Michael Galloway schrieb: > out of curiosity, i'm wondering what other folks are getting for backup rates > to LTO4. i seem to be getting these sorts of rates: > > local disk backups (3ware raid6 9650SE sata disks/xfs filesystem): > Elapsed time: 8 hours 22 mins > Priority: 10 > FD Files Written: 432,602 > SD Files Written: 432,602 > FD Bytes Written: 1,038,925,243,806 (1.038 TB) > SD Bytes Written: 1,038,995,304,809 (1.038 TB) > Rate: 34492.9 KB/s > > linux client, (3ware sata raid 5, ext3): > Elapsed time: 1 day 37 mins 15 secs > Priority: 10 > FD Files Written: 1,214,678 > SD Files Written: 1,214,678 > FD Bytes Written: 2,159,368,051,425 (2.159 TB) > SD Bytes Written: 2,159,551,222,342 (2.159 TB) > Rate: 24362.5 KB/s > > netapp client via nfs mount to bacula server: > Elapsed time: 18 hours 1 min 56 secs > Priority: 10 > FD Files Written: 863,458 > SD Files Written: 863,458 > FD Bytes Written: 1,825,660,355,131 (1.825 TB) > SD Bytes Written: 1,825,879,267,061 (1.825 TB) > Rate: 28123.4 KB/s > > clients are all on local lan via gigE connections.
For full backups I get 70-75MB/s write speed to LTO-4 tape. Spooling seems to make not much difference here. The overall backup speed (whole job) drops with spooling enabled, because it's asynchron for single jobs (spooling -> despooling -> spooling...). Therefor I don't use spooling for large jobs that run >20 hours. Are the above values with spooling or is this the 'Transfer rate' to tape? Ralf ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2005. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ _______________________________________________ Bacula-users mailing list Bacula-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/bacula-users
