@cmuratori @nothings @won3d Note: high level metadata is always changing on ZFS because of copy-on-write plus pointers to lower-level data.
-
-
Replying to @cmuratori
@thatcks@nothings@won3d Specifically, because you're always rewriting the uberblocks to the same addresses, you have a "superpage" problem1 reply 0 retweets 0 likes -
Replying to @cmuratori
@thatcks@nothings@won3d Ie., 8K may be the write size for an SSD, but the _clear_ size is actually like half a meg or something.1 reply 0 retweets 0 likes -
Replying to @cmuratori
@thatcks@nothings@won3d So, I think this only maps well to an SSD if the firmware happens to do a full 8K page mapping.1 reply 0 retweets 0 likes -
Replying to @cmuratori
@thatcks@nothings@won3d If they actually do mapping only at the half meg level, then you will thrash the fuck out of the drive, won't you?1 reply 0 retweets 0 likes -
Replying to @cmuratori
@thatcks@nothings@won3d You'll be doing half-meg writes _times four_ to rewrite the uberblock arrays every time. Makes me very nervous.1 reply 0 retweets 0 likes -
Replying to @cmuratori
@thatcks@nothings@won3d But maybe all SSDs do 8K-block level mapping, so it doesn't matter? I don't know. I need more firmware docs :P1 reply 0 retweets 0 likes -
Replying to @cmuratori
@cmuratori@nothings@won3d All I know is that lots of people seem to run ZFS pools on SSDs (us included) and they haven't exploded yet.1 reply 0 retweets 0 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.