Shared fleet vs cells
In a shared fleet, every user group runs on the same servers, so one failure reaches all of them. With cells, each group has its own servers, so a failure stays in one cell. When cell A fails for 30 s of a 60 s run, a shared fleet drops all four groups to 50 percent availability. Cells drop only A.
One shared path · cell A is down · 0% of requests work
Four cells · cell A is down · 75% of requests work
Case 1
Four equal user groups send 500 requests/s each. Cell A fails for 30 s. Groups B, C and D must keep 100 percent availability. Group A must keep at least 40 percent.
| Measure | Goal | One shared fleet | Four separate cells |
|---|---|---|---|
| Availability (Group b) | at least 100% | 50% Fail | 100% Pass |
| Availability (Group c) | at least 100% | 50% Fail | 100% Pass |
| Availability (Group d) | at least 100% | 50% Fail | 100% Pass |
| Availability (Group a) | at least 40% | 50% Pass | 50% Pass |
| Monthly cost | 16 USD/mo | 16 USD/mo | |
| p99 latency | 24 ms | 24 ms | |
| Error rate | 50% | 50% | |
| Level rules | none broken | Board is not complete Fail | Pass |