Summary
* A new error code (1122/"Bad replica entry returned by lfc_getreplicas(): SFN not set in LFC for this guid"/EXEPANDA_NOLFCSFN) is now used to identify stress related problems with the LFC. It has been observed that the lfc_getreplicas() in some cases return empty replica objects for a given guid (especialy when the LFC is under heavy load). The problem can occur when the distance between the client and server is large, and/or if several guids are sent with the lfc_getreplicas() call - as was recently introduced in the pilot. Jean-Philippe suggested that this can occur in older LFC server versions (problem partially fixed in v 1.7.0, and fully fixed in 1.7.2).
* Added file size info to DQ2 tracing report in all relevant site movers.
* The file size test in the dCacheLFC site mover has been dropped since it's comparing the checksums anyway. Problems have been observer at SARA where the local and remote file sizes failed due to an unexplained mixup of file sizes of different files (the DBRelease file was seemingly compared to another file..). It is not guaranteed that this fix will solve that problem. The problem has only been observerved at SARA to my knowledge.
* An annoying warning message ("Release XXX was not found in tags file") has been corrected when searching for releases in the tags file. Previously, the release number was expected to appear at the end of the string (e.g. VO-atlas-production-13.0.40 but was missed in e.g. VO-atlas-production-14.2.23.2-i686-slc4-gcc34-opt).
Version info
Set the filesize in the tracing report in get_data() (Mover)
Set the filesize in the tracing report in put_data() (lcgcpSiteMover, lcgcp2SiteMover, SiteMover, xrdcpSiteMover, xrootdSiteMover, BNLdCacheSiteMover, dCacheSiteMover, CastorSiteMover, COGSiteMover, dCacheLFCSiteMover, GSIftpSiteMover, HUSiteMover, LocalSiteMover, rfcpLFCSiteMover, SRMSiteMover)
Added new error code 1122, ERR_NOLFCSFN (PilotErrors)
Mover is now catching empty LFC entries (Mover)
Removed harmless monitor warning (PilotTCPServer.py)
Added python,share,EvgenJobOptions to rmRedundants list (pilot)
Created getPreDestination(), getFinalLCGPaths() (SiteMover)
Put functions now using getPreDestination(), getFinalLCGPaths() (lcgcpSiteMover, dq2SiteMover)
Dropped requirement that tags file list should contain release info at the end of the string (RunJobUtilities)
Skipped file size test in get function (dCacheLFCSiteMover)
Corrected the remote and local checksum order in error message (dCacheLFCSiteMover)
No comments:
Post a Comment