Re: [ptp-dev] Problem with running parallel debugging

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [List Home]

Re: [ptp-dev] Problem with running parallel debugging

From: Greg Watson <g.watson@xxxxxxxxxxxx>
Date: Thu, 10 Sep 2015 09:21:45 -0400
Delivered-to: ptp-dev@xxxxxxxxxxx
List-archive: <https://dev.eclipse.org/mailman/private/ptp-dev>
List-help: <mailto:ptp-dev-request@eclipse.org?subject=help>
List-subscribe: <https://dev.eclipse.org/mailman/listinfo/ptp-dev>, <mailto:ptp-dev-request@eclipse.org?subject=subscribe>
List-unsubscribe: <https://dev.eclipse.org/mailman/options/ptp-dev>, <mailto:ptp-dev-request@eclipse.org?subject=unsubscribe>

The “SDM: [4]” process is the master sdm and it looks like it’s trying to connect to tasks 0, 1, and 3. Task 0 is binding to port 53916 on linux-am7s, but for some reason the getaddrinfo function is failing when trying to resolve this address and port number. Since it looks like you’re running everything on the same machine, it’s hard to know why this is failing. Also the last message is “getaddrinfo: Success” so I’m not sure what that means.

Are you still having the problem?

Greg

On Aug 21, 2015, at 2:57 PM, Rinat Khaziev <rrkhaziev@xxxxxxxxx> wrote:

So the error from the gai_strerror(err) is "Name or service not known". Do u have any idea why it is happening?

Here is the full outup from console
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [0] size 5
SDM: [0] route for 2 is {}
SDM: [0] in sdm_create_sockd_map
SDM: [0] sdm_route_get_route dest {0-3}, parent 4
SDM: [0] adjacent nodes: {2}
SDM: [0] adding 2 to my map
SDM: [0] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [0] nodeID: 0, hostname: linux-am7s, port: 53916
SDM: [0] found entry for node 0
SDM: [0] found my entry
SDM: [0] [ACCEPT] sockfd: 4
SDM: [0] port bound: 53916
SDM: [0] bound to port 53916
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [1] size 5
SDM: [1] in sdm_create_sockd_map
SDM: [1] sdm_route_get_route dest {0-3}, parent 4
SDM: [1] adjacent nodes: {}
SDM: [1] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [1] nodeID: 0, hostname: linux-am7s, port: 53916
SDM: [1] found entry for node 0
SDM: [1] nodeID: 1, hostname: linux-am7s, port: 50494
SDM: [1] found entry for node 1
SDM: [1] found my entry
SDM: [1] [ACCEPT] sockfd: 4
SDM: [1] port bound: 50494
SDM: [1] bound to port 50494
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [2] size 5
SDM: [2] in sdm_create_sockd_map
SDM: [2] sdm_route_get_route dest {1-3}, parent 0
SDM: [2] adjacent nodes: {}
SDM: [2] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [2] nodeID: 0, hostname: linux-am7s, port: 53916
SDM: [2] found entry for node 0
SDM: [2] nodeID: 1, hostname: linux-am7s, port: 50494
SDM: [2] found entry for node 1
SDM: [2] nodeID: 2, hostname: linux-am7s, port: 54620
SDM: [2] found entry for node 2
SDM: [2] found my entry
SDM: [2] [ACCEPT] sockfd: 4
SDM: [2] port bound: 54620
SDM: [2] bound to port 54620
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [3] size 5
SDM: [3] in sdm_create_sockd_map
SDM: [3] sdm_route_get_route dest {0-3}, parent 4
SDM: [3] adjacent nodes: {}
SDM: [3] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [3] nodeID: 0, hostname: linux-am7s, port: 53916
SDM: [3] found entry for node 0
SDM: [3] nodeID: 1, hostname: linux-am7s, port: 50494
SDM: [3] found entry for node 1
SDM: [3] nodeID: 2, hostname: linux-am7s, port: 54620
SDM: [3] found entry for node 2
SDM: [3] nodeID: 3, hostname: linux-am7s, port: 56769
SDM: [3] found entry for node 3
SDM: [3] found my entry
SDM: [3] [ACCEPT] sockfd: 4
SDM: [3] port bound: 56769
SDM: [3] bound to port 56769
SDM: [master] effsize: 5, size: 4, rv: 0
SDM: [master] Found routing file, size=4
SDM: [4] size 5
SDM: [4] route for 0 is {2}
SDM: [4] route for 1 is {}
SDM: [4] route for 3 is {}
SDM: [4] in sdm_create_sockd_map
SDM: [4] sdm_route_get_route dest {0-4}, parent 4
SDM: [4] adjacent nodes: {0-1,3}
SDM: [4] adding 0 to my map
SDM: [4] adding 1 to my map
SDM: [4] adding 3 to my map
SDM: [master] effsize: 5, size: 4, rv: 0
SDM: [4] nodeID: 0, hostname: linux-am7s, port: 53916
SDM: [4] getaddrinfo error. hostname: linux-am7s, port: 53916
SDM: [4] failed to connect to child linux-am7s:53916
SDM: [4] sdm_message_init failed
SDM: sdm_init failed
getaddrinfo: Success

Thanks,
Rinat

On Fri, Aug 21, 2015 at 10:53 AM, Greg Watson <g.watson@xxxxxxxxxxxx> wrote:
I would try modifying the debug message at line 292 of sdm_message_tcpip.c to print gai_strerror(err) where err is the return value of getaddrinfo. That way at least you’ll find out why getaddrinfo failed.

