| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
In 7583:efd71d49bde0 (nginx 1.17.5) along with introduction of the
ioctl(FIONREAD) support proper handling of systems without EPOLLRDHUP
support in the kernel (but with EPOLLRDHUP in headers) was broken.
Before the change, rev->available was never set to 0 unless
ngx_use_epoll_rdhup was also set (that is, runtime test for EPOLLRDHUP
introduced in 6536:f7849bfb6d21 succeeded). After the change,
rev->available might reach 0 on systems without runtime EPOLLRDHUP
support, stopping further reading in ngx_readv_chain() and ngx_unix_recv().
And, if EOF happened to be already reported along with the last event,
it is not reported again by epoll_wait(), leading to connection hangs
and timeouts on such systems.
This affects Linux kernels before 2.6.17 if nginx was compiled
with newer headers, and, more importantly, emulation layers, such as
DigitalOcean's App Platform's / gVisor's epoll emulation layer.
Fix is to explicitly check ngx_use_epoll_rdhup before the corresponding
rev->pending_eof tests in ngx_readv_chain() and ngx_unix_recv().
|
|
This makes it possible to avoid looping for a long time while working
with a fast enough peer when data are added to the socket buffer faster
than we are able to read and process them (ticket #1431). This is
basically what we already do on FreeBSD with kqueue, where information
about the number of bytes in the socket buffer is returned by
the kevent() call.
With other event methods rev->available is now set to -1 when the socket
is ready for reading. Later in ngx_recv() and ngx_recv_chain(), if
full buffer is received, real number of bytes in the socket buffer is
retrieved using ioctl(FIONREAD). Reading more than this number of bytes
ensures that even with edge-triggered event methods the event will be
triggered again, so it is safe to stop processing of the socket and
switch to other connections.
Using ioctl(FIONREAD) only after reading a full buffer is an optimization.
With this approach we only call ioctl(FIONREAD) when there are at least
two recv()/readv() calls.
|
|
When it's known that the kernel supports EPOLLRDHUP, there is no need in
additional recv() call to get EOF or error when the flag is absent in the
event generated by the kernel. A special runtime test is done at startup
to detect if EPOLLRDHUP is actually supported by the kernel because
epoll_ctl() silently ignores unknown flags.
With this knowledge it's now possible to drop the "ready" flag for partial
read. Previously, the "ready" flag was kept until the recv() returned EOF
or error. In particular, this change allows the lingering close heuristics
(which relies on the "ready" flag state) to actually work on Linux, and not
wait for more data in most cases.
The "available" flag is now used in the read event with the semantics similar
to the corresponding counter in kqueue.
|
|
This makes ngx_unix_recv() and ngx_udp_unix_recv() differ minimally.
|
|
There's no real need in two separate implementations,
with and without kqueue support.
|
|
Now all functions always drop the ready flag in this case.
|
|
|
|
There is nothing to do more when recv() has returned 0,
so we should drop the flag.
|
|
Currently this flag is needed for epoll and rtsig, and though these methods
usually present on different platforms than kqueue, nginx can be compiled to
support all of them.
|
|
|
|
|
|
this fixes endless loop at least in lingering close
|
|
|
|
|
|
*) Bugfix: the accept-filter and the TCP_DEFER_ACCEPT option were set
for first "listen" directive only; the bug had appeared in 0.3.31.
*) Bugfix: in the "proxy_pass" directive without the URI part in a
subrequest.
|
|
*) Change: the "optimize_host_names" directive was renamed to the
"optimize_server_names".
*) Bugfix: if in the "proxy_pass" directive was no the URI part, then
the main request URI was transferred to a backend while proxying the
SSI subrequest.
|
|
*) Workaround: for bug in FreeBSD kqueue.
*) Bugfix: now a response generated by the "post_action" directive is
not transferred to a client.
*) Bugfix: the memory leaks were occurring if many log files were used.
*) Bugfix: the first "proxy_redirect" directive was working inside one
location.
*) Bugfix: on 64-bit platforms segmentation fault may occurred on start
if the many names were used in the "server_name" directives; the bug
had appeared in 0.3.18.
|
|
*) Feature: the new 444 code of the "return" directive to close
connection.
*) Feature: the "so_keepalive" directive in IMAP/POP3 proxy.
*) Bugfix: if there are unclosed connection nginx now calls abort()
only on gracefull quit and active "debug_points" directive.
|
|
*) Feature: the IMAP/POP3 proxy supports STARTTLS and STLS.
*) Bugfix: the IMAP/POP3 proxy did not work with the select, poll, and
/dev/poll methods.
*) Bugfix: in SSI handling.
*) Bugfix: now Solaris sendfilev() is not used to transfer the client
request body to FastCGI-server via the unix domain socket.
*) Bugfix: the "auth_basic" directive did not disable the
authorization; the bug had appeared in 0.3.11.
|
|
*) Security: if nginx was built with the ngx_http_realip_module and the
"satisfy_any on" directive was used, then access and authorization
directives did not work. The ngx_http_realip_module was not built
and is not built by default.
*) Change: the "$time_gmt" variable name was changed to "$time_local".
*) Change: the "proxy_header_buffer_size" and
"fastcgi_header_buffer_size" directives was renamed to the
"proxy_buffer_size" and "fastcgi_buffer_size" directives.
*) Feature: the ngx_http_memcached_module.
*) Feature: the "proxy_buffering" directive.
*) Bugfix: the changes in accept mutex handling when the "rtsig" method
was used; the bug had appeared in 0.3.0.
*) Bugfix: if the client sent the "Transfer-Encoding: chunked" header
line, then nginx returns the 411 error.
*) Bugfix: if the "auth_basic" directive was inherited from the http
level, then the realm in the "WWW-Authenticate" header line was
without the "Basic realm" text.
*) Bugfix: if the "combined" format was explicitly specified in the
"access_log" directive, then the empty lines was written to the log;
the bug had appeared in 0.3.8.
*) Bugfix: nginx did not run on the sparc platform under any OS except
Solaris.
*) Bugfix: now it is not necessary to place space between the quoted
string and closing bracket in the "if" directive.
|
|
*) Feature: the listen(2) backlog in the "listen" directive can be
changed using the -HUP signal.
*) Feature: the geo2nginx.pl script was added to contrib.
*) Change: the FastCGI parameters with the empty values now are passed
to a server.
*) Bugfix: the segmentation fault occurred or the worker process may
got caught in an endless loop if the proxied or FastCGI server sent
the "Cache-Control" header line and the "expires" directive was
used; in the proxied mode the the bug had appeared in 0.1.29.
|
|
*) Bugfix: the proxied request was sent without arguments if the
request contains "//", "/./", "/../" or "%XX".
*) Bugfix: the large compressed responses may be transferred not
completely.
*) Bugfix: the files bigger than 2G was not transferred on Linux that
does not support sendfile64().
*) Bugfix: while the build configuration on Linux the
--with-poll_module parameter was required; the bug had appeared in
0.1.8.
|
|
*) Feature: the --user=USER, --group=GROUP, and --with-ld-opt=OPTIONS
options in configure.
*) Feature: the server_name directive supports *.domain.tld.
*) Bugfix: the portability improvements.
*) Bugfix: if configuration file was set in command line, the
reconfiguration was impossible; the bug had appeared in 0.1.1.
*) Bugfix: proxy module may get caught in an endless loop when sendfile
is not used.
*) Bugfix: with sendfile the response was not recoded according to the
charset module directives; the bug had appeared in 0.1.1.
*) Bugfix: very seldom bug in the kqueue processing.
*) Bugfix: the gzip module compressed the proxied responses that was
already compressed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
