summaryrefslogtreecommitdiffhomepage
AgeCommit message (Collapse)AuthorFilesLines
2015-05-26nginx-1.9.1-RELEASErelease-1.9.1Maxim Dounin1-0/+74
2015-05-25Disabled SSLv3 by default (ticket #653).Maxim Dounin6-12/+9
2015-05-25Configure: GNU Hurd properly recognized.Maxim Dounin2-0/+17
With this change it's no longer needed to pass -D_GNU_SOURCE manually, and -D_FILE_OFFSET_BITS=64 is set to use 64-bit off_t. Note that nginx currently fails to work properly with master process enabled on GNU Hurd, as fcntl(F_SETOWN) returns EOPNOTSUPP for sockets as of GNU Hurd 0.6. Additionally, our strerror() preloading doesn't work well with GNU Hurd, as it uses large numbers for most errors.
2015-05-21Fixed reuseport with accept_mutex.Maxim Dounin1-1/+6
2015-05-20Upstream: report to error_log when max_fails is reached.Ruslan Ermilov2-0/+10
This can be useful to understand why "no live upstreams" happens, in particular.
2015-05-20The "reuseport" option of the "listen" directive.Maxim Dounin12-6/+206
When configured, an individual listen socket on a given address is created for each worker process. This allows to reduce in-kernel lock contention on configurations with high accept rates, resulting in better performance. As of now it works on Linux and DragonFly BSD. Note that on Linux incoming connection requests are currently tied up to a specific listen socket, and if some sockets are closed, connection requests will be reset, see https://lwn.net/Articles/542629/. With nginx, this may happen if the number of worker processes is reduced. There is no such problem on DragonFly BSD. Based on previous work by Sepherosa Ziehau and Yingqi Lu.
2015-05-20Simplified ngx_http_init_listening().Maxim Dounin3-21/+3
There is no need to set "i" to 0, as it's expected to be 0 assuming the bindings are properly sorted, and we already rely on this when explicitly set hport->naddrs to 1. Remaining conditional code is replaced with identical "hport->naddrs = i + 1". Identical modifications are done in the mail and stream modules, in the ngx_mail_optimize_servers() and ngx_stream_optimize_servers() functions, respectively. No functional changes.
2015-05-20Introduced worker number, ngx_worker.Maxim Dounin4-0/+5
2015-05-20Configure: style.Maxim Dounin1-1/+1
2015-05-19Core: properly initialized written bytes counter in memory log.Valentin Bartenev1-1/+1
2015-05-18Upstream hash: consistency across little/big endianness.Sergey Kandaurov2-8/+30
2015-05-16Upstream: $upstream_connect_time.Ruslan Ermilov2-1/+14
The variable keeps time spent on establishing a connection with the upstream server.
2015-05-16Upstream: times to obtain header/response are stored as ngx_msec_t.Ruslan Ermilov2-30/+13
2015-05-15Events: ngx_event_t size reduction by grouping bit fields.Igor Sysoev1-9/+8
2015-05-06Events: made a failure to create a notification channel non-fatal.Ruslan Ermilov1-1/+1
This may happen if eventfd() returns ENOSYS, notably seen on CentOS 5.4. Such a failure will now just disable the notification mechanism and let the callers cope with it, instead of failing to start worker processes. If thread pools are not configured, this can safely be ignored.
2015-04-29Configure: handle deprecated options.Ruslan Ermilov1-8/+12
Removed the deprecated --without-http_limit_zone_module option. Deprecated the --with-imap and --with-imap_ssl_module options.
2015-04-29Removed the deprecated "imap" directive.Ruslan Ermilov1-13/+0
2015-04-29Removed the deprecated "so_keepalive" directive.Ruslan Ermilov3-31/+0
2015-04-29Removed deprecated HTTP directives.Ruslan Ermilov1-33/+0
2015-04-29Removed the deprecated "connections" directive.Ruslan Ermilov1-13/+0
2015-04-28Fixed overflow detection in ngx_inet_addr().Valentin Bartenev1-5/+5
Overflow detection of the last octet might not work. Reported by Sergey Polovko.
