"Michael" == Michael Bergman michael.bergman@ericsson.com writes:
Michael> Recap and result(as promised) about the deswizzler scanner Michael> I wrote:
The da** thing walks inodes, and in all snapshots dirs as well *sigh*. It can also easily swamp the disks because it reads data fairly inefficiently. [...]
I'll try and find out if a reallocate -A has an effect on what the deswizzler needs to do, and share my findings here later (after summer).
Michael> 1. There is no connection between reallocate -A and what the deswizzler is Michael> doing. I'd recommend turning off deswizzler before doing reallocate -A, Michael> just to save some IOPS. The disks are hammered very hard by reallocate -A, Michael> and W latency will shoot up. A lot.
Michael> 2. The deswizzler scanner will do, in the bg, what a certain WAFL message Michael> also does. But it does it on-demand when data is read. Meaning that the 1st Michael> time a block is read, it will be "fixed" if there's an extra pointer there.
Michael> In a HFC (high file count) environment it's pointless to have deswizzler on. Michael> It won't do anything that is fruitful for the performance, rather on the Michael> contrary. Michael> Expecially with the bigger FAS models (80x0) my recommendation is to always set
Michael> options wafl.deswizzle.enable off
Interesting. Would this also impact the older 7-mode 32xx series boxes with large volumes with lots nad lots of files as well?