Can someone explain this result?

ahamilto ahamilto at tjhsst.edu
Sun May 8 02:24:58 EDT 2011


 I have noticed similar behavior, also with a RAIDZ1 non-rootfs pool 
 with dedup and compression both enabled.  If I run a large rsync 
 operation to or from the pool, the transfer will get slower and slower 
 over time until eventually (after a few hours or so) it will almost 
 grind to a halt.  If I stop the rsync and let the server idle for a 
 while, when i continue, performance is back up.  I have noticed that 
 while the rsync is running, server load and memory usage will steadily 
 climb until the server is using all of the memory (6GB) and the load 
 average hovers around 13.

 If anyone needs any more information on this setup, please let me know.

 --ahamilto

 On Sat, 7 May 2011 22:46:40 -0700 (PDT), devsk <devsku at gmail.com> 
 wrote:
> # time find rsynced/|wc -l
> 384736
>
> real    0m50.615s
> user    0m0.350s
> sys     0m19.404s
>
> # time find rsynced/|wc -l
> 384736
>
> real    2m5.708s
> user    0m0.315s
> sys     0m5.185s
>
> # time find rsynced/|wc -l
> 384736
>
> real    1m53.062s
> user    0m0.350s
> sys     0m4.418s
>
> The FS is idle at this time and so is the pool. This is not rootfs.
> Its a RAIDZ1 pool with dedup and compression on. There is an SSD
> configured as a cache device.
>
> How is it possible that when I run the first time, I get the fastest
> time while subsequent runs are slower by more than half. I am 
> baffled.
> And this is not the first time ZFS on Linux has done this: this has
> been seen multiple times now because it did this when I was running
> ZFS rootfs on my laptop.
>
> -devsk



More information about the zfs-discuss mailing list