Table of Contents outline true
...
- Through a series of experiments involving different placement strategies, instance types, and total instance counts, we found that the performance remained consistent when using these two configuration:
- six
c7g.largeinstances (three dedicated to theokapiservice and three allocated tomod-courses,mod-sender,mod-tasks-list,mod-gobi,edge-dematic,mod-erm-usage,mod-eusage-reports,mod-notify, andmod-data-importservices) alongside tenr7g.xlargeinstances for all other services, with the CPU parameter set to 2 for all services.
threec7g.largeinstances dedicated to theokapiservice alongside fiver7g.2xlargeinstances for all other services, with the CPU parameter set to 2 for all services.
- six
- Notably, both environment configuration offers a 40% cost reduction compared to the existing setup, making it a more economical option without compromising on performance.
- Configurations with three c7g.large instances for the okapi service and five r7g.2xlarge instances for all other services show the best performance across all experiments. So it will be more tests in this ticket.
- Tests had 100% errors count for AIE_TC: Create Invoices, AIE_TC: Invoices Approve, AIE_TC: Paying Invoices, TC: Receiving-an-Order-Line, Unreceiving-a-Piece and Unreceiving-a-Piece Workflows because data was not regenerated.
Test Runs
| Test # | Description | Status |
|---|---|---|
| Test 1 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 10 Instance Type: r7g.xlarge for others services. | Completed |
| Test 2 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 10 Instance Type: m6g.2xlarge for others modules. | Completed |
| Test 3 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 10 Instance Type: m6g.2xlarge for others services (Repeat Test 2). | Completed |
| Test 4 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. | Completed |
| Test 5 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules (Repeat Test 4). | Completed |
| Test 6 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Test was run without DE_Exporting MARC Bib records custom workflow, DE_Exporting MARC Bib records workflow, and OPIH_/oai/records workflow workflows. | Completed |
| Test 7 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Test was run without DE_Exporting MARC Bib records custom workflow, DE_Exporting MARC Bib records workflow, and OPIH_/oai/records workflow workflows (Repeat Test 6). | Completed |
| Test 8 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. | Completed |
| Test 9 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Test was run without DE_Exporting MARC Bib records custom workflow, DE_Exporting MARC Bib records workflow, and OPIH_/oai/records workflow workflows (Repeat Test 7 after Terminate Instances r7g.xlarge). | Completed |
| Test 10 | CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules (Repeat Test 8 after Terminate Instances r7g.xlarge). | Completed |
| Test 11 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services. | Completed |
| Test 12 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services (Repeat Test 11). | Completed |
| Test 13 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services (Repeat Test 11). | Completed |
| Test 14 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services (Repeat Test 11 after terminate 11 instances). | Completed |
| Test 15 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi and mod-authtoken services and 11 Instance Type: r7g.xlarge for others services. | Completed |
| Test 16 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 5 Instance Type: r7g.2xlarge for others services. | Completed |
| Test 17 | CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 5 Instance Type: r7g.2xlarge for others services (Repeat Test 16). | Completed |
Test Results
This table contains durations for all Workflows.
