata" : {
          "memory_size_in_bytes" : 3713608,
          "evictions" : 0
        },
        "percolate" : {
          "total" : 0,
          "time_in_millis" : 0,
          "current" : 0,
          "memory_size_in_bytes" : -1,
          "memory_size" : "-1b",
          "queries" : 0
        },
        "completion" : {
          "size_in_bytes" : 0
        },
        "segments" : {
          "count" : 2883,
          "memory_in_bytes" : 1275165840,
          "index_writer_memory_in_bytes" : 475612,
          "version_map_memory_in_bytes" : 6536
        },
        "translog" : {
          "operations" : 21629,
          "size_in_bytes" : 0
        },
        "suggest" : {
          "total" : 0,
          "time_in_millis" : 0,
          "current" : 0
        }
      },
      "os" : {
        "timestamp" : 1421060316390,
        "uptime_in_millis" : 308426,
        "load_average" : [ 2.16, 1.71, 1.55 ],
        "cpu" : {
          "sys" : 1,
          "user" : 9,
          "idle" : 84,
          "usage" : 10,
          "stolen" : 0
        },
        "mem" : {
          "free_in_bytes" : 1263923200,
          "used_in_bytes" : 7108706304,
          "free_percent" : 45,
          "used_percent" : 54,
          "actual_free_in_bytes" : 3821703168,
          "actual_used_in_bytes" : 4550926336
        },
        "swap" : {
          "used_in_bytes" : 159744,
          "free_in_bytes" : 821919744
        }
      },
      "process" : {
        "timestamp" : 1421060316391,
        "open_file_descriptors" : 9482,
        "cpu" : {
          "percent" : 32,
          "sys_in_millis" : 7198300,
          "user_in_millis" : 49129050,
          "total_in_millis" : 56327350
        },
        "mem" : {
          "resident_in_bytes" : 2771247104,
          "share_in_bytes" : 38199296,
          "total_virtual_in_bytes" : 19026513920
        }
      },
      "jvm" : {
        "timestamp" : 1421060316396,
        "uptime_in_millis" : 303072733,
        "mem" : {
          "heap_used_in_bytes" : 2264790672,
          "heap_used_percent" : 71,
          "heap_committed_in_bytes" : 3186360320,
          "heap_max_in_bytes" : 3186360320,
          "non_heap_used_in_bytes" : 52775528,
          "non_heap_committed_in_bytes" : 80363520,
          "pools" : {
            "young" : {
              "used_in_bytes" : 211515000,
              "max_in_bytes" : 279183360,
              "peak_used_in_bytes" : 279183360,
              "peak_max_in_bytes" : 279183360
            },
            "survivor" : {
              "used_in_bytes" : 16317936,
              "max_in_bytes" : 34865152,
              "peak_used_in_bytes" : 34865152,
              "peak_max_in_bytes" : 34865152
            },
            "old" : {
              "used_in_bytes" : 2036957736,
              "max_in_bytes" : 2872311808,
              "peak_used_in_bytes" : 2160199936,
              "peak_max_in_bytes" : 2872311808
            }
          }
        },
        "threads" : {
          "count" : 72,
          "peak_count" : 76
        },
        "gc" : {
          "collectors" : {
            "young" : {
              "collection_count" : 83026,
              "collection_time_in_millis" : 1033012
            },
            "old" : {
              "collection_count" : 274,
              "collection_time_in_millis" : 21758
            }
          }
        },
        "buffer_pools" : {
          "direct" : {
            "count" : 64,
            "used_in_bytes" : 13061311,
            "total_capacity_in_bytes" : 13061311
          },
          "mapped" : {
            "count" : 3978,
            "used_in_bytes" : 13254262144,
            "total_capacity_in_bytes" : 13254262144
          }
        }
      },
      "thread_pool" : {
        "generic" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 5,
          "completed" : 91516
        },
        "index" : {
          "threads" : 1,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 1,
          "completed" : 1
        },
        "snapshot_data" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "bench" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "get" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 2,
          "completed" : 2
        },
        "snapshot" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "merge" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 2,
          "completed" : 496234
        },
        "suggest" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "bulk" : {
          "threads" : 4,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 4,
          "completed" : 2385254
        },
        "optimize" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "warmer" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 2,
          "completed" : 256252
        },
        "flush" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 2,
          "completed" : 229764
        },
        "search" : {
          "threads" : 12,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 12,
          "completed" : 6666
        },
        "percolate" : {
          "threads" : 0,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 0,
          "completed" : 0
        },
        "management" : {
          "threads" : 3,
          "queue" : 0,
          "active" : 1,
          "rejected" : 0,
          "largest" : 3,
          "completed" : 50530
        },
        "refresh" : {
          "threads" : 2,
          "queue" : 0,
          "active" : 0,
          "rejected" : 0,
          "largest" : 2,
          "completed" : 235334
        }
      },
      "network" : {
        "tcp" : {
          "active_opens" : 440155,
          "passive_opens" : 872034,
          "curr_estab" : 130,
          "in_segs" : 43919765,
          "out_segs" : 42829383,
          "retrans_segs" : 4198,
          "estab_resets" : 4099,
          "attempt_fails" : 204,
          "in_errs" : 0,
          "out_rsts" : 3735
        }
      },
      "fs" : {
        "timestamp" : 1421060316396,
        "total" : {
          "total_in_bytes" : 221333442560,
          "free_in_bytes" : 184169394176,
          "available_in_bytes" : 172902658048,
          "disk_reads" : 66460,
          "disk_writes" : 6116675,
          "disk_io_op" : 6183135,
          "disk_read_size_in_bytes" : 1265398784,
          "disk_write_size_in_bytes" : 133966233600,
          "disk_io_size_in_bytes" : 135231632384
        },
        "data" : [ {
          "path" : "/data/elasticsearch/elasticsearch/nodes/0",
          "mount" : "/data",
          "dev" : "/dev/mapper/vg_autodata-lv_data",
          "total_in_bytes" : 221333442560,
          "free_in_bytes" : 184169394176,
          "available_in_bytes" : 172902658048,
          "disk_reads" : 66460,
          "disk_writes" : 6116675,
          "disk_io_op" : 6183135,
          "disk_read_size_in_bytes" : 1265398784,
          "disk_write_size_in_bytes" : 133966233600,
          "disk_io_size_in_bytes" : 135231632384
        } ]
      },
      "transport" : {
        "server_open" : 13,
        "rx_count" : 0,
        "rx_size_in_bytes" : 0,
        "tx_count" : 0,
        "tx_size_in_bytes" : 0
      },
      "http" : {
        "current_open" : 3,
        "total_opened" : 61850
      },
      "fielddata_breaker" : {
        "maximum_size_in_bytes" : 1911816192,
        "maximum_size" : "1.7gb",
        "estimated_size_in_bytes" : 3713608,
        "estimated_size" : "3.5mb",
        "overhead" : 1.03,
        "tripped" : 0
      }
    }
  }
}

