site: lists.dragonflybsd.org
dragonfly - Add initial FUSE support
http://lists.dragonflybsd.org/pipermail/commits/2019-March/718568.html [lists.dragonflybsd.org]
2019-05-03 00:32
tags:
dragonfly
fs
The basic code design comes from FreeBSD, but the code is written from scratch. It was just easier to write from scratch than trying to port sys/fs/fuse/* in FreeBSD for various reasons. Note that this is to implement FUSE API/ABI, but not to be compatible with FreeBSD implementation which contains FreeBSD specific sysctls, etc.
source: Dfly
ufs - Expand time_t support to 48 bits
http://lists.dragonflybsd.org/pipermail/commits/2019-March/718475.html [lists.dragonflybsd.org]
2019-04-24 22:42
tags:
bugfix
dragonfly
format
fs
storage
Fix time overflow issues in the original 32-bit UFS code in two ways. First, treat the original 32-bit seconds fields as unsigned.Second, utilize the spare fields to expand these fields to 48 bits each. Retain the nanosecond-grain accuracy of the nsec fields.
source: Dfly
socket: Limit the number of accepted sockets that kevent reports.
http://lists.dragonflybsd.org/pipermail/commits/2017-October/626501.html [lists.dragonflybsd.org]
2017-10-24 16:32
tags:
dragonfly
networking
perf
programming
Neat little change to control latency.
source: Dfly
Next DFly release will have an initial HAMMER2 implementation
http://lists.dragonflybsd.org/pipermail/users/2017-August/313558.html [lists.dragonflybsd.org]
2017-08-21 23:27
tags:
beta
dragonfly
fs
storage
update
It WILL be considered experimental and won’t be an installer option yet. This initial release will only have single-image support operational plus basic features. It will have live dedup (for cp’s), compression, fast recovery, snapshot, and boot support out of the gate.
source: Dfly
DragonFly NUMA and cache-line locality
http://lists.dragonflybsd.org/pipermail/users/2017-February/313242.html [lists.dragonflybsd.org]
2017-03-03 18:22
tags:
concurrency
cpu
dragonfly
perf
systems
update
The work that has gone into master the last two months has focused on the minutiae of the effect of cache line bounces in various subsystems. These are not contested locks per-say, instead they reflect performance on multi-socket systems when the same global might be hit by cpus on different sockets.
source: Dfly
DragonFly kernel - Improve exec performance
http://lists.dragonflybsd.org/pipermail/commits/2017-February/625534.html [lists.dragonflybsd.org]
2017-03-01 03:10
tags:
concurrency
dragonfly
perf
systems
My guess is that multiple atomic ops degrade the instruction pipeline more than one would otherwise expect due to the multiple memory fences.
source: Dfly