up_the_irons changed the topic of #arpnetworks to: VPS Services: https://arpnetworks.com/vps | KB: https://arpnetworks.com/help | Twitter/IG/etc: @arpnetworks | @up_the_irons, @mercutio are staff, other ops are long-time customers | Channel Log: https://irclogger.arpnetworks.com/arpnetworks/
lukori_ has joined #arpnetworks
lukori has quit [Read error: Connection reset by peer]
lukori_ has quit [Read error: Connection reset by peer]
lukori has joined #arpnetworks
lukori has quit [Remote host closed the connection]
lukori has joined #arpnetworks
Otshelnik has quit [Remote host closed the connection]
Otshelnik has joined #arpnetworks
<up_the_irons> todd: there's nothing about ceph that's low budget, believe me lol
<up_the_irons> ceph is redundant by its very nature. I'd rather put mirrors on a single 12TB 3.5" SATA dangling somewhere heh
<up_the_irons> grok is not technically wrong in your chat, but nobody would run ceph with a replication factor of 1; i've never even heard of that
<up_the_irons> replication factor of 3: you can lose 1 copy of everything, and it'll be rebuilt. if you lose 2 copies, then all writes block (until 2 copies are regenerated from the 1 lone survivor).
<up_the_irons> replication factor of 2: you can't lose anything without writes blocking immediately
<up_the_irons> replication factor of 1: I don't even think that's a thing lol
<up_the_irons> erasure encoded pools act differently, and there's tradeoffs with resiliency and performance. The details escape me, I looked at it a long time ago.