Staff Directory | Intranet | Search

Data Transfer Example Database

cat_in not array

Selected Category Information

GridFTP Transfers

Transfers that use a GridFTP server installation at one or both endpoints.



Example Listing

MSS (AR) -> Co (guc)

Attempt to transfer an archived file via globus-url-copy

  • globus-url-copy returns an error if the file is archived.
  • Archive retrieval is initiated by the (failed) request for the file.
  • A workaround for this would be to loop until no error is returned, or use uberftp with 'quote wait'.
  • The "-rp" or relative path option allows the paths to be specified relative to $HOME on either system. %2F in the path forces root directory.
> globus-url-copy -nodcau -tcp-bs 65536 -rp gsiftp://mss.ncsa.teragrid.org/1GB -2 gsiftp://gridftp-co.ncsa.teragrid.org/%2F/scratch/users/jdoe/
error: globus_ftp_client: the server responded with  an error
550 1GB-2: is being retrieved  from the archive...

 


MSS (AR) -> Hg

Retrival of an archived file from MSS using uberftp with the "quote wait" command.

  • Note the use of the "quote wait" command. This instructs the client to wait for the file(s) to be staged from the tape archive and then carry out the transfer.
> uberftp mss.ncsa.teragrid.org "lopen gridftp-hg.ncsa.teragrid.org; lcd /gpfs _scratch1/dadams; active; mode stream; quote wait; get 1GB-2"
UNIX Archive FTP server (DiskXtender Version 2 .9) active. Checking DiskXtender.conf

220  ;UNIX Archive FTP server ready.
230 User&nbs p;dadams logged in.
220 tg-s037.ncsa.teragrid.org  ;GridFTP Server 2.1 (gcc64dbg, 1122653280-63) ready .
230 User dadams logged in.
250 CWD& nbsp;command successful.
Active mode
Stream mod e
258 WAIT on
Transfer of 1073741824  bytes completed in 128.07 seconds. 8384.30 KB/ sec

 


guc large file

Third party transfer of a large file from NCSA to SDSC.

  • The stripe option is used here to utilize all of the servers at each end.
  • Large files benefit the most from striping.
  • A 10 MB tcp window size is used (tcp-bs) to keep the pipe full between SDSC and NCSA (~60ms RTT).
> globus-url-copy -vb -tcp-bs 10000000 -stripe gsiftp://gridftp-hg.ncsa.teragr id.org/gpfs_scratch1/nopurge/dadams/data/10GB/10GB-1 gsiftp://tg-gridftp.sds c.teragrid.org/gpfs/dadams/
Source: gsiftp://gridftp-hg.ncsa.teragrid.org/gpfs_scratch1/nopurge/dad ams/data/10GB/
Dest:   gsiftp://tg-gridftp.sdsc.teragr id.org/gpfs/dadams/
  10GB-1
  10737418240  bytes       567.29 MB/sec  ;avg       634.24 MB/sec inst

 


tgcp large file

Transfer of a large file from NCSA to SDSC using the TeraGrid copy (tgcp) tool.

  • Passing the -big option to tgcp tells it to employ striping.
  • The URL sytax is more relaxed here. Basically, you get the third party benifits without all the typing.
  • Notice that the full globus-url-copy comand is printed. This is a good way to develop globus-url-copy commands.
> tgcp -vb -big ./10GB-1 tg-gridftp.sdsc.teragrid.org:/gpfs/dadams/
/usr/local/globus-4.0.1-r3//bin/globus-url-copy -vb  -stripe& nbsp;-p 4 -tcp-bs 4000000 gsiftp://gridftp-hg.ncsa.terag rid.org/gpfs_scratch1/nopurge/dadams/data/10GB/10GB-1 gsiftp://tg-gridf tp.sdsc.teragrid.org/gpfs/dadams/

Source: gsiftp://gridf tp-hg.ncsa.teragrid.org/gpfs_scratch1/nopurge/dadams/data/10GB/
Dest:    gsiftp://tg-gridftp.sdsc.teragrid.org/gpfs/dadams/
  10GB-1
  10737418240 bytes  &nbs p;    582.65 MB/sec avg     ;   918.36 MB/sec inst

 


tgcp RFT

Transfer a single file using the RFT transfee management system.