Start Time "9/2/24, 9:16 AM"
End Time "9/2/24, 9:38 AM"
| Workflows | Test 1 | |
|---|---|---|
End Time "8/21/24, 1:04 PM"
Start Time "8/21/24, 2:35 PM"
End Time "8/21/24, 2:57 PM"
Start Time "8/22/24, 1:01 PM"
End Time "8/22/24, 1:23 PM"
Start Time "8/23/24, 9:05 AM"
End Time "8/23/24, 9:27 AM"
Start Time "8/23/24, 11:38 AM"
End Time "8/23/24, 12:00 PM"
Start Time "8/23/24, 3:27 PM"
End Time "8/23/24, 3:49 PM"
Start Time "8/26/24, 8:48 AM"
End Time "8/26/24, 9:09 AM"
Start Time "8/26/24, 9:18 AM"
End Time "8/26/24, 9:40 AM"
Start Time "8/26/24, 11:39 AM"
End Time "8/26/24, 12:01 PM"
Start Time "8/26/24, 12:37 PM"
End Time "8/26/24, 12:59 PM"
Start Time "8/28/24, 12:57 PM"
End Time "8/28/24, 1:19 PM"
Start Time "8/31/24, 10:16 AM"
End Time "8/31/24, 10:38 AM"
Start Time "8/31/24, 1:30 PM"
End Time "8/31/24, 1:51 PM"
Start Time "8/31/24, 3:21 PM"
End Time "8/31/24, 3:43 PM"
| Test 2 | Test 3 (repeat 2) | Test 4 | Test 5 (repeat 4) | Test 6 | Test 7 (repeat 6 ) | Test 8 | Test 9 (repeat 7 after Terminate) | Test 10 (repeat 8 after Terminate) | Test 11 | Test 12 | Test 13 | Test 14 (Terminate) | Test 15 | Test 16 | Test 17 | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | Average response time (milliseconds) | Errors | |
| AIE_TC: Create Invoices | 10227 | 100% | 7425 | 100% | 7645 | 100.00% | 8563 | 100.00% | 8132 | 100.00% | 7383 | 100.00% | 7575 | 100.00% | 7359 | 100.00% | 10061 | 100.00% | 11269 | 100.00% | 8607 | 100% | 11352 | 100% | 8293 | 100% | 9397 | 100% | 10687 | 100% | 8138 | 100% | 7063 | 100% |
| AIE_TC: Invoices Approve | 4649 | 100% | 3281 | 100% | 3252 | 100.00% | 3442 | 100.00% | 3175 | 100.00% | 3081 | 100.00% | 2966 | 100.00% | 3100 | 100.00% | 5464 | 100.00% | 7132 | 100.00% | 3438 | 100% | 4792 | 100% | 3506 | 100% | 4052 | 100% | 5297 | 100% |
| 3054 | 100% | 2873 | 100% | |||||||||||||||||||||||||||||||
| AIE_TC: Paying Invoices | 5686 | 100% | 3375 | 100% | 3481 | 100.00% | 3439 | 100.00% | 3250 | 100.00% | 3079 | 100.00% | 2948 | 100.00% | 3115 | 100.00% | 4504 | 100.00% | 4245 | 100.00% | 3580 | 100% | 4635 | 100% | 3548 | 100% | 4387 | 100% | 6265 | 100% | 3093 | 100% | 2811 | 100% |
| CICO_TC_Check-In Controller | 3828 | 0% | 2350 | 0% | 2446 | 0.00% | 2325 | 0.00% | 2259 | 0.00% | 2092 | 0.00% | 2046 | 0.00% | 2122 | 0.00% | 3113 | 0.00% | 2965 | 0.00% | 2508 | 0% | 3162 | 0% | 2396 | 0% | 2896 | 0% | 3817 | 0% | 2154 | 0% | 1902 | 0% |
| CICO_TC_Check-Out Controller | 5960 | 0% | 4085 | 0% | 4273 | 0.00% | 4129 | 0.00% | 3905 | 0.00% | 3769 | 0.00% | 3549 | 0.00% | 3816 | 0.00% | 5167 | 0.00% | 5224 | 0.00% | 4307 | 0% | 5954 | 1% | 4406 | 0% | 5100 | 0% | 6788 | 0% | 3721 | 0% | 3436 | 0% |
| CSI_TC:Share local instance | 13045 | 19% | 16081 | 0% | 16091 | 0.00% | 13105 | 18.63% | 13046 | 18.98% | 16087 | 0.00% | 13119 | 18.66% | 16071 | 0.00% | 16076 | 0.00% | 16058 | 0.00% | 4307 | 0% | 13261 | 18% | 16054 | 0% | 13123 | 19% | 16071 | 0% | 13076 | 19% | 16005 | 0% |
