Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "34b260b6-a504-4cce-a9b3-a3566a8dbeb5",
"metadata": {},
"outputs": [],
"source": [
"import random\n",
"import requests\n",
"import pandas as pd\n",
"\n",
"r = requests.get(\"https://pages.cs.wisc.edu/~harter/cs544/data/wi-stations/stations.txt\")\n",
"r.raise_for_status()\n",
"stations = r.text.strip().split(\"\\n\")\n",
"stations = random.sample(stations, k=10)\n",
"workload = random.choices(stations, k=100, weights=[0.3, 0.2] + [0.5/8]*8)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "c65f907c-049f-4110-a5ca-75772e76fdcf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"np.float64(3.0)"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import numpy as np\n",
"np.quantile([1,2,4,5], 0.5)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e913b0fa-138c-4fb1-99df-738e79b7b5ad",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'US1WIIW0014 US1WIPC0020 USC00478805 US1WIBR0019 US1WIPC0020 US1WIBR0019 USC00474391 US1WIPC0020 USC00470062 USC00478805 US1WIBR0019 US1WIBR0019 US1WIIW0014 USC00478329 US1WIIW0014 US1WIBR0019 USC00478329 USC00470062 US1WIBR0019 USC00474391 US1WIMM0001 US1WIIW0014 US1WIBR0019 US1WIBR0019 US1WIMM0001 US1WIIW0014 US1WIBR0019 US1WIBR0019 USC00478805 US1WIIW0014 US1WIBR0019 US1WIIW0014 US1WIDG0011 US1WIIW0014 US1WIIW0014 US1WIDG0011 US1WIDG0011 USC00478805 US1WIIW0014 USC00478329 US1WIDG0011 US1WIBR0019 US1WIIW0014 US1WIIW0014 US1WIDG0011 USC00478805 USC00474391 US1WIBR0019 US1WIMM0001 USC00478329 US1WIBR0019 US1WIIW0014 US1WIPC0020 US1WIIW0014 US1WIBR0019 US1WIBR0019 USC00474391 US1WIBR0019 US1WIDG0011 US1WIVL0014 US1WIIW0014 US1WIIW0014 USC00478805 USC00470062 US1WIIW0014 USC00474391 US1WIBR0019 US1WIVL0014 US1WIIW0014 US1WIBR0019 USC00470062 US1WIBR0019 US1WIBR0019 US1WIPC0020 USC00478805 US1WIPC0020 USC00470062 USC00478329 US1WIPC0020 US1WIMM0001 USC00478329 USC00478329 USC00474391 US1WIBR0019 US1WIBR0019 USC00478805 USC00470062 US1WIIW0014 USC00470062 US1WIMM0001 US1WIBR0019 USC00474391 US1WIIW0014 US1WIPC0020 US1WIIW0014 US1WIIW0014 US1WIBR0019 US1WIBR0019 US1WIIW0014 US1WIPC0020'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\" \".join(workload)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "3a66f04d-2361-4ca9-8556-d781d9e5b96c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1739200561.2493458"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import time\n",
"time.time() # seconds since Jan 1, 1970"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "ed3e0c8a-6831-411c-b26c-2d14555127f0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2000.2596378326416"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"start = time.time()\n",
"time.sleep(2)\n",
"end = time.time()\n",
"(end-start) * 1000 # milliseconds"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "508955f2-0071-4683-aae8-a8ddf8601570",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"miss miss miss miss hit hit miss miss miss miss miss hit miss miss hit hit hit miss miss miss miss miss miss hit hit hit hit hit miss hit hit hit miss miss hit hit hit hit hit miss hit miss hit hit miss miss miss miss miss miss hit miss miss hit miss hit miss hit miss miss miss hit miss miss hit miss miss miss miss hit miss miss hit miss miss hit miss miss miss miss hit hit miss miss hit miss miss miss hit miss miss miss miss miss hit hit miss hit hit hit "
]
}
],
"source": [
"# Example 1: FIFO Policy\n",
"\n",
"cache_size = 3\n",
"cache = {} # key=station name, value=DataFrame with weather data for that station\n",
"evict_order = [] # evict from the left, try to keep whatever is on the right\n",
"\n",
"# stats\n",
"hits = [] # 1 is a hit, 0 is a miss\n",
"latency_ms = [] # latency of get_station in milliseconds\n",
"\n",
"def get_station(station):\n",
" start = time.time()\n",
" if station in cache:\n",
" hits.append(1)\n",
