This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: S390x - REL5 stap_testing_200611132049.results]
David Wilder wrote:
David Smith wrote:
Hmm. It appears from that output that the 'stap' binary you are using
doesn't have caching support. If it did, the name of the C file
wouldn't be 'stap_9388.c', it would be something like
'stap_6bc3d92354bbb164201d174128e2eca5_122.c'.
Can you check and ensure that the latest systemtap has been compiled
and installed? Let's see the output of "stap -V".
Woops, I thought I had run make install, I guess not. Here is the
output running the current version of stap.
[root@hez235 obj]# ./stap -v -p4 -e "probe begin {}"
Pass 1: parsed user script and 52 library script(s) in
5740usr/130sys/6472real ms.
Pass 2: analyzed script: 1 probe(s), 0 function(s), 0 embed(s), 0
global(s) in 80usr/0sys/102real ms.
Pass 3: translated to C into
"/tmp/stapMeHOHh/stap_f087f4375cd915e8f124ba8ee388fbb9_177.c" in
10usr/10sys/2real ms.
Pass 4: compiled C into "stap_f087f4375cd915e8f124ba8ee388fbb9_177.ko"
in 7580usr/1360sys/10365real ms.
[root@hez235 obj]# ./stap -v -p4 -e "probe begin {}"
Pass 1: parsed user script and 52 library script(s) in
5720usr/130sys/6756real ms.
Pass 2: analyzed script: 1 probe(s), 0 function(s), 0 embed(s), 0
global(s) in 90usr/10sys/97real ms.
Pass 3: using cached
/root/.systemtap/cache/f0/stap_f087f4375cd915e8f124ba8ee388fbb9_177.c
Pass 4: using cached
/root/.systemtap/cache/f0/stap_f087f4375cd915e8f124ba8ee388fbb9_177.ko
Great. Now it looks like basic caching functionality is working for you.
Looks better, But I still needed to comment out the extra defines for
_stp_free_percpu() in alloc.c.
You might want to try a "make install" with an unmodified alloc.c just
to see if the real problem was with mismatches between old/new stap,
tapsets, and runtime.
--
David Smith
dsmith@redhat.com
Red Hat
http://www.redhat.com
256.217.0141 (direct)
256.837.0057 (fax)