| DE_Exporting MARC Bib records custom workflow | 53484 | 0% | 101324 | 0% | 46860 | 0.00% | 97169 | 0.00% | 160022 | 0.00% | 44292 | 0.00% | 72372 | 0.00% | 49515 | 0% | 179136 | 38% | 64827 | 0% | 127373 | 0% | 63206 | 0% | 84900 | 0% | 69446 | 0% | ||||||
| DE_Exporting MARC Bib records workflow | 42737 | 0% | 92213 | 0% | 64897 | 0.00% | 77747 | 0.00% | 265651 | 0.00% | 37622 | 0.00% | 70557 | 0.00% | 45640 | 0% | 187909 | 41% | 63085 | 0% | 159453 | 0% | 84220 | 0% | 72805 | 0% | 69905 | 0% | ||||||
| EVA_TC: View Account | 822 | 0% | 578 | 0% | 582 | 0.00% | 578 | 0.00% | 553 | 0.00% | 523 | 0.00% | 506 | 0.00% | 534 | 0.00% | 3539 | 0.00% | 2709 | 0.00% | 602 | 0% | 1513 | 2% | 527 | 0% | 670 | 0% | 967 | 0% | 503 | 0% | 480 | 0% |
| ILR_TC: Create ILR | 1979 | 0% | 1605 | 0% | 1645 | 0.00% | 1595 | 0.00% | 1523 | 0.00% | 1436 | 0.00% | 1394 | 0.00% | 1528 | 0.00% | 3147 | 0.00% | 3122 | 0.00% | 1576 | 0% | 2124 | 0% | 1708 | 0% | 1928 | 0% | 2643 | 0% | 1496 | 0% | 1298 | 0% |
| MSF_TC: mod search by auth query | 2227 | 26% | 1672 | 0% | 824 | 0.00% | 933 | 2.15% | 686 | 0.00% | 686 | 0.00% | 680 | 0.00% | 692 | 0.00% | 693 | 0.00% | 622 | 0.00% | 770 | 0% | 1224 | 0% | 680 | 0% | 810 | 0% | 1079 | 0% | 666 | 0% | 669 | 0% |
| MSF_TC: mod search by boolean query | 448 | 2% | 406 | 0% | 201 | 0.00% | 257 | 0.41% | 172 | 0.00% | 167 | 0.00% | 167 | 0.00% | 168 | 0.00% | 167 | 0.00% | 156 | 0.00% | 193 | 0% | 254 | 0% | 163 | 0% | 206 | 0% | 285 | 0% | 159 | 0% | 163 | 0% |
| MSF_TC: mod search by contributors | 882 | 0% | 982 | 0% | 495 | 0.00% | 566 | 1.25% | 407 | 0.00% | 415 | 0.00% | 402 | 0.00% | 406 | 0.00% | 394 | 0.00% | 377 | 0.00% | 441 | 0% | 510 | 0% | 399 | 0% | 480 | 0% | 605 | 0% | 393 | 0% | 406 | 0% |
| MSF_TC: mod search by filter query | 649 | 2% | 603 | 0% | 344 | 0.00% | 358 | 0.23% | 285 | 0.00% | 286 | 0.00% | 285 | 0.00% | 291 | 0.00% | 274 | 0.00% | 267 | 0.00% | 315 | 0% | 343 | 0% | 288 | 0% | 331 | 0% | 407 | 0% | 285 | 0% | 285 | 0% |
| MSF_TC: mod search by keyword query | 604 | 0% | 596 | 0% | 345 | 0.00% | 374 | 0.41% | 290 | 0.00% | 288 | 0.00% | 286 | 0.00% | 292 | 0.00% | 274 | 0.00% | 263 | 0.00% | 316 | 0% | 343 | 0% | 283 | 0% | 329 | 0% | 402 | 0% | 284 | 0% | 287 | 0% |
| MSF_TC: mod search by subject query | 930 | 1% | 932 | 0% | 515 | 0.00% | 598 | 0.80% | 420 | 0.00% | 430 | 0.00% | 419 | 0.00% | 425 | 0.00% | 408 | 0.00% | 390 | 0.00% | 456 | 0% | 563 | 0% | 416 | 0% | 485 | 0% | 588 | 0% | 413 | 0% | 417 | 0% |
| MSF_TC: mod search by title query | 2381 | 0% | 1965 | 0% | 1260 | 0.00% | 1362 | 0.49% | 1059 | 0.00% | 1061 | 0.00% | 1054 | 0.00% | 1064 | 0.00% | 1026 | 0.00% | 1012 | 0.00% | 1093 | 0% | 1157 | 0% | 1062 | 0% | 1135 | 0% | 1248 | 0% |
| 1064 | 0% | 1081 | 0% | |||||||||||||||||||||||||||||||
| OPIH_/oai/records | 5086 | 0% | 3248 | 0% | 3254 | 0.00% | 5193 | 0.00% | 3069 | 0.00% | 4113 | 0.00% | 2451 | 0.00% | 6267 | 0% | 4885 | 0% | 882 | 0% | 3026 | 0% | 943 | 0% | 2980 | 0% | 940 | 0% | ||||||
