On Thu, Aug 19, 2010 at 4:24 PM, Jean-Francois Malouin <[email protected]> wrote: > amreport will always show that it was written at dismally slow speed > yet the taper debug logs show very fast (80 to 100MBs) writes. > *Always* *and* *only* for the first flushed DLE. Me thinks that the > initial timestamp for the start of write to tape is taken while no > bytes has made to tape yet, and that it includes part of the time it > takes for the estimates to finish and time to chunk new DLEs to > holddisk, or something like this.
This is not possible - the durations are not based on timestamps. > This is not a ranti btw! > I'm just surprised that no one who have upgraded to 3.1.x have noticed > this! Don't people read their amreports :) If you can boil it down to some numbers that don't add up, then I can take a look, but I don't have anything concrete to look at yet. Dustin -- Open Source Storage Engineer http://www.zmanda.com
