Progress Logs for Service Challenge 3

This is the results of smoke tests we do on all sites - this consists of sending 1 small file across. Once this succeeds, we open the channel.

Tape Phase

Thursday 21 July 10:30

ASCC
Test Transfer succeeded

BNL
Failed.
2005-07-21 08:31:51,271 [ERROR] - Failed SRM put call. Error is
RequestFileStatus#-2147146727 failed with error:[ Thread queue is full]
FNAL
Failed.
2005-07-21 08:35:30,919 [DEBUG] - Performing Call to method finishRequest
2005-07-21 08:35:30,929 [DEBUG] - TURL is (null)

GRIDKA
Test Transfer succeeded

IN2P3
(tape) Test Transfer succeeded

INFN
(tape) Test Transfer succeeded

NDGF
Test Transfer succeeded

PIC
Test Transfer succeeded

RAL
(tape) Test Transfer succeeded

SARA
(tape) Test Transfer succeeded

TRIUMF
Test Transfer succeeded

Throughput Phase

Tuesday 12 July 9:35

ASCC
Test Transfer succeeded

BNL
Test Transfer Succeeded

FNAL
Not working - error on sending test file
2005-07-12 09:26:09,223 [ERROR] - FINAL:SRM_DEST: Failed on SRM put: NULL TURL returned on put
FINAL:SRM_DEST: Failed on SRM put: NULL TURL returned on put

GRIDKA
Problem on transfer:
FINAL:TRANSPORT:Transfer failed. the server sent an error response: 425 425 Cannot open port: java.lang.Exception: Pool request timed out : f01-015-108_1

IN2P3
Stuck in getRequestStatus on put

INFN
Test Transfer succeeded

NDGF
Test Transfer succeeded

PIC
Test Transfer succeeded

RAL
Test Transfer succeeded

SARA
Test Transfer succeeded

TRIUMF
Test Transfer succeeded

Tuesday 12 July 10:45

ASCC
Disk full - in progress cleaning

BNL
Test Transfer Succeeded - But all bulk file transfers fail - shut down channel again

FNAL
Not working - error on sending test file
2005-07-12 09:26:09,223 [ERROR] - FINAL:SRM_DEST: Failed on SRM put: NULL TURL returned on put
FINAL:SRM_DEST: Failed on SRM put: NULL TURL returned on put
GRIDKA
Not working - error on sending test file
2005-07-12 09:09:09,697 [DEBUG] - Performing Call to method srm__put
2005-07-12 09:09:10,819 [ERROR] - Failed to put File srm://f01-015-103-e.gridka.de:8443/srm/managerv1?SFN=/pnfs/gridka.de/sc3/dteam/2005-07-12/file-899-4ea3a71f-6e08-4664-87c7-007a71bfddfd.dat
2005-07-12 09:09:10,819 [ERROR] - Failed to put File. Error in srm__put: SOAP-ENV:Server - java.io.IOException: java.lang.NoSuchFieldException: map

IN2P3
Not working - error on sending test file
2005-07-12 09:11:36,152 [DEBUG] - Performing Call to method srm__put
2005-07-12 09:11:36,222 [ERROR] - Failed to put File srm://ccdcache.in2p3.fr:8443/srm/managerv1?SFN=/pnfs/in2p3.fr/data/dteam/hpss/2005-07-12/file-201-67d25609-f12e-40e5-b98c-06aa8bd83e9c.dat
2005-07-12 09:11:36,223 [ERROR] - Failed to put File. Error in srm__put: SOAP-ENV:Client - CGSI-gSOAP: Could not open connection !

INFN
Test Transfer succeeded

NDGF
Test Transfer succeeded

PIC
Test Transfer succeeded

RAL
Test Transfer succeeded

SARA
Test Transfer succeeded

TRIUMF
Test Transfer succeeded

Tuning Phase

Sat 09 July 19:30 CET - FTS results

ASCC
gridftp working - ~30MB/s

BNL
Works. seem approx 30MB/s

FNAL
get back NULL TURL

GRIDKA
Problem with 2/3 of pool nodes not having the PNFS namespace, so 60% of transfers fail

IN2P3
Down - never coming out of preparetoput cycle

INFN
Down - connection refused

NDGF
Working - some problems with the SRM, and one pool node, but transfers going through

PIC
Works ok - hard to get good numbers due to phedex load, but good individual file rates (~10MB/s) seen

