--- IO-AIO/Changes	2010/01/10 20:37:33	1.221
+++ IO-AIO/Changes	2011/07/18 03:09:06	1.271
@@ -5,12 +5,98 @@
 TODO: reduce condvar fairness: schedule hot-cache-threads first?
 TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/)
 TODO: aio_fcntl, at least for file-locking
-TODO: fallocate, if it wouldn't be so useless.
-TODO: IO::AIO::mmap? aio_mincore?
+TODO: aio_mincore?
+TODO: getxattr etc.?
 
+4.0   Mon Jul 18 05:01:10 CEST 2011
+	- INCOMPATIBLE CHANGE: fork is no longer supported (indeed, it never was),
+          see FORK BEHAVIOUR in manpage for details.
+	- passes testsuite on win32 now and may actually work
+          (activestate 5.10.1 / MSVC6, YMMV).
+	- (libeio) fix a deadlock where a wakeup signal could be missed when
+          a timeout occured at the same time.
+	- (libeio) added realpath.
+        - (libeio) added fallocate.
+	- (libeio) disabling sendfile on darwin unfortunately broke the emulation.
+        - (libeio) do not acquire any locks when forking.
+        - (libeio) use fewer time() syscalls when waiting for new requests.
+
+3.93  Wed Jun 29 23:44:18 CEST 2011
+	- ECB.H WAS MISSING.
+
+3.92  Wed Jun 29 14:45:41 CEST 2011
+	- ecb.h was missing.
+
+3.91  Wed Jun 29 13:24:42 CEST 2011
+        - (libeio) work around a Linux (and likely FreeBSD and other
+          kernels) bug where sendfile would not transfer all the requested
+          bytes on large transfers, using a heuristic.
+        - buggy sendfile caused aio_move/copy to sometimes fail for big
+          files (fortunately it checks that the whole file has been
+          transferred...)
+        - use libecb for higher performance and higher portability.
+        - (libeio) disable sendfile on darwin, it's too broken.
+        - disable fork tests on !linux, as only linux supports mixing
+          pthread and fork in perl.
+        - document the fact that fork doesn't work anymore when using
+          this module, on anything !GNU/Linux.
+        - increase timeout in t/04_fork.t, as too many CPAN-tester setups
+          run on a 0.1MHz cpu. Or so.
+
+3.9  Fri May 27 02:43:47 CEST 2011
+        - (libeio) fix memory corruption in aio_readdirx for the flags
+          combination READDIR_STAT_ORDER | READDIR_DIRS_FIRST.
+        - add lots of newer POSIX and GNU/Linux-specific open
+          flags.
+
+3.8  Sun Mar 27 12:25:33 CEST 2011
+	- use nonstandard but maybe-working-on-bsd fork technique.
+	- support a max_idle value of 0.
+	- support setting of idle timeout value (IO::AIO::idle_timeout).
+
+3.72 Fri Feb 11 04:25:38 CET 2011
+	- use _POSIX_MEMLOCK_RANGE to detect mlock/munlock.
+        - aio_mknod always used a dev_t value of 0.
+        - new treescan option: --grep.
+        - add more S_IF macros, and major/minor/makedev "macros".
+
+3.71 Thu Dec 30 08:18:46 CET 2010
+	- the numerical result value passed to callbacks did not stringify
+          correctly, due to internal reuse and failure to reset the sv flags.
+	- actually test for posix_[mf]advise, as at least uClibc defines
+          _POSIX_ADVISORY_INFO without actually having any of the required
+          funcitonality. ugh.
+
+3.7  Mon Nov  1 23:00:34 CET 2010
+        - implement/add madvise, mmap, munmap, aio_mlockall, munlockall,
+          aio_mlock, munlock, msync and mtouch to @EXPORT_OK.
+        - document the sad state of affairs w.r.t. pthread on many bsds.
+	- do not enable mmap on systems without _POSIX_MAPPED_FILES
+          (openbsd 4.8).
+        - do not leak memory in IO::AIO::mmap when the scalar already
+          had string-data.
+	- add O_RDWR, O_APPEND and O_EXCL symbols and semi-document
+          them.
+        - cache the result IV, for a minor speedup in the common case.
+        - croak when an mmapped-scalar changes location, to detect
+          user-errors better.
+        - fix aio_readlink prototype.
+
+3.65 Wed Mar 31 02:45:05 CEST 2010
+	- actually use PATH_MAX instead of NAME_MAX for readlink, as to not
+          cut off long pathnames in aio_readlink (based on patch by
+          Rasmus Andersson).
+	- a double fork partially killed the event pipe (great testcase
+          by dormando). affects IO::AIO, BDB and Async::Interrupt.
+        - suck steve's dick and rename our symbols to avoid colliding
+          with nonstandard identifier spam on the broken os x pseudo-os.
+          affects IO::AIO and BDB.
+
+3.6  Mon Jan 11 00:43:39 CET 2010
 	- (libeio) more fixes for the freebsd/apple sendfile - broken by
           manpage standards, but apparently correct accoridng to actual
           kernel sources.
+        - add IO::AIO::mmap/munmap support.
         - add IO::AIO::m(un)lockall support.
         - clean up manpage.