Gitiles
Code Review Sign In
git01.mediatek.com / haproxy / 4201df77df34492be89e9c720397ff66bc5775d9 / src
  1. 1714e0f [BUG] stream_sock: disable I/O on fds reporting an error by Willy Tarreau · 16 years ago
  2. 1eead50 [BUG] don't call epoll_ctl() on closed sockets by Willy Tarreau · 16 years ago
  3. 3884cba [MINOR] show sess: report number of calls to each task by Willy Tarreau · 16 years ago
  4. 2d04559 [BUG] reject unix accepts when connection limit is reached by Willy Tarreau · 16 years ago
  5. 127334e [BUG] reset the stream_interface connect timeout upon connect or error by Willy Tarreau · 16 years ago
  6. 573fd80 [OPTIM] sepoll: do not re-check whole list upon accepts by Willy Tarreau · 16 years ago
  7. b00f9c4 [BUG] check for global.maxconn before doing accept() by Willy Tarreau · 16 years ago
  8. 06bea94 [MEDIUM] session: don't resync FSMs on non-interesting changes by Willy Tarreau · 16 years ago
  9. 1b194fe [OPTIM] buffer: new BF_READ_DONTWAIT flag reduces EAGAIN rates by Willy Tarreau · 16 years ago
  10. 6f4a82c [OPTIM] stream_sock: don't retry to read after a large read by Willy Tarreau · 16 years ago
  11. e383880 [BUG] server check intervals must not be null by Willy Tarreau · 16 years ago
  12. c7bdf09 [MINOR] stats: report number of tasks (active and running) by Willy Tarreau · 16 years ago
  13. a461318 [MINOR] task: keep a task count and clean up task creators by Willy Tarreau · 16 years ago
  14. 135a113 [MINOR] sched: permit a task to stay up between calls by Willy Tarreau · 16 years ago
  15. 26ca34e [BUG] scheduler: fix improper handling of duplicates __task_queue() by Willy Tarreau · 16 years ago
  16. 218859a [BUG] sched: don't leave 3 lasts tasks unprocessed when niced tasks are present by Willy Tarreau · 16 years ago
  17. e35c94a [MEDIUM] scheduler: get rid of the 4 trees thanks and use ebtree v4.1 by Willy Tarreau · 16 years ago
  18. 5804434 [MINOR] update ebtree to version 4.1 by Willy Tarreau · 16 years ago
  19. 8365f93 [CLEANUP] http: remove some commented out obsolete code in process_response by Willy Tarreau · 16 years ago
  20. 86ef7dc [MINOR] tcp_request: let the caller take care of errors and timeouts by Willy Tarreau · 16 years ago
  21. 8445533 [BUG] session: errors were not reported in termination flags in TCP mode by Willy Tarreau · 16 years ago
  22. a3780f2 [BUG] connect timeout is in the stream interface, not the buffer by Willy Tarreau · 16 years ago
  23. 5af24ef [CLEANUP] config: catch and report some possibly wrong rule ordering by Willy Tarreau · 16 years ago
  24. 55bc0f8 [MEDIUM] reverse internal proxy declaration order to match configuration by Willy Tarreau · 16 years ago
  25. d869b24 [MINOR] tcp-inspect: permit the use of no-delay inspection by Willy Tarreau · 16 years ago
  26. 3cd9af2 [MINOR] cfgparse: set backends to "balance roundrobin" by default by Willy Tarreau · 16 years ago
  27. ff01a21 [MINOR] cfgparse: some cleanups in the consistency checks by Willy Tarreau · 16 years ago
  28. 787bbd9 [MINOR] show errors: encode backslash as well as non-ascii characters by Willy Tarreau · 16 years ago
  29. c961946 [BUG] stream_sock: write timeout must be updated when forwarding ! by Willy Tarreau · 16 years ago
  30. 6bf1736 [BUILD] proto_http did not build on gcc-2.95 (again) by Willy Tarreau · 16 years ago
  31. 87bed62 [BUILD] build fixes for Solaris by Willy Tarreau · 16 years ago
  32. 7c84bab [MEDIUM] rearrange forwarding condition to enable splice during analysis by Willy Tarreau · 16 years ago
  33. 6f0aa47 [CLEANUP] buffer_flush() was misleading, rename it as buffer_erase by Willy Tarreau · 16 years ago
