RE: RTEMS NFS/RPIOC problems?

["Hill, Jeff" <johill@lanl.gov>]

Ricardo,

 

Our RTEMS 4.11 systems are producing some messages like this. I wouldn’t be surprised if the log system was writing files periodically.

 

07tdaq.lcs.net:1024 Tue Jul  3 19:15:21 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 19:25:21 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 19:35:21 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 19:45:21 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 19:55:21 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 17:45:20 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

07tdaq.lcs.net:1024 Tue Jul  3 17:55:20 2018 save_restore.c(1785): [0x16]=write_it:Invalid argument

 

As memory serves the RTEMS 4.10 message is more like your messages below but I was having troubles finding an example in our log server.

 

“RPCIO: server '172.17.2.10' not responding - still trying”

 

Jeff

 

From: Ricardo Cardenes [mailto:rcardenes@gemini.edu]
Sent: Tuesday, July 03, 2018 4:43 PM
To: Hill, Jeff
Cc: Talk EPICS Tech
Subject: Re: RTEMS NFS/RPIOC problems?

 

Hi Jeff,

 

How frequent are those timeout messages? As you can see from my logs, in our case is quite systematic:

 

[...]

2018-07-01-tcs.log:Jul  1 04:40:34  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 41000 retries to server 172.17.2.10 

2018-07-01-tcs.log:Jul  1 17:28:44  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 42000 retries to server 172.17.2.10 

2018-07-01-tcs.log:Jul  1 22:21:06  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 43000 retries to server 172.17.2.10 

2018-07-02-tcs.log:Jul  2 02:28:07  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 44000 retries to server 172.17.2.10 

2018-07-02-tcs.log:Jul  2 11:11:52  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 45000 retries to server 172.17.2.10 

[...]

 

Cheers,

Ricardo

 

On Tue, Jul 3, 2018 at 12:29 PM Hill, Jeff <johill@lanl.gov> wrote:

Hi Recardo,

 

We also observe some intermittent NFS/RPC timeout console messages on nios2/rtems4.11/EPICS systems deployed at LANL.  We also observe intermittent issues with updating the EPICS save/restore files on these systems. No issues with CA disconnects on these systems based on R3.14 and our DAQ R3.15. I also monitor ping intervals on these systems and don’t see issues with latency there.

 

Jeff

 

From: tech-talk-bounces@aps.anl.gov [mailto:tech-talk-bounces@aps.anl.gov] On Behalf Of Ricardo Cardenes
Sent: Monday, July 02, 2018 5:10 PM
To: Talk EPICS Tech
Subject: RTEMS NFS/RPIOC problems?

 

 

Hi,

 

We've been experiencing some problems on some of our systems (based on MVME 2700/3100; EPICS 3.14.12.7, RTEMS 4.10.2) related to the RPC subsystem, like these:

 

2018-06-04-tcs.log:Jun  4 12:30:06 E) PORT: tcs_vme, MSG: RPCIO: server '172.17.71.11' not responding - still trying
[...]

\2018-06-07-tcs.log:Jun  7 13:11:37 E) PORT: tcs_vme, MSG: RPCIO: server '172.17.2.10' not responding - still trying
[...]

2018-06-26-tcs.log:Jun 26 16:43:14  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 17000 retries to server 172.17.2.10
2018-06-26-tcs.log:Jun 26 20:57:43  E) PORT: tcs_vme, MSG: RPCIO - statistics: already 18000 retries to server 172.17.2.10

 

And it seems to me that we're getting too many CA disconnects, too. We hadn't noticed until recently, when we commissioned a system that seems the only one being systematically affected (but it is the one that orchestrates most of the others, too...)

 

We suspect some hardware or networking problem, possibly outside of our boards, given that the interface stats look quite clear (no corrupt Ethernet frames, no retries, ...), and we've actually seen at least one corrupt UDP header, plus several thousand occurrences of timed out IP fragments (over a period of a few weeks).

 

In any case, while we investigate the possible hardware issue, has anyone else experienced a similar problem?

 

Regards,

Ricardo