[kepler-dev] [Bug 5363] spanTodt performance

bugzilla-daemon at ecoinformatics.org bugzilla-daemon at ecoinformatics.org
Mon Apr 25 12:22:26 PDT 2011


http://bugzilla.ecoinformatics.org/show_bug.cgi?id=5363

--- Comment #1 from Derik Barseghian <barseghian at nceas.ucsb.edu> 2011-04-25 12:22:26 PDT ---
It looks like spanTodt can also use up the gumstix memory to the point of the
oom-killer being repeatedly invoked, including killing span-dcd:
---
Out of memory: kill process 1265 (dcd_mgr) score 206 or a child
Killed process 1265 (dcd_mgr)
java invoked oom-killer: gfp_mask=0x201da, order=0, oom_adj=0
---

Before killing spanTodt:
---
MemTotal:         241596 kB
MemFree:            4788 kB
Buffers:             264 kB
Cached:             5648 kB
SwapCached:            0 kB
Active:           108124 kB
Inactive:         119648 kB
Active(anon):     107016 kB
Inactive(anon):   115024 kB
Active(file):       1108 kB
Inactive(file):     4624 kB
---

After killing spanTodt:
---
MemTotal:         241596 kB
MemFree:          195624 kB
Buffers:             288 kB
Cached:             4876 kB
SwapCached:            0 kB
Active:             5640 kB
Inactive:          31828 kB
Active(anon):       4528 kB
Inactive(anon):    27952 kB
Active(file):       1112 kB
Inactive(file):     3876 kB

-- 
Configure bugmail: http://bugzilla.ecoinformatics.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the QA contact for the bug.


More information about the Kepler-dev mailing list