Commit 25075fa
committed
[ML] Cache Inference Endpoints
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.cache.enabled` enables or disables the cache (default
enabled).
- `xpack.inference.cache.weight` controls how many endpoints can live in
the cache (default 25).
- `xpack.inference.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 #1331351 parent ea95e9e commit 25075fa
File tree
18 files changed
+893
-103
lines changed- x-pack/plugin
- core/src
- main/java/org/elasticsearch/xpack/core/inference
- action
- test/java/org/elasticsearch/xpack/core/inference/action
- inference/src
- main/java/org/elasticsearch/xpack/inference
- action
- registry
- test/java/org/elasticsearch/xpack/inference
- action
- registry
18 files changed
+893
-103
lines changedLines changed: 2 additions & 4 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
7 | 7 | | |
8 | 8 | | |
9 | 9 | | |
10 | | - | |
| 10 | + | |
11 | 11 | | |
12 | 12 | | |
13 | | - | |
14 | | - | |
15 | | - | |
| 13 | + | |
Lines changed: 24 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 | | |
| |||
18 | 19 | | |
19 | 20 | | |
20 | 21 | | |
| 22 | + | |
21 | 23 | | |
22 | 24 | | |
23 | 25 | | |
24 | 26 | | |
| 27 | + | |
25 | 28 | | |
26 | 29 | | |
27 | 30 | | |
| |||
116 | 119 | | |
117 | 120 | | |
118 | 121 | | |
| 122 | + | |
119 | 123 | | |
120 | 124 | | |
| 125 | + | |
| 126 | + | |
121 | 127 | | |
122 | | - | |
| 128 | + | |
123 | 129 | | |
124 | 130 | | |
| 131 | + | |
125 | 132 | | |
126 | 133 | | |
127 | 134 | | |
128 | 135 | | |
129 | 136 | | |
130 | 137 | | |
| 138 | + | |
| 139 | + | |
| 140 | + | |
131 | 141 | | |
132 | 142 | | |
133 | 143 | | |
134 | 144 | | |
135 | 145 | | |
136 | 146 | | |
| 147 | + | |
| 148 | + | |
| 149 | + | |
137 | 150 | | |
138 | 151 | | |
139 | 152 | | |
140 | 153 | | |
141 | 154 | | |
| 155 | + | |
| 156 | + | |
| 157 | + | |
142 | 158 | | |
143 | 159 | | |
144 | 160 | | |
| |||
147 | 163 | | |
148 | 164 | | |
149 | 165 | | |
150 | | - | |
| 166 | + | |
| 167 | + | |
151 | 168 | | |
152 | 169 | | |
153 | 170 | | |
154 | 171 | | |
155 | | - | |
| 172 | + | |
156 | 173 | | |
157 | 174 | | |
158 | 175 | | |
159 | 176 | | |
160 | 177 | | |
161 | 178 | | |
| 179 | + | |
| 180 | + | |
| 181 | + | |
| 182 | + | |
162 | 183 | | |
163 | 184 | | |
164 | 185 | | |
| |||
Lines changed: 53 additions & 5 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
11 | 11 | | |
12 | 12 | | |
13 | 13 | | |
| 14 | + | |
| 15 | + | |
| 16 | + | |
14 | 17 | | |
15 | 18 | | |
| 19 | + | |
| 20 | + | |
16 | 21 | | |
17 | 22 | | |
18 | 23 | | |
| 24 | + | |
19 | 25 | | |
20 | 26 | | |
21 | 27 | | |
22 | 28 | | |
23 | 29 | | |
24 | 30 | | |
25 | 31 | | |
26 | | - | |
| 32 | + | |
| 33 | + | |
| 34 | + | |
| 35 | + | |
| 36 | + | |
| 37 | + | |
| 38 | + | |
| 39 | + | |
| 40 | + | |
| 41 | + | |
| 42 | + | |
| 43 | + | |
27 | 44 | | |
28 | 45 | | |
29 | 46 | | |
| |||
50 | 67 | | |
51 | 68 | | |
52 | 69 | | |
53 | | - | |
| 70 | + | |
| 71 | + | |
54 | 72 | | |
55 | 73 | | |
56 | 74 | | |
| |||
59 | 77 | | |
60 | 78 | | |
61 | 79 | | |
62 | | - | |
| 80 | + | |
| 81 | + | |
63 | 82 | | |
64 | 83 | | |
65 | 84 | | |
| |||
68 | 87 | | |
69 | 88 | | |
70 | 89 | | |
71 | | - | |
| 90 | + | |
| 91 | + | |
72 | 92 | | |
73 | 93 | | |
74 | 94 | | |
| |||
77 | 97 | | |
78 | 98 | | |
79 | 99 | | |
80 | | - | |
