|
c986f232
|
2011-12-08T14:30:20
|
|
Fix behavior of evbuffer_peek(buf,-1,NULL,NULL,0)
(Patch altered by nickm to not affect the behavior of
evbuffer_peek(buf,-1,NULL,vec,n_vec).)
|
|
358c745e
|
2011-12-08T11:39:48
|
|
check for sysctl before we use it
Not all C libraries under Linux support the sysctl() func.
|
|
19277763
|
2011-12-06T13:35:54
|
|
Fix a silly compilation error with the sun compiler
Apparently, other compilers were allowing "return free(x)" in a
function returning void.
|
|
11f36a5f
|
2011-12-05T15:02:27
|
|
Be absolutely sure to clear pncalls before leaving event_signal_closure
I thought we'd fixed the cases where this could come up, but
apparently having an event_base_break() happen while processing
signal events could get us in trouble.
Found by Remi Gacogne. Sourceforge issue 3451433 .
|
|
|
ba4d6696
|
2011-11-18T15:34:37
|
|
Increment version to 2.0.16-stable-dev
|
|
|
5de3fa32
|
2011-11-18T15:27:06
|
|
Increment version to 2.0.16-stable
|
|
|
31c99bd2
|
2011-11-18T15:14:50
|
|
Revise 2.0.16-stable changelog
|
|
|
ebf82199
|
2011-11-17T17:42:45
|
|
add comment to new consider_reading code
|
|
2aa036fa
|
2011-11-17T11:59:41
|
|
Avoid spinning on OpenSSL reads
Previously, if some sender were generating data to read on an
OpenSSL connection as fast as we could process it, we could easily
wind up looping on an openssl do_read operation without ever
considering other sockets.
The difference between this and the original method in
consider_reading() is that it only loops for a single completed
*frame* instead of looping until fd is drained or an error condition
was triggered.
{Patch split out by nickm}
|
|
|
96c562fa
|
2011-11-17T11:54:07
|
|
Move SSL rate-limit enforcement into bytes_to_read()
|
|
|
a186e732
|
2011-11-17T11:45:49
|
|
Refactor amount-to-read calculations in buffervent_ssl consider_reading()
Split up consider_reading()'s conditional checks into another function
can_read() for simplicity sake.
{Split into a separate patch by nickm}
|
|
|
6660c9a3
|
2011-11-15T18:34:24
|
|
Revert "Avoid potential SSL read spinlocks"
This reverts commit fc52dbac87f4937f8306759506d6a2ad15ca244c.
|
|
|
a62346de
|
2011-11-15T18:33:50
|
|
Revert "openssl bufferevent has the same issue with writing as prior commit."
This reverts commit 7353663eb7c0b2a1caaaa5acd818515f156cf2ca.
|
|
|
34045c8f
|
2011-11-15T17:22:12
|
|
Add new entries to changelog, new credits to README
|
|
|
b17b0eec
|
2011-11-15T17:11:42
|
|
Fix DNS memleak checks when running with malloc-replacement/debugging disabled
|
|
|
e7874133
|
2011-11-14T17:33:02
|
|
Don't try to make notifiable event_base when no threading fns are configured
|
|
|
4e797f38
|
2011-11-14T17:32:22
|
|
Warn when unable to construct base because of failing make_base_notifiable
|
|
|
7353663e
|
2011-11-14T10:57:15
|
|
openssl bufferevent has the same issue with writing as prior commit.
|
|
|
fc52dbac
|
2011-11-14T10:24:07
|
|
Avoid potential SSL read spinlocks
OpenSSL bufferevents with deferred callbacks enabled under high load will
spinlock in the function consider_reading(). This loop continues until all
data has been read.
Because of this condition; openssl bufferevents will never return back into
event_base_loop() until SSL_read has determined data is no longer ready.
As of yet I have not found a reason why this while loop exists, so this patch
just swaps out while for if.
If needed I can write same code which would trigger this effect; optionally
libevhtp has a test.c program which can be run with the following flags:
./test -s <keyfile.pem>
curl -vvvv -k -d@<HUGE_ASS_FILE> https://127.0.0.1:8081/
The return data will include the number of times the readcb got data and the
length of that read.