  34. ed066fa [CLEANUP] don't enable kernel splicing when socket is closed by Willy Tarreau · 16 years ago
  35. 0be0ef9 [OPTIM] do not re-check req buffer when only response has changed by Willy Tarreau · 16 years ago
  36. 531cf0c [OPTIM] task: reduce the number of calls to task_queue() by Willy Tarreau · 16 years ago
  37. d0a201b [CLEANUP] task: distinguish between clock ticks and timers by Willy Tarreau · 16 years ago
  38. 721fdbc [BUG] event_accept() must always wake the task up, even in health mode by Willy Tarreau · 16 years ago
  39. 26c2506 [MEDIUM] minor update to the task api: let the scheduler queue itself by Willy Tarreau · 16 years ago
  40. 4136522 [OPTIM] displace tasks in the wait queue only if absolutely needed by Willy Tarreau · 16 years ago
  41. 4726f53 [OPTIM] task: don't unlink a task from a wait queue when waking it up by Willy Tarreau · 16 years ago
  42. 1b8ca66 [BUG] task: fix handling of duplicate keys by Willy Tarreau · 16 years ago
  43. 39af0f6 [BUG] rate-limit in defaults section was ignored by Willy Tarreau · 16 years ago
  44. 2ade301 [BUG] disable any analysers for monitoring requests by Willy Tarreau · 16 years ago
  45. 3d8c553 [OPTIM] freq_ctr: do not rotate the counters when reading by Willy Tarreau · 16 years ago
  46. ec22b2c [CLEANUP] remove last references to term_trace by Willy Tarreau · 16 years ago
  47. 9279562 [BUG] switch server-side stream interface to close in case of abort by Willy Tarreau · 16 years ago
  48. 7958422 [OPTIM] rate-limit: cleaner behaviour on low rates and reduce consumption by Willy Tarreau · 16 years ago
  49. efcbc6e [OPTIM] maintain_proxies: only wake up when the frontend will be ready by Willy Tarreau · 16 years ago
  50. bb9251e [BUG] typo in timeout error reporting : report *res and not *err by Willy Tarreau · 16 years ago
  51. 604e830 [BUG] interface binding: length must include the trailing zero by Willy Tarreau · 16 years ago
  52. 3a7d207 [MEDIUM] implement "rate-limit sessions" for the frontend by Willy Tarreau · 16 years ago
  53. 079ff0a [MINOR] acl: add 2 new verbs: fe_sess_rate and be_sess_rate by Willy Tarreau · 16 years ago
  54. 3a8efeb [BUG] the "connslots" keyword was matched as "connlots" by Willy Tarreau · 16 years ago
  55. 7f062c4 [MEDIUM] measure and report session rate on frontend, backends and servers by Willy Tarreau · 16 years ago
  56. 7559058 [MINOR] add curr_sec_ms and curr_sec_ms_scaled for current second. by Willy Tarreau · 16 years ago
  57. defc52d [MINOR] errors dump must use user-visible date, not internal date. by Willy Tarreau · 16 years ago
  58. 74808cb [MEDIUM] implement error dump on unix socket with "show errors" by Willy Tarreau · 16 years ago
  59. f073a83 [MEDIUM] store a complete dump of request and response errors in proxies by Willy Tarreau · 16 years ago
  60. 7552c03 [MINOR] ensure that http_msg_analyzer updates pointer to invalid char by Willy Tarreau · 16 years ago
  61. f49d1df [BUG] global.tune.maxaccept must be limited even in mono-process mode by Willy Tarreau · 16 years ago
  62. 368480c [BUG] the "source" keyword must first clear optional settings by Willy Tarreau · 16 years ago
  63. 7b92db4 [BUILD] proto_http did not build on gcc-2.95 by Willy Tarreau · 16 years ago
  64. 38c99bc [BUG] fix unix socket processing of interrupted output by Willy Tarreau · 16 years ago
  65. fd3828e [BUG] fix random memory corruption using "show sess" by Willy Tarreau · 16 years ago
  66. 9b97cff [BUILD] Haproxy won't compile if DEBUG_FULL is defined by Vincenzo Farruggia · 16 years ago