| 100 | + | |
| 101 | + | |
81 | 102 | | |
82 | 103 | | |
83 | 104 | | |
84 | 105 | | |
| 106 | + | |
| 107 | + | |
| 108 | + | |
| 109 | + | |
| 110 | + | |
| 111 | + | |
| 112 | + | |
| 113 | + | |
| 114 | + | |
| 115 | + | |
| 116 | + | |
| 117 | + | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
| 121 | + | |
| 122 | + | |
| 123 | + | |
| 124 | + | |
| 125 | + | |
| 126 | + | |
| 127 | + | |
| 128 | + | |
| 129 | + | |
| 130 | + | |
| 131 | + | |
| 132 | + | |
85 | 133 | | |
Lines changed: 14 additions & 2 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
10 | 10 | | |
11 | 11 | | |
12 | 12 | | |
| 13 | + | |
13 | 14 | | |
14 | 15 | | |
15 | 16 | | |
| |||
36 | 37 | | |
37 | 38 | | |
38 | 39 | | |
39 | | - | |
| 40 | + | |
| 41 | + | |
| 42 | + | |
| 43 | + | |
| 44 | + | |
| 45 | + | |
| 46 | + | |
40 | 47 | | |
41 | 48 | | |
42 | 49 | | |
| |||
46 | 53 | | |
47 | 54 | | |
48 | 55 | | |
49 | | - | |
| 56 | + | |
50 | 57 | | |
51 | 58 | | |
52 | 59 | | |
| |||
67 | 74 | | |
68 | 75 | | |
69 | 76 | | |
| 77 | + | |
| 78 | + | |
| 79 | + | |
| 80 | + | |
| 81 | + | |
70 | 82 | | |
Lines changed: 31 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
7 | 7 | | |
8 | 8 | | |
9 | 9 | | |
| 10 | + | |
| 11 | + | |
| 12 | + | |
10 | 13 | | |
11 | 14 | | |
12 | 15 | | |
| |||
17 | 20 | | |
18 | 21 | | |
19 | 22 | | |
| 23 | + | |
20 | 24 | | |
21 | 25 | | |
22 | 26 | | |
| |||
31 | 35 | | |
32 | 36 | | |
33 | 37 | | |
| 38 | + | |
| 39 | + | |
34 | 40 | | |
35 | 41 | | |
36 | 42 | | |
| |||
600 | 606 | | |
601 | 607 | | |
602 | 608 | | |
| 609 | + | |
| 610 | + | |
| 611 | + | |
| 612 | + | |
| 613 | + | |
| 614 | + | |
| 615 | + | |
| 616 | + | |
| 617 | + | |
| 618 | + | |
| 619 | + | |
| 620 | + | |
| 621 | + | |
| 622 | + | |
| 623 | + | |
| 624 | + | |
| 625 | + | |
| 626 | + | |
| 627 | + | |
| 628 | + | |
| 629 | + | |
| 630 | + | |
| 631 | + | |
| 632 | + | |
| 633 | + | |
603 | 634 | | |
604 | 635 | | |
605 | 636 | | |
| |||
Lines changed: 45 additions & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
104 | 104 | | |
105 | 105 | | |
106 | 106 | | |
| 107 | + | |
| 108 | + | |
107 | 109 | | |
108 | 110 | | |
109 | 111 | | |
| |||
199 | 201 | | |
200 | 202 | | |
201 | 203 | | |
| 204 | + | |
| 205 | + | |
| 206 | + | |
| 207 | + | |
| 208 | + | |
| 209 | + | |
| 210 | + | |
| 211 | + | |
| 212 | + | |
| 213 | + | |
| 214 | + | |
| 215 | + | |
| 216 | + | |
| 217 | + | |
| 218 | + | |
| 219 | + | |
| 220 | + | |
| 221 | + | |
| 222 | + | |
| 223 | + | |
| 224 | + | |
202 | 225 | | |
203 | 226 | | |
204 | 227 | | |
| |||
237 | 260 | | |
238 | 261 | | |
239 | 262 | | |
240 | | - | |
| 263 | + | |
| 264 | + | |
241 | 265 | | |
242 | 266 | | |
243 | 267 | | |
| |||
389 | 413 | | |
390 | 414 | | |
391 | 415 | | |
| 416 | + | |
| 417 | + | |
| 418 | + | |
| 419 | + | |
| 420 | + | |
| 421 | + | |
| 422 | + | |
| 423 | + | |
| 424 | + | |
| 425 | + | |
392 | 426 | | |
393 | 427 | | |
394 | 428 | | |
| |||
443 | 477 | | |
444 | 478 | | |
445 | 479 | | |
| 480 | + | |
| 481 | + | |
| 482 | + | |
| 483 | + | |
| 484 | + | |
| 485 | + | |
| 486 | + | |
446 | 487 | | |
447 | 488 | | |
448 | 489 | | |
| |||
527 | 568 | | |
528 | 569 | | |
529 | 570 | | |
| 571 | + | |
| 572 | + | |
| 573 | + | |
530 | 574 | | |
531 | 575 | | |
532 | 576 | | |
| |||
0 commit comments