I happened to see a couple of similar issues discussed in this forum, and hence thought if someone could help. Please spare me , if it's not the right place for the discussion.
I'm working with a linux5.4.213 - OpenWRT based (QCA driver) Mesh AP. Currently the device is running into Out of memory and looking at the slab info, we see skb_head_cache and skb_data_cache accounting a major increase.
But i don't have any clue on how to go about debugging the same. I came across similar issues discussed years ago, but there were no conclusion or methods to debug/triage the issue further.
We gave a shot with kmemtracer, but that seems to pretty much point to false positives and the module itself was contributing to leak and we were asked to turn the configs off.
If someone could point me on what the next set of debugging steps could be, would really help.
Hi All,
I happened to see a couple of similar issues discussed in this forum, and hence thought if someone could help. Please spare me , if it's not the right place for the discussion.
I'm working with a linux5.4.213 - OpenWRT based (QCA driver) Mesh AP. Currently the device is running into Out of memory and looking at the slab info, we see skb_head_cache and skb_data_cache accounting a major increase.
But i don't have any clue on how to go about debugging the same. I came across similar issues discussed years ago, but there were no conclusion or methods to debug/triage the issue further.
We gave a shot with kmemtracer, but that seems to pretty much point to false positives and the module itself was contributing to leak and we were asked to turn the configs off.
If someone could point me on what the next set of debugging steps could be, would really help.
Thanks in advance!