exception while executing any application linked with hwloc

[maciekab]

Attempt to run any application linked with hwloc terminates prematurely with the following error message:

hpx::init: std::exception caught: failed to initialize core affinity mask for thread 4: HPX(kernel_error)

Disabling hwloc during configuration fixes the problem.
(boost 1.52.0, gcc 4.6.3, hwloc 1.6.1)

[hkaiser]

Could you provide the full trace info it prints? I'd like to see the filename and line number where this exception gets raised.

[maciekab]

On 01/31/2013 12:58 PM, Hartmut Kaiser wrote:

Could you provide the full trace info it prints? I'd like to see the
filename and line number where this exception gets raised.

—
Reply to this email directly or view it on GitHub
#691 (comment).

What was reported is precisely what gets printed out. There's no stack
trace and no value being computed.

I can rerun with additional options/env. variables if that helps, just
let me know which.

[sithhell]

I am not sure why this is happening. Can you please provide additional information:

• The git commit you are on
• The topology of the system the problems occur (attach the output of lstopo)
• An example invocation of an application that leads to that error

Thanks!

[sithhell]

I am not able to reproduce the problem for any machine i have access on with the latest git commit (fce1042).

[sithhell]

This is really strange. Two other people independently reported the same problem. The problem is known to persist in the 0.9.5 release. However i thought i fixed it with the latest commits as i can't reproduce any of this anymore.

[maciekab]

Thomas,

Here's the requested info.

Commit hash: 7f09dc0

---

Topology:
Machine (24GB)
NUMANode L#0 (P#0 10223MB) + Socket L#0 + L3 L#0 (12MB)
L2 L#0 (256KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0
PU L#0 (P#0)
PU L#1 (P#8)
L2 L#1 (256KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1
PU L#2 (P#1)
PU L#3 (P#9)
L2 L#2 (256KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2
PU L#4 (P#2)
PU L#5 (P#10)
L2 L#3 (256KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3
PU L#6 (P#3)
PU L#7 (P#11)
NUMANode L#1 (P#1 14GB) + Socket L#1 + L3 L#1 (12MB)
L2 L#4 (256KB) + L1d L#4 (32KB) + L1i L#4 (32KB) + Core L#4
PU L#8 (P#4)
PU L#9 (P#12)
L2 L#5 (256KB) + L1d L#5 (32KB) + L1i L#5 (32KB) + Core L#5
PU L#10 (P#5)
PU L#11 (P#13)
L2 L#6 (256KB) + L1d L#6 (32KB) + L1i L#6 (32KB) + Core L#6
PU L#12 (P#6)
PU L#13 (P#14)
L2 L#7 (256KB) + L1d L#7 (32KB) + L1i L#7 (32KB) + Core L#7
PU L#14 (P#7)
PU L#15 (P#15)
HostBridge L#0
PCIBridge
PCI 1002:679a
PCIBridge
PCI 14e4:1684
Net L#0 "eth0"
PCIBridge
PCI 14e4:1684
Net L#1 "eth1"
PCI 8086:2822
Block L#2 "sda"
Block L#3 "sdb"
Block L#4 "sdc"
Block L#5 "sdd"
Block L#6 "sr0"
HostBridge L#4
PCIBridge
PCI 1000:0058

---

Example invocation:

./packages/hpx/bin/fibonacci
hpx::init: std::exception caught: failed to initialize core affinity
mask for thread 4: HPX(kernel_error)

HTH,

Maciek

[sithhell]

Thanks. This commit should not lead to that error. One of the other errors was resolved by just having a clean and fresh clone of the repo. Do you have an local modifactions? Like merges or something?
Another cause of the error could be that you use SLURM to start the job. I isolated the problem there (at least i hope so) and have a fix in mind. Please be patient.

[sithhell]

I committed a series of patches which should have fixed the issue. Please retry.

[maciekab]

It works for me now.