- 03 Dec, 2013 13 commits
-
-
Geoff Simmons authored
- read config files - read closing tags for *both* client and backend requests
-
Geoff Simmons authored
-
Geoff Simmons authored
- added debugging - read closing tags for client and/or backend requests
-
Geoff Simmons authored
-
Geoff Simmons authored
output formats now compiled at init time and formatted with callbacks at runtime
-
Geoff Simmons authored
- stats/monitoring for data length overflows
-
Geoff Simmons authored
- fd table is static in varnishevent.c - mutexing SPSCQ enqueue and dequeue - writer flushes only when waiting
-
Geoff Simmons authored
- fixes for empty data fields - preliminary fix for SessionOpen, SessionClose & SessStat
-
Geoff Simmons authored
-
Geoff Simmons authored
-
Geoff Simmons authored
- fixed a bug parsing fields from data - now ignoring SessionClose and StatSess
-
Geoff Simmons authored
-
Geoff Simmons authored
-
- 20 Aug, 2012 2 commits
-
-
Tollef Fog Heen authored
-
Tollef Fog Heen authored
-
- 15 Aug, 2012 1 commit
-
-
Martin Blix Grydeland authored
wrk_herder_thread and wrk_herdtimer_thread causing bogus n_wrk_max stat increments. Fixes: #1183
-
- 08 Aug, 2012 1 commit
-
-
Andreas Plesner Jacobsen authored
-
- 05 Aug, 2012 1 commit
-
-
Andreas Plesner Jacobsen authored
-
- 27 Jul, 2012 1 commit
-
-
Andreas Plesner Jacobsen authored
-
- 20 Jul, 2012 1 commit
-
-
Lasse Karstensen authored
-
- 19 Jul, 2012 3 commits
-
-
Martin Blix Grydeland authored
If the ban lurker finds a busy object, skip the object and defer the checking to a later pass. No test case because it is very timing sensitive (but see the trac bug report for a VTC-file that mostly triggers it on the 3.0 branch only) Fixes: #1162
-
Martin Blix Grydeland authored
There is a short window of opportunity between HSH_Insert() and HSH_Unbusy(), where the locks are released and the expiry thread can try to expire an object that is still busy (for objects with very short TTL). This patch makes the expiry thread check for busy objects and wait if the head of the binheap is busy. No test case as the window is too small. Fixes: #1150
-
Martin Blix Grydeland authored
An attempt to nuke a busy object will end in assertion.
-
- 16 Jul, 2012 1 commit
-
-
- 13 Jul, 2012 1 commit
-
-
Dag Haavi Finstad authored
-
- 12 Jul, 2012 1 commit
-
-
Martin Blix Grydeland authored
objects. This avoids a memory race on the n_sess counter, which can lead to excessive session object allocation. Keeping the counters of in use and released separate allows the acceptor to continue to run lockless. Fixes: #897
-
- 05 Jul, 2012 1 commit
-
-
Dag Haavi Finstad authored
-
- 20 Jun, 2012 1 commit
-
-
Martin Blix Grydeland authored
Patch by: tnt
-
- 06 Jun, 2012 2 commits
-
-
Poul-Henning Kamp authored
Fixes #1100 Conflicts: bin/varnishd/cache_fetch.c bin/varnishd/cache_panic.c
-
Poul-Henning Kamp authored
Conflicts: bin/varnishd/cache/cache_esi_fetch.c bin/varnishd/cache_fetch.c bin/varnishd/cache_gzip.c
-
- 25 May, 2012 1 commit
-
-
Tollef Fog Heen authored
-
- 24 May, 2012 9 commits
-
-
Andreas Plesner Jacobsen authored
-
Poul-Henning Kamp authored
Submitted by: Martin Fixes #1140
-
Poul-Henning Kamp authored
-
Dag Haavi Finstad authored
Fixes a case where we might get a cache hit even though hash_always_miss is set. Fixes: #1073
-
Poul-Henning Kamp authored
-
Kristian Lyngstol authored
Fixes #1035
-
Poul-Henning Kamp authored
-
Poul-Henning Kamp authored
-
Dan McGee authored
Implemented more or less as described in the pcrejit(3) manpage, and adds some compatibility defines for use with older pre-8.20 libraries that do not have this functionality. Fixes: #1080
-