2015-04-28Version bump.Valentin Bartenev1-2/+2
2015-04-28release-1.9.0 tagMaxim Dounin1-0/+1
2015-04-28nginx-1.9.0-RELEASErelease-1.9.0Maxim Dounin1-0/+78
2015-04-27Added stream module to win32 builds.Maxim Dounin1-0/+2
2015-04-27Win32: shared memory base addresses and remapping.Maxim Dounin4-2/+100
Two mechanisms are implemented to make it possible to store pointers in shared memory on Windows, in particular on Windows Vista and later versions with ASLR: - The ngx_shm_remap() function added to allow remapping of a shared memory zone to the address originally used for it in the master process. While important, it doesn't solve the problem by itself as in many cases it's not possible to use the address because of conflicts with other allocations. - We now create mappings at the same address in all processes by starting mappings at predefined addresses normally unused by newborn processes. These two mechanisms combined allow to use shared memory on Windows almost without problems, including reloads. Based on the patch by Sergey Brester: http://mailman.nginx.org/pipermail/nginx-devel/2015-April/006836.html
2015-04-27Win32: fixed shm.handle loss on reload.Maxim Dounin1-0/+3
2015-04-27Core: fixed nginx_shared_zone name.Maxim Dounin1-1/+1
2015-02-20Mail: error_log support.Vladimir Homutov4-19/+54
2015-04-25Core: the ngx_set_connection_log() macro.Vladimir Homutov7-27/+17
The http and stream versions of this macro were identical.
2015-04-24Merge proxy_protocol setting of listen directives.Roman Arutyunyan1-1/+4
It's now enough to specify proxy_protocol option in one listen directive to enable it in all servers listening on the same address/port. Previously, the setting from the first directive was always used.
2015-04-23Removed the "worker_rlimit_sigpending" directive.Ruslan Ermilov3-22/+0
It was only needed by the just removed rtsig module.
2015-04-23Removed the obsolete rtsig module.Ruslan Ermilov14-914/+27
2015-04-22Removed the obsolete aio module.Ruslan Ermilov20-630/+14
2015-04-22Stream: prevent repeated event notifications after eof.Roman Arutyunyan1-1/+4
When client or upstream connection is closed, level-triggered read event remained active until the end of the session leading to cpu hog. Now the flag NGX_CLOSE_EVENT is used to unschedule the event.
2015-04-22Upstream: allow multiple upstreams to use the same shared zone.Ruslan Ermilov2-84/+112
2015-04-21Memcached: enabled ranges.Martin Mlynář1-0/+1
2015-04-21Upstream: simplified ip_hash and hash peer selection code.Ruslan Ermilov3-66/+24
Now that peers are stored as a list, the weighted and unweighted cases became nearly identical.
2015-04-20Fixed building --with-stream when precompiled headers are used.Sergey Kandaurov1-1/+1
2015-04-20Limit req: removed check for unknown limit_req_zone.Sergey Kandaurov1-7/+0
With 48b3d5ddfb03, it's possible to specify limit_req_zone after limit_req.
2015-04-20Core: allow shared memory size to be declared after a reference.Sergey Kandaurov1-0/+4
For example, this fixes the case when "proxy_cache_path" is specified after "proxy_cache" that references it.
2015-04-20Stream: port from NGINX+.Ruslan Ermilov20-2/+6079
2015-04-19Upstream: fixed unlocked access to peer->conns.Ruslan Ermilov1-3/+6
2015-03-26Replaced the remaining NGX_OLD_THREADS check with NGX_WIN32.Ruslan Ermilov2-3/+3
2015-03-26Removed NGX_OLD_THREADS from select and poll modules.Ruslan Ermilov2-20/+0
These modules can't be compiled on win32.
2015-03-26Removed "worker_threads" and "thread_stack_size" directives.Ruslan Ermilov5-78/+1
2015-03-26Removed unused thread-local-storage code.Ruslan Ermilov5-56/+0
2015-03-26Removed ngx_threaded and related code.Ruslan Ermilov3-39/+0
2015-04-16Upstream: get rid of questionable micro-optimization in ip_hash.Ruslan Ermilov1-7/+2
If a peer was initially skipped due to max_fails, there's no reason not to try it again if enough time has passed, and the next_upstream logic is in action. This also reduces diffs with NGINX Plus.
2015-04-16Core: ensure that ngx_config.h is always included first.Sergey Kandaurov1-0/+3
This fixes compilation of various 3rd party modules when nginx is configured with threads.
generated by cgit (git 2.34.1) at 2025-12-07 03:12:26 +0000