| POO_TC: Add Order Lines | 60193 | 1% | 53341 | 0% | 54507 | 0.00% | 55008 | 0.00% | 54646 | 0.00% | 52806 | 0.00% | 52115 | 0.00% | 54083 | 0.00% | 49475 | 0.00% | 44615 | 0.00% | 56555 | 0% | 65436 | 2% | 59207 | 0% | 59732 | 0% | 62116 | 0% | 55661 | 0% | 53052 | 0% |
| POO_TC: Approve Order | 45294 | 0% | 41750 | 0% | 41935 | 0.00% | 42445 | 0.00% | 42486 | 0.00% | 41569 | 0.00% | 41194 | 0.00% | 42034 | 0.00% | 37310 | 0.00% | 33982 | 0.00% | 44255 | 0% | 46133 | 0% | 46189 | 0% | 45238 | 0% | 47387 | 0% | 42564 | 0% | 41507 | 0% |
| POO_TC Create Order | 34305 | 0% | 30583 | 0% | 30965 | 0.00% | 31853 | 0.00% | 31440 | 0.00% | 30970 | 0.00% | 30392 | 0.00% | 30575 | 0.00% | 28081 | 0.00% | 25451 | 0.00% | 32601 | 0% | 42267 | 1% | 33058 | 0% | 33996 | 0% | 22828 | 0% | 31745 | 0% | 30479 | 0% |
| RTAC_TC: edge-rtac | 4050 | 0% | 2228 | 0% | 2184 | 0.00% | 3665 | 0.00% | 3787 | 0.00% | 1978 | 0.00% | 3888 | 0.00% | 1980 | 0.00% | 9297 | 0.00% | 10041 | 0.00% | 3868 | 0% | 8348 | 0% | 2115 | 0% | 3854 | 0% | 2236 | 0% | 3729 | 0% | 2005 | 0% |
| SDIC_Single Record Import (Create) | 14783 | 19% | 11882 | 0% | 11441 | 0.00% | 13868 | 18.39% | 13345 | 18.82% | 10964 | 0.00% | 12949 | 18.23% | 11001 | 0.00% | 12015 | 0.00% | 11556 | 0.00% | 13848 | 18% | 16236 | 18% | 12538 | 0% | 14482 | 18% | 33721 | 0% | 13357 | 18% | 10702 | 0% |
| SDIU_Single Record Import (Update) | 22347 | 4% | 19685 | 0% | 19298 | 0.00% | 19504 | 0.00% | 3787 | 0.00% | 18869 | 0.00% | 18706 | 0.00% | 18748 | 0.00% | 21745 | 0.00% | 20829 | 0.00% | 19741 | 0% | 23376 | 3% | 20741 | 0% | 20933 | 0% | 22828 | 0% | 19420 | 0% | 18330 | 0% |
| TC: Receiving-an-Order-Line | 50466 | 100% | 44954 | 100% | 46684 | 100.00% | 46396 | 100.00% | 45548 | 100.00% | 45629 | 100.00% | 44356 | 100.00% | 45106 | 100.00% | 40982 | 100.00% | 36920 | 100.00% | 47570 | 100% | 53302 | 100% | 50146 | 100% | 49516 | 100% | 52266 | 100% | 46404 | 100% | 44880 | 100% |
| Serials-Receiving-Workflow | 51572 | 100% | 46047 | 100% | 47460 | 100.00% | 48142 | 100.00% | 47661 | 100.00% | 45645 | 100.00% | 45404 | 100.00% | 46299 | 100.00% | 42105 | 100.00% | 38241 | 100.00% | 49262 | 100% | 61545 | 100% | 50285 | 100% | 50943 | 100% | 52493 | 100% | 48123 | 100% | 45827 | 100% |
| Unreceiving-a-Piece | 9422 | 100% | 8028 | 100% | 8303 | 100.00% | 8247 | 100.00% | 7865 | 100.00% | 7897 | 100.00% | 7748 | 100.00% | 7887 | 100.00% | 7468 | 100.00% | 6812 | 100.00% | 8438 | 100% | 9945 | 100% | 8544 | 100% | 8829 | 100% | 9368 | 100% | 8058 | 100% | 7581 | 100% |
| ULR_TC: Users loan Renewal Transaction | 4027 | 0% | 3198 | 0% | 3275 | 0.00% | 3060 | 0.00% | 2957 | 0.00% | 2814 | 0.00% | 2810 | 0.00% | 2969 | 0.00% | 44632 | 0.00% | 88602 | 0.00% | 3197 | 0% | 5080 | 1% | 3406 | 0% | 3583 | 0% | 4955 | 0% | 2865 | 0% | 2626 | 0% |
Comparison
This graph shows the durations of all workflows compared between the best test result from Test №8, MCPT Basile configuration with 14 instances m6g.2xlarge and result from mcpt tunning report.
