Zygo Blaxell ff3b5a7a1b hash: drop bees_unreadahead ...

Forcing the entire hash table into immediate writeback causes crippling
write latencies at shutdown.  Even discarding pages as they are read in
at startup can trigger a writeback latency spike if the pages are dirty
at read time.

Better to let the VM subsystem handle this on its own.

Signed-off-by: Zygo Blaxell <bees@furryterror.org>

2021-11-29 21:27:48 -05:00

..

.gitignore

bees: move usage message out of source file and fix a few inaccuracies

2020-12-17 17:54:51 -05:00

bees-context.cc

context: stop using deprecated memset_zero template

2021-11-29 21:27:48 -05:00

bees-hash.cc

hash: drop bees_unreadahead

2021-11-29 21:27:48 -05:00

bees-resolve.cc

bees: misc comment updates

2021-06-11 20:56:54 -04:00

bees-roots.cc

roots: use the new type argument to next_min

2021-10-31 19:59:09 -04:00

bees-thread.cc

context: get rid of all instances of pthread_cancel

2021-04-28 21:42:03 -04:00

bees-trace.cc

trace: current_exception() is not a replacement for uncaught_exception()

2021-06-11 20:56:54 -04:00

bees-types.cc

bees: use helper function for readahead

2021-06-11 20:56:54 -04:00

bees-usage.txt

bees: move usage message out of source file and fix a few inaccuracies

2020-12-17 17:54:51 -05:00

bees.cc

hash: move the random generator out of bees-hash.cc

2021-11-29 21:27:48 -05:00

bees.h

bees: clean up #include list

2021-11-29 21:27:48 -05:00

fiemap.cc

fs: fix FIEMAP_MAX_OFFSET type silliness in fiemap.h

2021-10-06 15:17:02 -04:00

fiewalk.cc

bees: remove local cruft, throw at github

2016-11-17 12:12:13 -05:00

Makefile

trace: move BeesTrace and BeesNote into their own translation unit

2021-06-11 20:56:54 -04:00