Without this patch, you are likely to see a small amount of "bytes read....",
otherwise the "bytes read..." return data should show much more reasonable
numbers.
|
|
a3f320e8
|
2011-11-09T00:17:56
|
|
Improve win32 behavior of dns-sample.c codex
|
|
674bc6a2
|
2011-11-03T11:43:49
|
|
Fix typo in whatsnew-2.0.txt
|
|
|
c37069cd
|
2011-11-02T16:09:15
|
|
Fix an evbuffer crash in evbuffer_remove_buffer()
Found by Greg Hazel.
|
|
7eb52eb8
|
2011-11-02T15:19:05
|
|
improve test to remove at least one buffer from src
|
|
|
90bd620f
|
2011-11-01T13:44:40
|
|
unit test for remove_buffer bug
|
|
|
447b0bad
|
2011-10-30T22:32:18
|
|
Fix compile warning from saying event2/*.h inside a comment
Based on a patch by Adrian Chadd
|
|
1aee7183
|
2011-10-26T13:24:30
|
|
epoll: close fd on alloc fail at initialization
If the memory allocations fail then we free any other allocated
structures but don't close the file descriptor resulting in an leak of
fd's.
|
|
|
3c824bd3
|
2011-10-24T13:18:09
|
|
Update copyright dates to 2011.
|
|
|
724bfb56
|
2011-10-19T22:59:47
|
|
Add note about evhttp_send_reply_end to its doxygen
|
|
9e6a4efa
|
2011-10-19T17:44:17
|
|
More detailed message in case of libevent self-debugging failure.
|
|
|
5e42202d
|
2011-10-19T22:41:11
|
|
Style and comment tweaks for dns/leak* tests
|
|
|
f7841bfc
|
2011-10-18T17:49:40
|
|
Test for commit aff6ba1
|
|
|
21a08d68
|
2011-10-19T22:38:37
|
|
Empty DNS reply with OK status is another way to say NODATA.
Sometimes DNS reply has nothing but query section. It does not look like
error, so it should be treated as NODATA with TTL=0 as soon as there is
no SOA record to deduce negative TTL from.
|
|
|
d58c15ee
|
2011-10-19T22:36:12
|
|
Tests for 94fba5b and f72e8f6
|
|
|
8589f6c4
|
2011-10-12T01:00:23
|
|
Bump version to 2.0.15-stable-dev
|
|
|
c54c2358
|
2011-10-12T00:39:22
|
|
Credit a patch from a one-named user
|
|
|
4d9529fc
|
2011-10-12T00:22:17
|
|
Increment version to 2.0.15-stable
|
|
|
7c3e0612
|
2011-10-12T00:16:12
|
|
Add changelog for 2.0.15-stable
|
|
|
ba5c27d4
|
2011-10-10T08:24:43
|
|
refer to non-deprecated evdns functions in comments
|
|
|
706aa5f4
|
2011-10-06T15:11:50
|
|
Merge remote-tracking branch 'github/20_addfile_ssl' into patches-2.0
|
|
|
39c0cf7c
|
2011-10-03T12:49:02
|
|
Fix some "value never used" warnings with gcc 4.6.1
|
|
|
2b768479
|
2011-10-03T12:45:36
|
|
Make write-checking fixes use tt_fail_perror
|
|
|
c3b62fd7
|
2011-07-12T13:05:36
|
|
Fixed compiler warnings for unchecked read/write calls.
|
|
|
0ba0af9c
|
2011-09-29T09:30:04
|
|
Prefer mmap to sendfile unless a DRAINS_TO_FD flag is set. Allows add_file to work with SSL.
The sendfile() implementation for evbuffer_add_file is potentially more
efficient, but it has a problem: you can only use it to send bytes over
a socket using sendfile(). If you are writing bytes via SSL_send() or
via a filter, or if you need to be able to inspect your buffer, it
doesn't work.
As an easy fix, this patch disables the sendfile-based implementation of
evbuffer_add_file on an evbuffer unless the user sets a new
EVBUFFER_FLAG_DRAINS_TO_FD flag on that evbuffer, indicating that the
evbuffer will not be inspected, but only written out via
evbuffer_write(), evbuffer_write_atmost(), or drained with stuff like
evbuffer_drain() or evbuffer_add_buffer(). This flag is off by
default, except for evbuffers used for output on bufferevent_socket.
In the future, it could be interesting to make a best-effort file
segment implementation that tries to send via sendfile, but mmaps on
demand. That's too much complexity for a stable release series, though.
|
|
|
1ef1f684
|
2011-09-28T09:22:17
|
|
Make evbuffer callbacks get the right n_added value after evbuffer_add
Patch from Alex.
|
|
|
296d29a1
|
2011-09-26T11:07:58
|
|
Merge branch '20_loopbreak_in_signal' into patches-2.0
|
|
|
7f82382a
|
2011-09-25T07:39:00
|
|
Use _SOURCES, not _sources, in sample/Makefile.am
Found by Adrian Chadd
|
|
9ae061ac
|
2011-09-15T13:06:38
|
|
le-proxy and regress depend on openssl directly
|
|
94fba5b9
|
2011-08-10T15:58:47
|
|
Add DNS_ERR_NODATA error code to handle empty replies.
|
|
|
2b6eae59
|
2011-08-10T15:58:19
|
|
Fix docstring in dns.h
|
|
|
4e8eb6a5
|
2011-09-09T20:53:30
|
|
When a signal callback is activated to run multiple times, allow event_base_loopbreak to work even before they all have run.