Discussion afterwards in #elasticsearch on Freenode:

11:04 <dakrone> mikepea: you have a very high segment count and it looks like the segments memory_in_bytes is about 1.2gb out of your 3gb heap
11:04 <dakrone> mikepea: also, it looks like you're using swap (which will make things very slow for JVM-based processes!)
11:05 <dakrone> mikepea: how many shards does this cluster have?
11:05 <mikepea> just the one
11:05 <mikepea> I'd say it's a typical 'small' ELK stack box. 
11:06 ⇐ johnraz_ quit (~johnraz@unaffiliated/johnraz) Ping timeout: 245 seconds
11:06 <dakrone> one shard? that is a lot of segments for a single shard
11:06 <dakrone> how big is the index?
11:06 <dakrone> size and document-wise
11:08 <mikepea> dakrone: 33GB for all indices, currently there are 44 indices (logstash daily pattern)
11:09 → costin_ joined ([email protected])
11:09 <mikepea> is indices->docs->count the doc count? In which case 33 million docs.
11:10  → jluis joined  ⇐ costin, falood and ArnaudM quit  
11:12 <dakrone> mikepea: oh okay, segment count is okay for 44 indices, in that case, since it's just lucene segment memory, that seems pretty reasonable, you have only the single node?
11:13 <mikepea> yeah, at the moment. Considering the potential of creating a larger stack, but for now it's not cost justifiable to have many ES nodes in the stack. 
11:13 ⇐ darkelda quit (~darkelda@unaffiliated/darkelda) Ping timeout: 265 seconds
11:15 <dakrone> okay, well if you can't add nodes, you could delete or close older indices, which would free the lucene memory associated with them
11:15 <mikepea> i guess this is a 'tuning ELK' question really. How can we reduce the segments memory_in_bytes count for an ELK system that's largely concerned with quick query of the current day's index.
11:15 <mikepea> is there any way of saying 'load this index into segment memory dynamically'?
11:16 <dakrone> mikepea: something you could do is optimize older indices that you are not indexing into into a single segment, see: http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/indices-optimize.html#indices-optimize
11:16 <dakrone> set max_num_segments to 1 in that case
11:16 ⇐ Xylakant quit ([email protected]) Quit: Leaving...
11:16 <dakrone> you can also use the curator tool to do it
11:18  → nickjj joined  ⇐ gschuring quit  
11:19 <mikepea> that sounds like a fine plan. We already have curator in place, but just for purging old data. I'll start graphing  segments memory_in_bytes and enable optimizing in curator.
11:19 <mikepea> thanks a million, this was gold knowledge. I'll update the gist with this discussion :)

As a follow-up, I configured curator to run daily as curator optimize --older-than 3 --max_num_segments 1

This dropped segments (on a test system) down from 600ish to 300ish, and heap seemed to reduce to 40% (from 80%). Interestingly segment memory (on the test system) only reduced from 250MB to 225MB.

I'll post results for the production system above when it has been applied.