The large number of files are from the SYS volume which we don't restore on a daily basis. We'll try to test just the VOL1 and VOL2 backup though.
We commented out the resourceutilization parameter in the dsm.opt file setting it to the default 1 transmitting session and 1 querying session and it seemed to improve the backup times. We were getting (.80 GB/min or 13.31 MB/min) on the backups which are at least a little closer to the (.93 GB/min or 15.59 MB/min) we were getting on our restores. We did notice that with resource utilization commented out it was REALLY slow on the SYS volume. Fortunately since 95% of the data is on VOL1 and VOL2, it sped up dramatically on those volumes the times were ok. Also CPU utilization was consistent at 66% when it hit VOL1 and VOL2. We assume that the smaller files in the SYS volume were slowing things down dramatically on the backup with resourceutilization commented out, but we were confused by the fact that we had to do this. We also ran a backup with resourceutilization 5 which resulted in 10.6 MB/s not much of an improvement. Are there any other ideas to consider at this point? Thanks. -Vin -----Original Message----- From: ADSM: Dist Stor Manager [mailto:ADSM-L@;VM.MARIST.EDU]On Behalf Of Rushforth, Tim Sent: Friday, November 01, 2002 10:45 AM To: [EMAIL PROTECTED] Subject: Re: HELP! Faster Restore than Backups over Gigabit? The number of objects backed up (11,854) does not match the # of objects restored (2687+1122) so you are not comparing the same thing. Does the backup include NDS? To do an accurate comparison, only backup VOL1 and VOL2. -----Original Message----- From: Vin Yam [mailto:vyam@;QBCT.COM] Sent: October 31, 2002 3:23 PM To: [EMAIL PROTECTED] Subject: Re: HELP! Faster Restore than Backups over Gigabit? We used the bytes transfered and elapsed time to calculate the throughput. Here are the actual stats though: Backup: 10/25/2002 16:03:12 Total number of objects inspected: 11,858 10/25/2002 16:03:12 Total number of objects backed up: 11,854 10/25/2002 16:03:12 Total number of objects updated: 0 10/25/2002 16:03:12 Total number of objects rebound: 0 10/25/2002 16:03:12 Total number of objects deleted: 0 10/25/2002 16:03:12 Total number of objects expired: 0 10/25/2002 16:03:12 Total number of objects failed: 0 10/25/2002 16:03:12 Total number of bytes transferred: 42.39 GB 10/25/2002 16:03:12 Data transfer time: 6,624.70 sec 10/25/2002 16:03:12 Network data transfer rate: 6,710.10 KB/sec 10/25/2002 16:03:12 Aggregate data transfer rate: 9,776.55 KB/sec 10/25/2002 16:03:12 Objects compressed by: 0% 10/25/2002 16:03:12 Elapsed processing time: 01:15:46 Restore: VOL1 10/25/2002 16:36:42 Total number of objects restored: 2,687 10/25/2002 16:36:42 Total number of objects failed: 0 10/25/2002 16:36:42 Total number of bytes transferred: 31.82 GB 10/25/2002 16:36:42 Data transfer time: 1,314.00 sec 10/25/2002 16:36:42 Network data transfer rate: 25,394.00 KB/sec 10/25/2002 16:36:42 Aggregate data transfer rate: 15,411.48 KB/sec 10/25/2002 16:36:42 Elapsed processing time: 00:36:05 VOL2 10/25/2002 16:51:50 Total number of objects restored: 1,122 10/25/2002 16:51:50 Total number of objects failed: 0 10/25/2002 16:51:50 Total number of bytes transferred: 9.92 GB 10/25/2002 16:51:50 Data transfer time: 416.11 sec 10/25/2002 16:51:50 Network data transfer rate: 25,021.00 KB/sec 10/25/2002 16:51:50 Aggregate data transfer rate: 15,532.12 KB/sec 10/25/2002 16:51:50 Elapsed processing time: 00:11:10 10/25/2002 16:51:50 --- SCHEDULEREC STATUS END 10/25/2002 16:51:50 --- SCHEDULEREC OBJECT END CDB02_VOL2_TEMP 10/25/2002 16:40:49 10/25/2002 16:51:50 --- SCHEDULEREC STATUS BEGIN 10/25/2002 16:51:50 --- SCHEDULEREC STATUS END 10/25/2002 16:51:50 Thanks for any help. -Vin -----Original Message----- From: ADSM: Dist Stor Manager [mailto:ADSM-L@;VM.MARIST.EDU]On Behalf Of Nicholas Cassimatis Sent: Thursday, October 31, 2002 12:13 PM To: [EMAIL PROTECTED] Subject: Re: HELP! Faster Restore than Backups over Gigabit? Is the performance comparison from the stats ITSM gives at the end of the session? If so, are you giving us the network or the aggregate transfer? I'd expect the network transfer rate to be about the same, but the aggregate to be faster on the restore (unless it's a fairly small restore). Nick Cassimatis [EMAIL PROTECTED] Today is the tomorrow of yesterday.