Found by Abilio Marques.
|
|
|
f72e8f66
|
2011-08-31T00:56:45
|
|
DNS: add ttl for negative answers using RFC 2308 idea.
|
|
|
a718b6c3
|
2011-08-31T11:25:11
|
|
Increment version to 2.0.14-stable-dev
|
|
|
ac9f2adb
|
2011-08-31T00:23:20
|
|
Credit new contributors for 2.0.14-stable
|
|
|
da90a9be
|
2011-08-30T22:35:51
|
|
Pick a release date for the changelog
|
|
|
85976ddf
|
2011-08-30T22:28:02
|
|
Bump version to 2.0.14-stable
|
|
54f7e61b
|
2011-08-29T23:39:26
|
|
clear read watermark on underlying bufferevent when creating filtering bev to fix potentially failing fragmented ssl handshakes
|
|
|
6476d92d
|
2011-08-29T13:40:03
|
|
Checkpoint changelog entries for 2.0.14-stable
|
|
|
e6af35d7
|
2011-08-24T21:39:28
|
|
Correctly terminate IO on an async bufferevent on bufferevent_free
|
|
|
0ff2c5a9
|
2011-08-24T18:42:12
|
|
Have test-ratelim.c support IOCP
|
|
|
a98da7bf
|
2011-08-24T18:41:35
|
|
Make IOCP rate-limiting group support stricter and less surprising.
Previously, we wouldn't decrement read/write buckets because of IOCP
reads and writes until those reads and writes were complete. That's
not so bad on the per-connection front. But for group limits, the
old approach makes us launch a huge amount of reads and writes
whenever the group limit becomes positive, and then decrement the
limit to a hugely negative number as they complete.
With this patch, we decrement our read buckets whenever we launch an
IOCP read or write, based on the maximum that tried to read or
write. Later, when the operations finish, we re-increment the
bucket based on the portion of the request that couldn't finish.
|
|
|
c75341b0
|
2011-08-24T18:42:00
|
|
Support negative arguments to _bufferevent_decrement_(read/write)_buckets()
|
|
|
2f51dc03
|
2011-08-28T14:03:10
|
|
Cleanup on 7c11e51e1ab: fix strtol usage
|
|
|
6056d6e0
|
2011-08-28T14:02:40
|
|
Cleanup on 7c11e51e1ab: restore c90 declaration compliance
|
|
7c11e51e
|
2011-08-27T05:48:11
|
|
Clean up some problems identified by Coverity.
|
|
|
5b18f130
|
2011-08-24T16:17:05
|
|
Make rate limiting work with common_timeout logic
|
|
|
6736852e
|
2011-08-18T15:09:44
|
|
Merge branch '20_iocp_fixes' into patches-2.0
|
|
|
6acfbdd8
|
2011-08-18T12:35:27
|
|
Make overlapped reads result in evbuffer callbacks getting invoked
|
|
|
495c227f
|
2011-08-18T11:41:55
|
|
IOCP: don't launch reads or writes on an unconnected socket
|
|
04656ea8
|
2011-08-15T14:40:32
|
|
Try to fix 'make distcheck' errors when building out-of-tree
|
|
|
e067d0e3
|
2011-08-17T21:47:19
|
|
Merge branch '20_low_ratelim' into patches-2.0
|
|
643922e9
|
2011-08-15T13:39:10
|
|
Solaris sendfile: correctly detect amount of data sent
Original message:
Solaris sendfile seems to fail when sending moderately large (<1GB)
files. Not a 32/64 problem, but a buffer problem.
Anyone else ever try this? It is definitely broken in http-server.c.
It seems to be broken in the following way:
When sendfile sends partial data (EAGAIN, would block), "res" is
always -1, rather than the amount sent.