Average Case workflows: Part 1.
Average Case workflows: Part 2.
Average Case workflows: Part 3.
Test №1
Introduction: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 10 Instance Type: r7g.xlarge for others services. Fixed Load (average case) MOBIUS test was run.
Objective: The objective of test was to evaluate the performance of the MCPT environment by applying the baseline configuration, while adjusting the CPU allocation for all services to 2 vCPUs. Additionally, the test aimed to assess the impact of using two distinct autoscaling groups with different instance types: c7g.large for the Okapi service and r7g.xlarge for all other services. By running the Fixed Load (average case) MOBIUS test, the goal was to determine if this modified configuration could achieve similar or improved performance compared to the baseline, while potentially optimizing resource allocation and cost.
Results: Almost all workflows shows significant performance degradation.
...
Service CPU Utilization
Here we can see that okapi modules used 42k% CPU power parameter CPU=2 for module.
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99% average with ERW: Exporting Receiving Information.
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99% average with ERW: Exporting Receiving Information
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99% maximum.
...
Service CPU Utilization
Here we can see that okapi used 43k% of the CPU power of parameter CPU=2.
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
...
Service CPU Utilization
Here we can see that okapi used 46k% of the CPU power of parameter CPU=2.
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
...
Service CPU Utilization
Here we can see that okapi used 46k% of the CPU power of parameter CPU=2.
...
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
...
Test №7 - 8
Introduction:
- Test 7: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Fixed Load (average case without DE_Exporting MARC Bib records custom workflow, DE_Exporting MARC Bib records workflow, and OPIH_/oai/records workflow) MOBIUS test was run (Repeat Test 6).
- Test 8: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Fixed Load (average case) MOBIUS test was run.
Objective: The objective of these tests was to validate the consistency of performance observed in Test 5 and Test 6. This was achieved by repeating the same configuration.
Results: WE We see performance improvements for Test 8.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 48k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 6010.
DB load
Top SQL-queries
Test №9 - 10
Introduction:
- Test 9: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Fixed Load (average case without DE_Exporting MARC Bib records custom workflow, DE_Exporting MARC Bib records workflow, and OPIH_/oai/records workflow) MOBIUS test was run (Repeat Test 7 after Terminate Instances r7g.xlarge).Test 10: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance workflow) MOBIUS test was run (Repeat Test 7 after Terminate Instances r7g.xlarge).
- Test 10: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all modules, used two autoscaling groups, 1st with 6 Instance Type: c7g.large, 3 of them for okapi service and other 3 for mod-cources, mod-sender, mod-tasks-list, mod-gobi, edge-dematic, mod-erm-usage, mod-eusage-reports, mod-notify, mod-data-import services and 10 Instance Type: r7g.xlarge for others modules. Fixed Load (average case) MOBIUS test was run (Repeat Test 8 after Terminate Instances r7g.xlarge).
Objective: The objective of these tests was to validate the consistency of performance observed in Test 7 and Test 8. This was achieved by repeating the same configuration and applying new random task locations per instance after terminating the r7g.xlarge instances.
Results: Performance result were worse on 50% for several workflows after terminating the r7g.xlarge instances and applying new random task locations per instance.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 48k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 5150.
DB load
Top SQL-queries
Test №11
Introduction: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others
modulesservices. Fixed Load (average case) MOBIUS test was run
(Repeat Test 8 after Terminate Instances r7g.xlarge).
Objective: The
objectivegoal of
these tests was to validate the consistency of performance observed in Test 7 and Test 8. This was achieved by repeating the same configuration and applying new random task locations per instance after terminating ther7g.xlarge instances.Results: Performance result were worse on 50% for several workflows after terminating the r7g.xlarge instances and applying new random task locations per instancethis test was to replace three c7g.large instances with one additional r7g.xlarge instance for all services, while retaining three c7g.large instances specifically for the okapi service.