Greg

On Aug 21, 2015, at 11:28 AM, Rinat Khaziev <rrkhaziev@xxxxxxxxx> wrote:

Hello,

I am trying to start use PTP with sdm on my local machine, I have tried to use manually compiled and precompiled versions of sdm.

Platform OpenSUSE 12.2(local workstation)
PTP version: 9.0.0
OpenMPI version:1.5.4
debugger session: Generic OpenMPI Interactive.
session adress: localhost

The following sdm output is written to console

#PTP job_id=21859

SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [0] size 5
SDM: [0] route for 2 is {}
SDM: [0] in sdm_create_sockd_map
SDM: [0] sdm_route_get_route dest {0-3}, parent 4
SDM: [0] adjacent nodes: {2}
SDM: [0] adding 2 to my map
SDM: [0] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [0] nodeID: 0, hostname: linux-am7s, port: 56555
SDM: [0] found entry for node 0
SDM: [0] found my entry
SDM: [0] [ACCEPT] sockfd: 4
SDM: [0] port bound: 56555
SDM: [0] bound to port 56555
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [1] size 5
SDM: [1] in sdm_create_sockd_map
SDM: [1] sdm_route_get_route dest {0-3}, parent 4
SDM: [1] adjacent nodes: {}
SDM: [1] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [1] nodeID: 0, hostname: linux-am7s, port: 56555
SDM: [1] found entry for node 0
SDM: [1] nodeID: 1, hostname: linux-am7s, port: 58731
SDM: [1] found entry for node 1
SDM: [1] found my entry
SDM: [1] [ACCEPT] sockfd: 4
SDM: [1] port bound: 58731
SDM: [1] bound to port 58731
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [2] size 5
SDM: [2] in sdm_create_sockd_map
SDM: [2] sdm_route_get_route dest {1-3}, parent 0
SDM: [2] adjacent nodes: {}
SDM: [2] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [2] nodeID: 0, hostname: linux-am7s, port: 56555
SDM: [2] found entry for node 0
SDM: [2] nodeID: 1, hostname: linux-am7s, port: 58731
SDM: [2] found entry for node 1
SDM: [2] nodeID: 2, hostname: linux-am7s, port: 50389
SDM: [2] found entry for node 2
SDM: [2] found my entry
SDM: [2] [ACCEPT] sockfd: 4
SDM: [2] port bound: 50389
SDM: [2] bound to port 50389
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [server] Found routing file, size=4
SDM: [3] size 5
SDM: [3] in sdm_create_sockd_map
SDM: [3] sdm_route_get_route dest {0-3}, parent 4
SDM: [3] adjacent nodes: {}
SDM: [3] This node is a server!
SDM: [server] effsize: 5, size: 4, rv: 0
SDM: [3] nodeID: 0, hostname: linux-am7s, port: 56555
SDM: [3] found entry for node 0
SDM: [3] nodeID: 1, hostname: linux-am7s, port: 58731
SDM: [3] found entry for node 1
SDM: [3] nodeID: 2, hostname: linux-am7s, port: 50389
SDM: [3] found entry for node 2
SDM: [3] nodeID: 3, hostname: linux-am7s, port: 51354
SDM: [3] found entry for node 3
SDM: [3] found my entry
SDM: [3] [ACCEPT] sockfd: 4
SDM: [3] port bound: 51354
SDM: [3] bound to port 51354
SDM: [master] effsgetaddrinfo: Success
ize: 5, size: 4, rv: 0
SDM: [master] Found routing file, size=4
SDM: [4] size 5
SDM: [4] route for 0 is {2}
SDM: [4] route for 1 is {}
SDM: [4] route for 3 is {}
SDM: [4] in sdm_create_sockd_map
SDM: [4] sdm_route_get_route dest {0-4}, parent 4
SDM: [4] adjacent nodes: {0-1,3}
SDM: [4] adding 0 to my map
SDM: [4] adding 1 to my map
SDM: [4] adding 3 to my map
SDM: [master] effsize: 5, size: 4, rv: 0
SDM: [4] nodeID: 0, hostname: linux-am7s, port: 56555
SDM: [4] getaddrinfo error. hostname: linux-am7s, port: 56555
SDM: [4] failed to connect to child linux-am7s:56555
SDM: [4] sdm_message_init failed
SDM: sdm_init failed

I would be appreciated if you can help me to set up sdm
Thanks,
Rinat
_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
To change your delivery options, retrieve your password, or unsubscribe from this list, visit
https://dev.eclipse.org/mailman/listinfo/ptp-dev

_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
To change your delivery options, retrieve your password, or unsubscribe from this list, visit
https://dev.eclipse.org/mailman/listinfo/ptp-dev

_______________________________________________
ptp-dev mailing list
ptp-dev@xxxxxxxxxxx
To change your delivery options, retrieve your password, or unsubscribe from this list, visit
https://dev.eclipse.org/mailman/listinfo/ptp-dev

References:
- [ptp-dev] Problem with running parallel debugging
  - From: Rinat Khaziev
- Re: [ptp-dev] Problem with running parallel debugging
  - From: Greg Watson
- Re: [ptp-dev] Problem with running parallel debugging
  - From: Rinat Khaziev

Prev by Date: [ptp-dev] Fwd: [epp-dev] Mars.1 RC3 packages
Next by Date: [ptp-dev] [Hudson] Build failed in Hudson: ptp-nightly-packages #237
Previous by thread: Re: [ptp-dev] Problem with running parallel debugging
Next by thread: [ptp-dev] [Hudson] Build failed in Hudson: ptp-release-packages #40
Index(es):
- Date
- Thread

Breadcrumbs