> Hi all
> I just tested dedup on this test box running OpenIndiana (147) storing bacula
> backups, and did some more testing on some datasets with ISO images. The >
> results show so far that removing 30GB deduped datasets are done in a matter
> of minutes, which is not the case with 134 (which may take hours). The tests
> also show that the write speed to the pool is low, very low, if dedup is
> enabled. This is a box with a 3GHz core2duo, 8 gigs of RAM, eight 2TB drives
> and a 80GB x25m for the SLOG (4 gigs) and L2ARC (the rest of it).
> So far I will conclude that dedup should be useful if storage capacity is
> crucial, but not if performance is taken into concideration.
> Mind, this is not a high-end box, but still, I think the numbers show
Hi, it is probably due you have quite low amount of ram. I have similar setup,
10TB dataset that can handle 100MB/s writes easily, system has 24GB of ram.
zfs-discuss mailing list