" print(\"hit\", end=\" \")\n",
" df = cache[station]\n",
" else:\n",
" hits.append(0)\n",
" print(\"miss\", end=\" \")\n",
" df = pd.read_csv(f\"https://pages.cs.wisc.edu/~harter/cs544/data/wi-stations/{station}.csv.gz\",\n",
" names=[\"station\", \"date\", \"element\", \"value\", \"m\", \"q\", \"s\", \"obs\"], low_memory=False)\n",
" cache[station] = df\n",
" evict_order.append(station)\n",
" \n",
" if len(cache) > cache_size:\n",
" #print(\"evict!\")\n",
" victim = evict_order.pop(0)\n",
" cache.pop(victim)\n",
" #print(\"CACHE:\", evict_order)\n",
" end = time.time()\n",
" latency_ms.append((end-start)*1000)\n",
" return df\n",
"\n",
"for station in workload:\n",
" get_station(station)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "01d83645-241b-478c-9142-dde57d778b63",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Hits: 40\n",
"Hit Rate: 0.4\n",
"Avg Latency: 16.57418727874756\n",
"Median Latency: 15.306830406188965\n",
"p99 Latency: 93.56653213500977\n"
]
}
],
"source": [
"print()\n",
"print(\"Hits:\", sum(hits))\n",
"print(\"Hit Rate:\", sum(hits) / len(hits))\n",
"print(\"Avg Latency:\", sum(latency_ms) / len(latency_ms))\n",
"print(\"Median Latency:\", np.quantile(latency_ms, 0.5))\n",
"print(\"p99 Latency:\", np.quantile(latency_ms, 0.99))"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "2f4e837c-da54-48f3-bd04-0465064c2df6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"miss miss miss miss hit hit miss hit miss miss miss hit miss miss hit hit hit miss hit miss miss miss miss hit hit hit hit hit miss hit hit hit miss hit hit hit hit miss hit miss miss miss miss hit hit miss miss miss miss miss hit miss miss hit hit hit miss hit miss miss miss hit miss miss hit miss miss miss miss hit miss hit hit miss miss hit miss miss hit miss hit hit miss miss hit miss miss miss hit miss miss miss miss miss hit hit miss hit hit hit "
]
}
],
"source": [
"# Example 2: LRU Policy\n",
"\n",
"cache_size = 3\n",
"cache = {} # key=station name, value=DataFrame with weather data for that station\n",
"evict_order = [] # evict from the left, try to keep whatever is on the right\n",
"\n",
"# stats\n",
"hits = [] # 1 is a hit, 0 is a miss\n",
"latency_ms = [] # latency of get_station in milliseconds\n",
"\n",
"def get_station(station):\n",
" start = time.time()\n",
" if station in cache:\n",
" hits.append(1)\n",
" print(\"hit\", end=\" \")\n",
" df = cache[station]\n",
" evict_order.remove(station)\n",
" evict_order.append(station)\n",
" else:\n",
" hits.append(0)\n",
" print(\"miss\", end=\" \")\n",
" df = pd.read_csv(f\"https://pages.cs.wisc.edu/~harter/cs544/data/wi-stations/{station}.csv.gz\",\n",
" names=[\"station\", \"date\", \"element\", \"value\", \"m\", \"q\", \"s\", \"obs\"], low_memory=False)\n",
" cache[station] = df\n",
" evict_order.append(station)\n",
" \n",
" if len(cache) > cache_size:\n",
" #print(\"evict!\")\n",
" victim = evict_order.pop(0)\n",
" cache.pop(victim)\n",
" #print(\"CACHE:\", evict_order)\n",
" end = time.time()\n",
" latency_ms.append((end-start)*1000)\n",
" return df\n",
"\n",
"for station in workload:\n",
" get_station(station)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "70dfb612-f83b-4d78-899d-afea29ea24de",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Hits: 44\n",
"Hit Rate: 0.44\n",
"Avg Latency: 16.295619010925293\n",
"Median Latency: 15.197038650512695\n",
"p99 Latency: 95.38349866867067\n"
]
}
],
"source": [
"print()\n",
"print(\"Hits:\", sum(hits))\n",
"print(\"Hit Rate:\", sum(hits) / len(hits))\n",
"print(\"Avg Latency:\", sum(latency_ms) / len(latency_ms))\n",
"print(\"Median Latency:\", np.quantile(latency_ms, 0.5))\n",
"print(\"p99 Latency:\", np.quantile(latency_ms, 0.99))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1afdfed8-d89b-4bc1-a0a7-688d751bc9c6",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}