91–100 of 161 posts
Earlier quoted context omitted.
On top of the block layer cache there's also the namei cache for filename to inode lookups, I'm not sure if that covers a file not found case or just a success path, but it may apply here too.
Still backed by block layer cache for (hopefully) quick response regardless of outcome
Earlier quoted context omitted.
Just quickly remove some drives and set the write protect slider on them, problem solved, no data loss
A few years ago I finally bought a USB drive to read an old 3.5" floppy from the late '90s on which I had archived my e-mail messages before moving away to college. I completely forgot about write protection (as well as atime write-backs). I managed to read a surprising amount of data off of the disk, but I think less than if I had remembered to write-protect the disk before inserting it into the drive. The files wer…
sync;sync;halt was once a legit way to shut down ;)
Earlier quoted context omitted.
A few years ago I finally bought a USB drive to read an old 3.5" floppy from the late '90s on which I had archived my e-mail messages before moving away to college. I completely forgot about write protection (as well as atime write-backs). I managed to read a surprising amount of data off of the disk, but I think less than if I had remembered to write-protect the disk before inserting it into the drive. The files wer…
So rare to see ppl writing about sync. sync;sync;halt was once a legit way to shut down ;)
I'd expect the vast majority of IO requests to be served from the kernel's IO cache (we're talking 30 * 1.44MBs here so just under 50MB, trivial for even an old computer to hold in RAM), thus I wouldn't be surprised for it to be very fast and reliable as long as he sticks to read-only workloads - those would never actually touch the floppies beyond the initial read.
Would it be more fun to run a live cd webserver only? piece together an old computer, with an old live linux installation, and either run it unupdated or patched and carrying updates it can only apply w/o reboot?
- Put a bird^H^H ZFS on it
- Switch to RAID10 (a stripe of mirrors), and go 2/3 floppys wide so you can have some redundancy in each mirror gropu
- Get some Pis (or other SBCs) and hook those up and run Ceph... if this keeps going we'll have a SAN soon enough.
- ZIP disks?[0]
Also, I don't think I ever want to hear of the "hug of death" for any site ever again -- I don't think this site hosted on 30 floppies was hugged to death.