/memcached, High-performance distributed memory object caching system
1.4.22, Package name:
memcached-1.4.22, Maintainer: pkgsrc-users
memcached is a high-performance, distributed memory object caching
system, generic in nature, but intended for use in speeding up dynamic
web applications by alleviating database load.
Master sites: SHA1:
Version history: (Expand)
- (2015-01-05) Updated to version: memcached-1.4.22
- (2014-10-23) Updated to version: memcached-1.4.21
- (2014-07-16) Updated to version: memcached-1.4.20nb2
- (2014-05-30) Updated to version: memcached-1.4.20nb1
- (2014-05-18) Updated to version: memcached-1.4.20
- (2014-05-04) Updated to version: memcached-1.4.19
CVS history: (Expand)
| 2015-01-05 00:41:05 by Thomas Klausner | Files touched by this commit (2) | |
Update to 1.4.22:
Bugfix maintenance release. Fixes to hash table expansion now
completely hang all threads very briefly while the hash table
pointers are swapped. Once swapped, it unlocks and uses locks as
In previous versions, the hash table was switched to a global lock
instead of a map of bucket-locks during expansion. This should be
faster overall with a small latency penalty. It's possible to
presize the hash table with -o hashpower
| 2014-10-23 13:24:31 by Thomas Klausner | Files touched by this commit (2) | |
Update to 1.4.21:
Avoid OOM errors when locked items stuck in tail
If clients occasionally fetch many items, more than can fit the
TCP buffers, then hang for a very long period of time, that slab
class could OOM. In older versions this could cause a crash. Since
1.4.20 this will cause OOM errors.
Now, if a locked item lands in the LRU tail, it will be bumped back
to the head and an lrutail_reflocked counter incremented. If you're
concerned about having stuck clients, watch that counter.
Big thanks to Jay Grizzard et all at Box for helping track this
| 2014-07-15 19:30:26 by Filip Hajny | Files touched by this commit (3) |
Fix my previous commit, use user/group vars properly.
| 2014-07-15 18:52:34 by Thomas Klausner | Files touched by this commit (1) |
Set PKG_HOME, which is used but not set.
XXX: please check if this is what was intended here.
| 2014-07-15 16:28:26 by Filip Hajny | Files touched by this commit (1) | |
Fix invalid PKG_USERS usage. Clean up unneeded bits. Bump PKGREVISION.
| 2014-05-30 01:38:20 by Thomas Klausner | Files touched by this commit (3049) |
Bump for perl-5.20.0.
Do it for all packages that
* mention perl, or
* have a directory name starting with p5-*, or
* depend on a package starting with p5-
like last time, for 5.18, where this didn't lead to complaints.
Let me know if you have any this time.
| 2014-05-18 10:15:17 by Thomas Klausner | Files touched by this commit (2) | |
Update to 1.4.20:
Just one tiny change to fix a regression causing threads to lock
up and spin max CPU.
1.4.18 and 1.4.19 were affected. 1.4.17 and earlier were not
affected. If you are on .18 or .19 an upgrade to 1.4.20 is strongly
Thanks to commando.io for reporting the bug initially and putting
up with me being blind for a few weeks.
Fix a race condition causing new connections to appear closed,
causing an inifinte loop.
| 2014-05-04 19:04:48 by Thomas Klausner | Files touched by this commit (2) | |
Update to 1.4.19:
Fix endianness detection during configure.
Fixes a performance regression with binary protocol (up to 20%)
Fix rare segfault in incr/decr.
disable tail_repair_time by default.
Likely not needed anymore, and can rarely cause bugs.
use the right hashpower for the item_locks table. Small perf improvement.
Fix crash for LRU crawler while using lock elision (haswell+ processors)