Basic eBPF tests
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v4 Latest posting 2/20 of 4 patches 0 repliesNew
- v4 posting 1/21 of 4 patches 0 repliesSuperseded
Patches in v4 posting 2/2 No applies recorded yet
None of the 4 patches the cover letter announces are in this archive.
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v4 yet.
Cover letter [LTP] [PATCH v4 0/4] Basic eBPF tests
Quoted 100 lines · Jan Stancek
----- Original Message -----
Quoted 70 lines · Jan Stancek
Quoted 47 lines
----- Original Message -----
Quoted 17 lines
I've ended up playing with the patchset and fixed a few loose ends
on
the map test and as I had the code at hand I decided to send v4 instead
of pointing out the mistakes in a review.There were numerous small changes for the map test:
* Make sure the key buffer is sized exactly for the content
* Initialized the array/hash element value in test setup
* Made the code flow a bit more obvious, it was hard to tell which
part was run for n == 0 and which for n == 1Quoted 7 lines
Also it looks that for me the test that loads the eBPF program ends
up
with EPERM randomly at about 10th iteration both as unpriviledged
and
priviledged user, which is really strange.There's one EPERM I can reproduce reliably with
bpf_maptest, which
appears
to originate from "bpf_charge_memlock".There's a deferred component to map freeing, and unchange appears to
be part of it:
bpf_map_releasebpf_map_put INIT_WORK(&map->work, bpf_map_free_deferred); (deferred) bpf_uncharge_memlockWhen I lower max locked memory, it's easy to hit:
# ulimit -l 128; ./bpf_map01 -i 100 ... bpf_map01.c:52: CONF: bpf() requires CAP_SYS_ADMIN on this system: EPERMQuoted 3 lines
Can you try bumping max locked memory to some high value and check
if that helps your case?# for i in 64 128 256 1024; do echo $i; ulimit -l $i; ./bpf_prog01 -i 100 |& grep -P 'passed|CONF'; done64
CONF:bpf()requiresCAP_SYS_ADMINon this system: EPERM
passed 16128
CONF:bpf()requiresCAP_SYS_ADMINon this system: EPERM
passed 16256
CONF:bpf()requiresCAP_SYS_ADMINon this system: EPERM
passed 32Quoted 8 lines
1024
CONF:bpf()requiresCAP_SYS_ADMINon this system: EPERM
passed 192Which produce almost the same results.
Same approach withbpf_map01differs a lot. Sometimes all pass, sometimes none.Seems to make difference for me on 5.2:
# cat bench.sh; sh bench.sh for i in 128 256 512 1024 4096 65536; do echo $i; ulimit -l $i; ./bpf_prog01 -i 100 |& grep -P 'passed|CONF'; sleep 4; done128
bpf_prog01.c:114: CONF:bpf()requiresCAP_SYS_ADMINon this system:
EPERM
passed 32
256
bpf_prog01.c:114: CONF:bpf()requiresCAP_SYS_ADMINon this system:
EPERM
passed 64
512
bpf_prog01.c:114: CONF:bpf()requiresCAP_SYS_ADMINon this system:
Quoted 9 lines
EPERM
passed 128
1024
passed 200
4096
passed 200
65536
passed 200
I ran it again and now my results looks like yours...