  67. f39c71c [CRITICAL] fix server state tracking: it was O(n!) instead of O(n) by Krzysztof Piotr Oledzki · 16 years ago
  68. 0b9c02c [MEDIUM] implement bind-process to limit service presence by process by Willy Tarreau · 16 years ago
  69. c76721d [MEDIUM] add support for source interface binding at the server level by Willy Tarreau · 16 years ago
  70. d53f96b [MEDIUM] add support for source interface binding by Willy Tarreau · 16 years ago
  71. 4e30ed7 [BUG] inform the user when root is expected but not set by Willy Tarreau · 16 years ago
  72. 5e6e204 [MINOR] add support for bind interface name by Willy Tarreau · 16 years ago
  73. 0a3b9d9 [BUG] we must not exit if protocol binding only returns a warning by Willy Tarreau · 16 years ago
  74. 7b723ef [DOC] remove buggy comment for use_backend by Krzysztof Piotr Oledzki · 16 years ago
  75. 52d522b [BUG] Fix listen & more of 2 couples <ip>:<port> by Krzysztof Piotr Oledzki · 16 years ago
  76. 3ab68cf [MEDIUM] splice: add the global "nosplice" option by Willy Tarreau · 16 years ago
  77. 43b7899 [MEDIUM] move global tuning options to the global structure by Willy Tarreau · 16 years ago
  78. 686ac82 [OPTIM] make global.maxpipes default to global.maxconn/4 when not specified by Willy Tarreau · 16 years ago
  79. a206fa9 [STATS] report pipe usage in the statistics by Willy Tarreau · 16 years ago
  80. 3eba98a [MEDIUM] splice: make use of pipe pools by Willy Tarreau · 16 years ago
  81. 982b6e3 [MEDIUM] introduce pipe pools by Willy Tarreau · 16 years ago
  82. 98b306b [MEDIUM] splice: add hints to support older buggy kernels by Willy Tarreau · 16 years ago
  83. afb4876 [BUG] reserve some pipes for backends with splice enabled by Willy Tarreau · 16 years ago
  84. 5bd8c37 [MAJOR] complete support for linux 2.6 kernel splicing by Willy Tarreau · 16 years ago
  85. 6b4aad4 [MEDIUM] add definitions for Linux kernel splicing by Willy Tarreau · 16 years ago
  86. 259de1b [MINOR] introduce structures required to support Linux kernel splicing by Willy Tarreau · 16 years ago
  87. 66aa61f [MEDIUM] splice: add configuration options and set global.maxpipes by Willy Tarreau · 16 years ago
  88. 3ec79b9 [MINOR] global.maxpipes: add the ability to reserve file descriptors for pipes by Willy Tarreau · 16 years ago
  89. a456f2a [MEDIUM] stream_sock: try to send pending data on chk_snd() by Willy Tarreau · 16 years ago
  90. d2def0f [MINOR] stream_sock: fix a few wrong empty calculations by Willy Tarreau · 16 years ago
  91. 9c0fe59 [MEDIUM] stream_sock_read: call ->chk_snd whenever there are data pending by Willy Tarreau · 16 years ago
  92. 0c2fc1f [MEDIUM] split stream_sock_write() into callback and core functions by Willy Tarreau · 16 years ago
  93. ac128fe [CLEANUP] stream_sock: move the write-nothing condition out of the loop by Willy Tarreau · 16 years ago
  94. efc612c [CLEANUP] replace a few occurrences of (flags & X) && !(flags & Y) by Willy Tarreau · 16 years ago
  95. 68eac13 [OPTIM] stream_sock: factor out the buffer full handling out of the loop by Willy Tarreau · 16 years ago
  96. 03d60bb [OPTIM] buffer: replace rlim by max_len by Willy Tarreau · 16 years ago
  97. af78d0f [OPTIM] stream_sock: do not ask for polling on EAGAIN if we have read by Willy Tarreau · 16 years ago
  98. 0abebcc [MEDIUM] i/o: rework ->to_forward and ->send_max by Willy Tarreau · 16 years ago
  99. 4d9b1de [MEDIUM] stream_sock: factor out the return path in case of no-writes by Willy Tarreau · 16 years ago
  100. dcef33f [MINOR] add the splice_len member to the buffer struct in preparation of splice support by Willy Tarreau · 16 years ago