  • RFT functionality is implemented with the -rft option.
  • tgcp automatically generates an input file for the rft command then executed the rft command.
  • Using the -v option, the file name of the temporary input file for rft is displayed, and it's contents can be inspected.
> tgcp -v -rft 1GB tg-gridftp.sdsc.teragrid.org:/gpfs/dadams/
/usr/local/globus-4.0.1-r3/bin/rft -h rft-hg.ncsa.teragrid.org&nbs p;-r 8443 -l 60 -z host -f /tmp/filelTzYM v

Number of transfers in this reques t: 1
Subscribed for overall status
Termina tion time to set: 60 minutes

 O verall status of transfer:
Finished/Active/Failed/Retr ying/Pending
0/1/0/0/0

 Overall status  of transfer:
Finished/Active/Failed/Retrying/Pending
1/0/ 0/0/0
All Transfers are completed

 


Client -> Server

Pushing data from client process to waiting GridFTP server.

  • The "-vb" option is included to show performance data.
> globus-url-copy -vb file:///gpfs_scratch1/nopurge/dadams/1GB gsiftp://gridft p-co.ncsa.teragrid.org/scratch/users/dadams/1GB
Source: file:///gpfs_scratch1/nopurge/dadams/
Dest:  & nbsp;gsiftp://gridftp-co.ncsa.teragrid.org/scratch/users/dadams/
&nbs p; 1GB
   1045430272 bytes         28.58 MB/sec avg   &n bsp;    30.00 MB/sec inst

 


guc: Client -> Server

Pushing data from client process to waiting GridFTP server

  • The parallel streams parameter is adjusted here to claim more "fair shares" of the network.
> globus-url-copy -vb -p 8 file:///gpfs_scratch1/nopurge/dadams/1GB gsiftp://g ridftp-co.ncsa.teragrid.org/scratch/users/dadams/1GB
Source: file:///gpfs_scratch1/nopurge/dadams/
Dest:  & nbsp;gsiftp://gridftp-co.ncsa.teragrid.org/scratch/users/dadams/
&nbs p; 1GB
   1073741824 bytes         72.62 MB/sec avg   &n bsp;    70.49 MB/sec inst

 


guc: whole directory

Copy an entire directory hierarchy to another location.

  • The "fast" option tells the GridFTP servers to always use Mode E to complete transfers. This, among other things enables the reuse of the control channel connection reducing the overhead of each individual file transfer.
  • Adding the "-r>" and "-cd" options ensures that directories are recursively copied and created when needed.
  • The trailing slashes on the source and destination URLs indicate a directory is being copied rather than a file.
> globus-url-copy -vb -tcp-bs 8388608 -fast -r -cd gsiftp://gridftp-hg.ncsa.te ragrid.org/gpfs_scratch1/nopurge/dadams/data/dfiles/ gsiftp://tg-gridftp.sds c.teragrid.org/gpfs/dadams/dfiles/
Source: gsiftp://gridftp-hg.ncsa.teragrid.org/gpfs_scratch1/nopurge/dad ams/data/dfiles/
Dest:   gsiftp://tg-gridftp.sdsc.tera grid.org/gpfs/dadams/dfiles/
  d1/

 &nb sp;d2/

  d3/

Source: gsiftp://g ridftp-hg.ncsa.teragrid.org/gpfs_scratch1/nopurge/dadams/data/dfiles/d1/
Dest:   gsiftp://tg-gridftp.sdsc.teragrid.org/gpfs/dadams /dfiles/d1/
  m_000001
      ;10485760 bytes        16.67&nb sp;MB/sec avg        16.67  ;MB/sec inst
Source: gsiftp://gridftp-hg.ncsa.teragrid.org/ gpfs_scratch1/nopurge/dadams/data/dfiles/d2/
Dest:   g siftp://tg-gridftp.sdsc.teragrid.org/gpfs/dadams/dfiles/d2/
 &nb sp;m_000001

Source: gsiftp://gridftp-hg.ncsa.teragrid.or g/gpfs_scratch1/nopurge/dadams/data/dfiles/d3/
Dest:    ;gsiftp://tg-gridftp.sdsc.teragrid.org/gpfs/dadams/dfiles/d3/
 & nbsp;m_000001