RAL
Works well - see ~ 100MB/s

SARA
Seems broken again on the gridftp write - SRM negotiation works fine

TRIUMF
Works - Seen up to 50 MB/s

Tue 05 July 17:00 CET - FTS results

ASCC
Still a problem with the SRM

BNL
Works. seem approx 50MB/s

FNAL
get back NULL TURL

GRIDKA
Was working, but now very slow -transfers timing out after 1 hour. Can't make subdirec tories via SRM

IN2P3
Works seen approx 80MB/s - low rate of errors

INFN
SRM Down - No Air-con working

NDGF
No contact details yet

PIC
Works. Seen approx 40MB/s

RAL
Tested with one file - requested to wait until network tuning is over

SARA
Works. Seen max 200MB/s but now dCache seems broken

TRIUMF
Work. Seen apoprox 20 MB/s

Sunday 03 July

ASCC
Does not return TURL
2005-07-03 17:29:14,162 [INFO ] - STATUS:BEGIN:SRM_PUT
2005-07-03 17:29:14,162 [DEBUG] - Now calling requestTurlFromSurl ; srm://lcg00115.grid.sinica.edu.tw:8443/srm/managerv1?SFN=/castor/grid.sinica.edu.tw/sc/file-000-f5253f1e-6d1d-480a-baee-5ce6c39bb56b.dat
2005-07-03 17:29:14,162 [DEBUG] - Performing Call to method requestTurlFromSurl
2005-07-03 17:29:14,162 [DEBUG] - Performing Call to method srm__put
2005-07-03 17:29:15,836 [INFO ] - SRM put request ID: 372034003
2005-07-03 17:29:15,836 [DEBUG] - Call completed to srm__put
2005-07-03 17:29:15,836 [DEBUG] - Call completed to prepareRequest
2005-07-03 17:29:15,836 [DEBUG] - got file status state Pending
2005-07-03 17:29:15,836 [DEBUG] - Call completed to requestTurlFromSurl
2005-07-03 17:29:15,836 [DEBUG] - Performing Call to method updateTurlFromSurlRequest
2005-07-03 17:29:15,836 [DEBUG] - Performing Call to method srm__getRequestStatus
2005-07-03 17:29:17,502 [DEBUG] - Call completed to srm__getRequestStatus
2005-07-03 17:29:17,502 [DEBUG] - Returned state is Pending
2005-07-03 17:29:17,502 [DEBUG] - Call completed to updateTurlFromSurlRequest - not finished yet

BNL
Works. Lots of timeouts on transfer (due to slow/long link ?)

FNAL
get back NULL TURL

GRIDKA
Works, but lots of error - security config on some pool nodes wrong ?

IN2P3
Works well - ~80MB/s - low rate of errors ~2%

INFN
SRM Down

NDGF
No contact details yet

PIC
SRM Down
2005-07-03 17:30:28,455 [INFO ] - STATUS:BEGIN:SRM_PUT
2005-07-03 17:30:28,455 [DEBUG] - Now calling requestTurlFromSurl ; srm://castor
srmsc.pic.es:8443/srm/managerv1?SFN=/castor/pic.es/sc3/scratch/file-000-f5253f1e
-6d1d-480a-baee-5ce6c39bb56b.dat
2005-07-03 17:30:28,455 [DEBUG] - Performing Call to method requestTurlFromSurl
2005-07-03 17:30:28,455 [DEBUG] - Performing Call to method srm__put
2005-07-03 17:30:28,809 [ERROR] - Failed to put File srm://castorsrmsc.pic.es:84
43/srm/managerv1?SFN=/castor/pic.es/sc3/scratch/file-000-f5253f1e-6d1d-480a-baee
-5ce6c39bb56b.dat
2005-07-03 17:30:28,809 [ERROR] - Failed to put File. Error in srm__put: SOAP-EN
V:Server - CGSI-gSOAP
2005-07-03 17:30:28,809 [INFO ] - STATUS:END fail:SRM_PUT

RAL
No Contact details yet

SARA
Works on small files. Timeouts on large files

TRIUMF
Works on small files. Timeouts on large files.

-- JamesCasey - 17 Jun 2005


This topic: LCG > WebHome > LCGServiceChallenges > ProgressLogs > ServiceChallengeThreeProgress
Topic revision: r8 - 2005-07-21 - unknown
 
This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2019 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback