Commit 422db0d
authored
[ML] Cache Inference Endpoints (elastic#133860)
Maintain parsed Inference Endpoints in memory for reuse. Endpoints are
cached on first access and expire after write. This removes search
pressure during inference, bypassing search requests to system indices
for repeated model access. When any endpoint is updated or deleted, the
whole cache is invalidated and must be reloaded.
Cache can be configured with three settings:
- `xpack.inference.endpoint.cache.enabled` enables or disables the cache (default
enabled).
- `xpack.inference.endpoint.cache.weight` controls how many endpoints can live in
the cache (default 25).
- `xpack.inference.endpoint.cache.expiry_time` controls how long endpoints live
in the cache, measured from when they are first accessed (default 15
minutes, minimum 1 minute, maximum 1 hour).
Resolve elastic#1331351 parent 500b68a commit 422db0d
File tree
23 files changed
+938
-146
lines changed- docs/changelog
- server/src/main/java/org/elasticsearch
- x-pack/plugin
- core/src
- main/java/org/elasticsearch/xpack/core/inference
- action
- test/java/org/elasticsearch/xpack/core/inference/action
- inference
- qa/inference-service-tests/src/javaRestTest/java/org/elasticsearch/xpack/inference
- src
- main/java/org/elasticsearch/xpack/inference
- action
- registry
- test/java/org/elasticsearch/xpack/inference
- action
- registry
- ml/qa/native-multi-node-tests/src/javaRestTest/java/org/elasticsearch/xpack/ml/integration
- security/qa/operator-privileges-tests/src/javaRestTest/java/org/elasticsearch/xpack/security/operator
23 files changed
+938
-146
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
| 4 | + | |
| 5 | + | |
| 6 | + | |
Lines changed: 1 addition & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
335 | 335 | | |
336 | 336 | | |
337 | 337 | | |
| 338 | + | |
338 | 339 | | |
339 | 340 | | |
340 | 341 | | |
| |||
Lines changed: 0 additions & 15 deletions
This file was deleted.
Lines changed: 60 additions & 4 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
19 | 19 | | |
20 | 20 | | |
21 | 21 | | |
| 22 | + | |
22 | 23 | | |
23 | 24 | | |
24 | 25 | | |
| |||
28 | 29 | | |
29 | 30 | | |
30 | 31 | | |
| 32 | + | |
| 33 | + | |
31 | 34 | | |
32 | 35 | | |
33 | 36 | | |
| |||
119 | 122 | | |
120 | 123 | | |
121 | 124 | | |
| 125 | + | |
122 | 126 | | |
123 | 127 | | |
124 | 128 | | |
125 | | - | |
126 | | - | |
| 129 | + | |
| 130 | + | |
| 131 | + | |
| 132 | + | |
| 133 | + | |
| 134 | + | |
| 135 | + | |
| 136 | + | |
| 137 | + | |
127 | 138 | | |
128 | 139 | | |
129 | 140 | | |
| 141 | + | |
130 | 142 | | |
131 | 143 | | |
132 | 144 | | |
| |||
138 | 150 | | |
139 | 151 | | |
140 | 152 | | |
| 153 | + | |
| 154 | + | |
| 155 | + | |
141 | 156 | | |
142 | 157 | | |
143 | 158 | | |
| |||
148 | 163 | | |
149 | 164 | | |
150 | 165 | | |
| 166 | + | |
| 167 | + | |
| 168 | + | |
151 | 169 | | |
152 | 170 | | |
153 | 171 | | |
| |||
163 | 181 | | |
164 | 182 | | |
165 | 183 | | |
| 184 | + | |
| 185 | + | |
| 186 | + | |
166 | 187 | | |
167 | 188 | | |
168 | 189 | | |
| |||
172 | 193 | | |
173 | 194 | | |
174 | 195 | | |
175 | | - | |
| 196 | + | |
| 197 | + | |
176 | 198 | | |
177 | 199 | | |
178 | 200 | | |
179 | 201 | | |
180 | | - | |
| 202 | + | |
181 | 203 | | |
182 | 204 | | |
183 | 205 | | |
| |||
188 | 210 | | |
189 | 211 | | |
190 | 212 | | |
| 213 | + | |
| 214 | + | |
| 215 | + | |
| 216 | + | |
191 | 217 | | |
192 | 218 | | |
193 | 219 | | |
| |||
270 | 296 | | |
271 | 297 | | |
272 | 298 | | |
| 299 | + | |
| 300 | + | |
| 301 | + | |
| 302 | + | |
| 303 | + | |
| 304 | + | |
| 305 | + | |
| 306 | + | |
| 307 | + | |
| 308 | + | |
| 309 | + | |
| 310 | + | |
| 311 | + | |
| 312 | + | |
| 313 | + | |
| 314 | + | |
| 315 | + | |
| 316 | + | |
| 317 | + | |
| 318 | + | |
| 319 | + | |
| 320 | + | |
| 321 | + | |
| 322 | + | |
| 323 | + | |
| 324 | + | |
| 325 | + | |
| 326 | + | |
| 327 | + | |
| 328 | + | |
273 | 329 | | |
274 | 330 | | |
Lines changed: 46 additions & 15 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
26 | 26 | | |
27 | 27 | | |
28 | 28 | | |
29 | | - | |
| 29 | + | |
30 | 30 | | |
31 | 31 | | |
32 | 32 | | |
| |||
45 | 45 | | |
46 | 46 | | |
47 | 47 | | |
48 | | - | |
| 48 | + | |
| 49 | + | |
| 50 | + | |
| 51 | + | |
| 52 | + | |
| 53 | + | |
49 | 54 | | |
50 | 55 | | |
51 | 56 | | |
52 | | - | |
| 57 | + | |
53 | 58 | | |
54 | 59 | | |
55 | 60 | | |
| |||
79 | 84 | | |
80 | 85 | | |
81 | 86 | | |
| 87 | + | |
| 88 | + | |
| 89 | + | |
| 90 | + | |
| 91 | + | |
| 92 | + | |
| 93 | + | |
| 94 | + | |
| 95 | + | |
82 | 96 | | |
83 | 97 | | |
84 | 98 | | |
85 | 99 | | |
86 | 100 | | |
87 | | - | |
88 | | - | |
89 | | - | |
90 | | - | |
91 | | - | |
92 | | - | |
93 | | - | |
94 | | - | |
95 | | - | |
96 | | - | |
97 | | - | |
98 | | - | |
| 101 | + | |
| 102 | + | |
| 103 | + | |
| 104 | + | |
| 105 | + | |
| 106 | + | |
| 107 | + | |
| 108 | + | |
99 | 109 | | |
100 | 110 | | |
| 111 | + | |
| 112 | + | |
| 113 | + | |
| 114 | + | |
| 115 | + | |
| 116 | + | |
| 117 | + | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
| 121 | + | |
| 122 | + | |
| 123 | + | |
| 124 | + | |
| 125 | + | |
| 126 | + | |
| 127 | + | |
| 128 | + | |
| 129 | + | |
| 130 | + | |
| 131 | + | |
101 | 132 | | |
102 | 133 | | |
Lines changed: 33 additions & 3 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
8 | 8 | | |
9 | 9 | | |
10 | 10 | | |
| 11 | + | |
11 | 12 | | |
12 | 13 | | |
13 | 14 | | |
14 | 15 | | |
15 | | - | |
16 | 16 | | |
17 | 17 | | |
18 | 18 | | |
| 19 | + | |
19 | 20 | | |
20 | 21 | | |
21 | 22 | | |
22 | 23 | | |
23 | 24 | | |
24 | 25 | | |
25 | | - | |
| 26 | + | |
| 27 | + | |
26 | 28 | | |
27 | 29 | | |
28 | 30 | | |
| |||
39 | 41 | | |
40 | 42 | | |
41 | 43 | | |
42 | | - | |
| 44 | + | |
| 45 | + | |
| 46 | + | |
| 47 | + | |
| 48 | + | |
| 49 | + | |
| 50 | + | |
| 51 | + | |
43 | 52 | | |
44 | 53 | | |
45 | 54 | | |
| |||
65 | 74 | | |
66 | 75 | | |
67 | 76 | | |
| 77 | + | |
| 78 | + | |
| 79 | + | |
| 80 | + | |
| 81 | + | |
| 82 | + | |
68 | 83 | | |
69 | 84 | | |
70 | 85 | | |
| |||
88 | 103 | | |
89 | 104 | | |
90 | 105 | | |
| 106 | + | |
| 107 | + | |
| 108 | + | |
| 109 | + | |
| 110 | + | |
| 111 | + | |
| 112 | + | |
| 113 | + | |
| 114 | + | |
| 115 | + | |
| 116 | + | |
| 117 | + | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
91 | 121 | | |
0 commit comments