closing, won't be fixing this, its 4 years old now.
** Changed in: linux (Ubuntu)
Status: In Progress => Invalid
** Tags removed: hwcert-server
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/15
I've removed you. I'm not positive this is a kernel bug so much as an
issue with this specific issue. I'm hoping HP can test this same model
and CPU and let us know if the issue is reproducible on a similar
system.
** Changed in: linux (Ubuntu)
Assignee: Colin Ian King (colin-king) => (unas
Hi there, this bug is assigned to me but I suspect it's a machine
specific issue that I can't resolve. Will this bug be escalated? Can I
be removed as the assignee?
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad
Softlock could be related if the timer is not functioning sanely.
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564949
Title:
Severe latency/skew on AMD Opetron processor
To manage notifications a
Per Narinder:
Also on DL385p Gen8 is reported the kernel hang and storage controller in soft
lock up mode with 14.4.4 and 16.04 images. And i believe it is hpsa driver
error which is soft locking. I told HP team to look into it as HP owns the hpsa
driver.
So there's more than just the CPU time
Firmware updated to "A28 03/07/2016". This does not help; the system is
still showing clock skew.
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564949
Title:
Severe latency/skew on AMD Opetron proc
Update the firmware first, and if we still have an issue then we need to
dig into what's up with this.
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564949
Title:
Severe latency/skew on AMD Opetron
The current firmware on this box is A28 02/06/2014 (not sure exactly
what that corresponds to just yet, the HP website is less than
forthcoming on firmware updates so far).
You'd mentioned getting one of our firmware devs to take a look would
you prefer I hold off on updating this system until the
OK, so the local APIC timer is not working as I expected. Perhaps it's
not wired up to produce the timer interrupt as we expect.
I've disabled the Local APIC timer and lo and behold it works fine:
./clocktest
Testing for clock jitter on 8 cpus
PASSED: largest jitter seen was 0.001365
Testing cl
Just to clarify, the kernel parameter I used to work around the
underlying issue is: nolapic_timer
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564949
Title:
Severe latency/skew on AMD Opetron pro
Looks like when CPUs going into a deep C state idle the latency jitter
is low, but when we go into a deep idle on a HLT or WAIT we're taking a
while to get active again.
With non-idle CPUs:
./clocktest
Testing for clock jitter on 8 cpus
PASSED: largest jitter seen was 0.000184
Testing clock dir
Experiment #3, idle=halt
./clocktest
Testing for clock jitter on 8 cpus
PASSED: largest jitter seen was 0.000103
Testing clock direction for 5 minutes...
FAILED: Iteration 0 delta: 2.905905
FAILED: Iteration 1 delta: 1.162889
FAILED: Iteration 2 delta: 1.204066
FAILED: Iteration 3 delta: 1.15738
Experiment #2, idle=nomwait
./clocktest
Testing for clock jitter on 8 cpus
PASSED: largest jitter seen was 0.000539
Testing clock direction for 5 minutes...
FAILED: Iteration 0 delta: 0.644422
FAILED: Iteration 1 delta: 0.193849
FAILED: Iteration 2 delta: 0.278920
FAILED: Iteration 3 delta: 0.23
Experiment #1, with idle=poll kernel parameter:
$ ./clocktest
Testing for clock jitter on 8 cpus
PASSED: largest jitter seen was 0.000479
Testing clock direction for 5 minutes...
PASSED: Iteration 0 delta: 0.000101
PASSED: Iteration 1 delta: 0.000124
PASSED: Iteration 2 delta: 0.61
PASSED: I
** Changed in: linux (Ubuntu)
Status: Confirmed => In Progress
** Changed in: linux (Ubuntu)
Importance: Undecided => High
** Changed in: linux (Ubuntu)
Assignee: (unassigned) => Colin Ian King (colin-king)
--
You received this bug notification because you are a member of Ubuntu
** Tags added: hwcert-server
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564949
Title:
Severe latency/skew on AMD Opetron processor
To manage notifications about this bug go to:
https://bugs.lau
apport information
** Tags added: apport-collected uec-images xenial
** Description changed:
Discovered this while doing pre-release certification testing for 16.04
on an HP ProLiant DL385p Gen8 with an AMD Opteron 6320 8-core CPU.
I have some code that essentially does this: And note,
Also note, both the Intel and AMD boxes were tested with the same kernel
and the TSC clocksource in use. I tried HPET on the AMD box as well but
it didn't make any difference.
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bu
$ cat /etc/lsb-release
DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=16.04
DISTRIB_CODENAME=xenial
DISTRIB_DESCRIPTION="Ubuntu Xenial Xerus (development branch)"
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1564
19 matches
Mail list logo