Here's a patch that reads from the "offset" pointer instead to
discover what was sent. This seems to work:
|
|
|
aff6ba15
|
2011-08-11T03:24:06
|
|
Fix request_finished memory leak with debugging turned on.
|
|
|
9b724b28
|
2011-08-11T03:10:08
|
|
Fix evsig_dealloc memory leak with debugging turned on.
|
|
|
50be5a14
|
2011-08-11T03:06:07
|
|
Another docstring fix.
|
|
|
6d5440e8
|
2011-08-11T15:15:17
|
|
Fix handling of group rate limits under 64 bytes of burst
The "min_share" logic, which was designed to prevent piles of
extremely small writes when running up against a group rate limit,
could lead to confusing behavior if you ever set a min_share less
than your burst rate. If that happened, then as soon as your group
rate limit was exhausted, you'd stop reading/writing, and never
start again, since the amount readable/writeable would never
actually hit min_share.
We now cap min_share at the rate per tick.
Found by George Kadianakis
|
|
5d1b255b
|
2011-08-10T19:11:55
|
|
Ignore deprecation warnings on OS X
Starting with Lion, Apple decided to deprecate the system openssl. We
can start requiring users to install their own openssl once OS X doesn't
ship with it anymore.
|
|
b4423029
|
2011-08-08T17:06:46
|
|
Allow OS-neutral builds for platforms where some versions have arc4random_buf
|
|
|
4a343943
|
2011-07-26T10:31:18
|
|
Propagate errors on the underlying bufferevent to the user.
|
|
|
1183f7e2
|
2011-08-01T10:27:56
|
|
Fix typo in event_compat.h comments.
|
|
|
a2fdf9b0
|
2011-07-18T23:37:59
|
|
Bump version to 2.0.13-stable-dev
|
|
|
80414e22
|
2011-07-18T18:19:25
|
|
Bump version to 2.0.13-dev
|
|
|
62b8ce58
|
2011-07-18T17:05:20
|
|
acks and changelog for 2.0.13-stable
|
|
|
b3b425eb
|
2011-07-18T12:45:50
|
|
Give Makefile.am echo a non-null argument. msys likes this
|
|
|
00a7a0e4
|
2011-07-17T21:48:38
|
|
Fix a warning in evutil_rand when building with threads disabled
|
|
|
4a5c82d6
|
2011-07-15T10:20:01
|
|
Use AM_CPPFLAGS in sample/Makefile.am, not AM_CFLAGS
Reported by Dagobert Michelsen.
|
|
|
d5bd604a
|
2011-07-05T14:57:08
|
|
Add doxygen to .gitignore
|
|
|
caf695af
|
2011-07-05T14:55:09
|
|
Fix up test_evutil_snprintf
|
|
|
af6a05f7
|
2011-07-05T14:51:24
|
|
Merge remote-tracking branch 'github/20_size_fmt' into patches-2.0
|
|
|
341e1b03
|
2011-07-05T13:04:30
|
|
Merge branch 'doxygen' into patches-2.0
|
|
|
aea0555b
|
2011-07-04T23:14:19
|
|
Update Doxyfile to produce more useful output
|
|
|
2888facc
|
2011-07-04T23:02:11
|
|
Revise the event/evbuffer/bufferevent doxygen for clarity and accuracy
|
|
|
49d11362
|
2011-07-05T00:11:59
|
|
Fix select.c compilation on systems with no NFDBITS
|
|
|
e7fe9270
|
2011-07-04T12:16:08
|
|
Merge remote-tracking branch 'github/20_global_locks_init' into patches-2.0
|
|
|
f87f5689
|
2011-07-04T11:47:24
|
|
Speed up invoke_callbacks on evbuffers when there are no callbacks
This fixes a performance regression against 1.4
|
|
e050703d
|
2011-07-04T11:36:14
|
|
Fix bug in SSL bufferevents backed by a bev with a write high-watermarks
Original mail:
the logic that handles write watermarks in "bio_bufferevent_write"
is not working. It currently doesn't write any data if the high
watermark is *above* the amount of data to write (i.e. when there
is actually enough room available).
|
|
8ee9f9c1
|
2011-07-02T21:49:07
|
|
Fix a few warnings on OpenBSD
- redeclaration of dst_size
- arpa/inet.h requires netinet/in.h first
- don't use a local with the same name as a global - it isn't needed so
remove it
|
|
|
e9340964
|
2011-06-22T11:22:35
|
|
Fix AIX build issue with TAILQ_FOREACH definition
Reported by Lawnstein Chan.
|
|
|
e23cda3d
|
2011-06-21T10:05:28
|
|
Don't install event_rpcgen.py when --disable-libevent-install is used
|
|
|
79ff78d2
|
2011-06-16T13:19:43
|
|
Merge branch '20_kqueue_badf' into patches-2.0
|
|
|
b031adf1
|
2011-06-14T14:37:49
|
|
Don't break when building tests from git without python installed
|