This is my first time using K6 and I’m loving it so far.
I need to run a load test with 36000 VUs. I keep running out of memory on an amazon EC2 instance during initialization. I’m generating memory reports using /usr/bin/time.
What could be the cause of this gigantic memory difference?
User scripts generated using postman-to-k6.
Mac OS side
Apple M1 Pro Sequoia 15.3.1 16gb
k6 v0.57.0 (go1.24.0, darwin/arm64)
It gets killed at 6061 VUs due to out of memory, as expected. /usr/bin/time -l k6 run script.js reports 3071 MB under maximum resident set size.
Full time log;
3221028864 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
14416940 page reclaims
1478 page faults
0 swaps
0 block input operations
0 block output operations
47 messages sent
61 messages received
69648 signals received
887282 voluntary context switches
4450816 involuntary context switches
2771119850002 instructions retired
1076649572957 cycles elapsed
71403542912 peak memory footprint
EC2 Instance
R6G.2XLarge 64GB running Amazon Linux 2023 LTS
k6 v0.57.0 (commit/50afd82c18, go1.23.6, linux/arm64)
(manually killed or the EC2 will hang) at 1077 VUs. /usr/bin/time -v k6 run script.js reports 10.57GB under Maximum resident set size.
Full time log;
User time (seconds): 73.19
System time (seconds): 4.97
Percent of CPU this job got: 733%
Elapsed (wall clock) time (h:mm:ss or m:ss): 0:10.65
Average shared text size (kbytes): 0
Average unshared data size (kbytes): 0
Average stack size (kbytes): 0
Average total size (kbytes): 0
Maximum resident set size (kbytes): 11088080
Average resident set size (kbytes): 0
Major (requiring I/O) page faults: 0
Minor (reclaiming a frame) page faults: 3001623
Voluntary context switches: 15405
Involuntary context switches: 1817
Swaps: 0
File system inputs: 0
File system outputs: 0
Socket messages sent: 0
Socket messages received: 0
Signals delivered: 0
Page size (bytes): 4096
Exit status: 105
1 post - 1 participant