Results: The performance was worse compared to when we used the additional three c7g.large instances for services with smaller workloads.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used
48k%45k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was
51505900.
DB load
Top SQL-queries
Test
№11№12 - 13
Introduction: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services. Fixed Load (average case) MOBIUS test was run.
Objective: The goal objective of this test was to replace three c7g.large instances with one additional r7g.xlarge instance for all services, while retaining three c7g.large instances specifically for the okapi service.Results: The performance was worse compared to when we used the additional three c7g.large instances for services with smaller workloadsvalidate the degradation of performance observed in Test 11 by repeating the same configuration.
Results: We confirmed performance degradation with this configuration.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 45k% 43k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 59006200.
DB load
Top SQL-queries
Test
№12 - 13№14
Introduction: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi service and 11 Instance Type: r7g.xlarge for others services. Fixed Load (average case) MOBIUS test was run.
Objective: The objective of this test was to validate the degradation of performance observed in Test 11 by repeating the same configuration.
Results: We confirmed performance degradation with this configuration.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 43k% 45k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 62005900.
DB load
Top SQL-queries
Test
№14№15
Introduction: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi and mod-authtoken service and 11 Instance Type: r7g.xlarge for others services. Fixed Load (average case) MOBIUS test was run.
Objective: The objective of this test was to validate the degradation of performance observed in Test 11 by repeating the same configuration.
Results: We confirmed performance degradation with this configuration.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 45k% 38k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 59005150.
DB load
Top SQL-queries
Test
№15№16 - 17
Introduction: The Test 16: The Baseline MCPT Environment configuration was applied, and CPU=2 was set for all services, used two autoscaling groups, 1st with 3 Instance Type: c7g.large for okapi and mod-authtoken service and 11 Instance 5 Instance Type: r7g.xlarge 2xlarge for others services. Fixed Load (average case) MOBIUS test was run.
Objective:
Results: We confirmed performance degradation with this configuration Test 17: Repeat Test 16 with the same environment configuration.
Objective: The objective of this test was to reduce the number of instances in the main group from 10 to 5, while using higher capacity r7g.2xlarge instances instead of r7g.xlarge
Results: We observed performance improvements in Test 16 compared to Test 8, and by repeating the same configuration in Test 17, we confirmed these performance improvements.
Instance CPU Utilization
Service CPU Utilization
Here we can see that okapi used 38k% 45k% of the CPU power of parameter CPU=2.
Service Memory Utilization
Here we can't see any sign of memory leaks on every module. Memory shows stable trend.
Kafka metrics
DB CPU Utilization
DB CPU was 99%.
DB Connections
Max number of DB connections was 51506100.
DB load
Top SQL-queries
Appendix
Infrastructure
PTF - Baseline MCPT environment configurationenvironment configuration (was changed during testing)
- 14 m6g.2xlarge EC2 instances located in US East (N. Virginia)us-east-1
1 database instance, writer
Name Memory GIB vCPUs db.r6g.4xlarge
128 GiB 16 vCPUs - Open Search ptf-test
- Data nodes
- Instance type - r6g.2xlarge.search
- Number of nodes - 4
- Version: OpenSearch_2_7_R20240502
- Dedicated master nodes
- Instance type - r6g.large.search
- Number of nodes - 3
- Data nodes
- MSK ptf-KRaft-mode
- 2 brokers, kafka.m7g.xlarge brokers in 2 zones
Apache Kafka version 3.7.x
EBS storage volume per broker 300 GiB
- auto.create.topics.enable=true
- log.retention.minutes=480
- default.replication.factor=3
...
Baseline MCPT Environment configuration according to tunning environment from previous report: task count: 4 for services: mod-permissions, mod-search, mod-patron, mod-inventory, mod-inventory-storage, mod-circulation, mod-circulation-storage, mod-order, mod-order-storage, mod-invoice, mod-invoice-storage, for mod-users and mod-authtoken task count 6. Parameter srs.marcIndexers.delete.interval.seconds=86400 for mod-source-record-storage. Instance type: m6g.2xlarge. Instances count: 14. Database r6g.4xlarge, Amazon OpenSearch Service ptf-test: r6g.2хlarge.search (4 nodes).
...