This is the mail archive of the systemtap@sourceware.org mailing list for the systemtap project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[Bug runtime/22265] on rawhide, we're getting a kernel panic


https://sourceware.org/bugzilla/show_bug.cgi?id=22265

--- Comment #3 from David Smith <dsmith at redhat dot com> ---
(In reply to David Smith from comment #2)
> I wonder if the bpf changes
> have upped our memory requirements.

Here's the pre-bpf code on this rawhide system:

====
# ./stap -vwp2 -e 'probe kernel.function("*") {} probe
module("*").function("*") {} probe kernel.function("*").call {} probe
module("*").function("*").call {} probe kernel.function("*").return {} probe
module("*").function("*").return {} probe kernel.function("*").inline {} probe
module("*").function("*").inline {}' > /dev/null
Pass 1: parsed user script and 467 library scripts using
143236virt/47356res/8128shr/39336data kb, in 120usr/30sys/147real ms.
Pass 2: analyzed script: 2100235 probes, 0 functions, 0 embeds, 0 globals using
4998228virt/3816824res/1660shr/4894328data kb, in 73530usr/9430sys/122315real
ms.
====

Here's the current HEAD code on the same system:

====
# /usr/local/bin/stap -vwp2 -e 'probe kernel.function("*") {} probe
module("*").function("*") {} probe kernel.function("*").call {} probe
module("*").function("*").call {} probe kernel.function("*").return {} probe
module("*").function("*").return {} probe kernel.function("*").inline {} probe
module("*").function("*").inline {}' > /dev/null
Pass 1: parsed user script and 469 library scripts using
143748virt/47616res/7852shr/39692data kb, in 130usr/30sys/470real ms.
Pass 2: analyzed script: 2100235 probes, 0 functions, 0 embeds, 0 globals using
5031620virt/3829572res/1592shr/4927564data kb, in 70740usr/9160sys/109159real
ms.
====

So, in pass 2 we've gone from:

virt: 4998228 -> 5031620
res:  3816824 -> 3829572
shr:  1660    -> 1592
data: 4894328 -> 4927564

So, the memory use has been upped a bit, but nothing dramatic.

-- 
You are receiving this mail because:
You are the assignee for the bug.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]