windows: link with advapi32 and shell32 libraries

Older versions of GYP would set up the Visual Studio project to link
with these libraries by default, but this was changed in r1584 (see

windows: link with advapi32 and shell32 libraries

Older versions of GYP would set up the Visual Studio project to link
with these libraries by default, but this was changed in r1584 (see
https://codereview.chromium.org/12256017).

Closes #728

show more ...

linux: make uv_cpu_info() handle absent procfs

Return an error when reading from /proc files fails because the procfs
isn't mounted.

darwin: fix spurious uv_write2() segfault

We abuse uv_write2() to send over UDP handles to child processes.
Don't call uv__stream_fd() on those handles, it's a macro that on OS X
eva

darwin: fix spurious uv_write2() segfault

We abuse uv_write2() to send over UDP handles to child processes.
Don't call uv__stream_fd() on those handles, it's a macro that on OS X
evaluates to a function that operates on a uv_stream_t with a couple of
OS X specific fields. On other Unices it does (handle)->io_watcher.fd,
which works but only by accident.

Fixes joyent/node#4870.

show more ...

build, windows: return an error code on failure

test: fix tap output even when ok but have output

test: fix tap output check

Only report as an error when status != 0.

Stops the platform_output test from being reported as having failed
on Jenkins.

build: add distclean target to out-of-tree builds

build: make clean target remove all build artifacts

darwin: fix read from uninitialized struct kevent

In the OS X fallback code, don't read from the struct when the kevent()
syscall times out.

unix: make stream.c internal functions static

test: remove 'is root?' check

I debug tests regularly as root (because dtrace and dtruss require the
additional privileges). The 'is root?' check gets in the way more often
than it p

test: remove 'is root?' check

I debug tests regularly as root (because dtrace and dtruss require the
additional privileges). The 'is root?' check gets in the way more often
than it prevents me from doing something silly. Remove it.

show more ...

build, windows: allow override of python executable

Fixes #723.

linux, darwin: don't touch environ in uv_setup_args

Don't overwrite the environment. On OS X, the entries in the environ
table are not necessarily adjacent. It's arguably also safer for

linux, darwin: don't touch environ in uv_setup_args

Don't overwrite the environment. On OS X, the entries in the environ
table are not necessarily adjacent. It's arguably also safer for setuid
binaries.

Fixes joyent/node#4847.

show more ...

unix, windows: add common uv_udp_* error checking

windows: initialize stop_flag explicitly

The default loop lives in the bss section so it's zeroed on startup
but loops created with uv_loop_new() live on the heap and contain
random

windows: initialize stop_flag explicitly

The default loop lives in the bss section so it's zeroed on startup
but loops created with uv_loop_new() live on the heap and contain
random garbage. Initialize the stop_flag explicitly to avoid spurious
bugs.

show more ...

test: don't rewind_cursor when using tap_output

windows: fix uv_stop in ONCE and NOWAIT modes

Same as the fix in 492efb9 but this time for uv-win.

unix: make uv_stop work when embedded

* Make uv_stop() work when libuv is embedded in another event loop.

* Fix a small bug where loop->stop_flag was not reset when mode ==
UV

unix: make uv_stop work when embedded

* Make uv_stop() work when libuv is embedded in another event loop.

* Fix a small bug where loop->stop_flag was not reset when mode ==
UV_RUN_ONCE or UV_RUN_NOWAIT. The next call to uv_run() would return
immediately without doing any work.

show more ...

unix, windows: add uv_stop, stop running event loop

windows: align uv_run code with unix

build: fix misleading vcbuild.bat error message

build: turn on strict aliasing in release builds

unix: set errno in sendfile emulation

The sendfile emulation in src/unix/fs.c polls the file descriptor for
write readiness. If POLLERR or POLLHUP is set, it bails out but doesn't
se

unix: set errno in sendfile emulation

The sendfile emulation in src/unix/fs.c polls the file descriptor for
write readiness. If POLLERR or POLLHUP is set, it bails out but doesn't
set errno (hence it doesn't report a useful error code). Rectify that.

Fixes #620.

show more ...

linux: use eventfds for async handles

Use eventfds to drive async handles, fall back to regular pipes on older
kernels (pre-2.6.22).

Gives a nice boost on the async handle bench

linux: use eventfds for async handles

Use eventfds to drive async handles, fall back to regular pipes on older
kernels (pre-2.6.22).

Gives a nice boost on the async handle benchmarks. Before:

12,516,113 async events in 5.0 seconds (2,503,222/s, 1,048,576 unique
async1: 11.95 sec (83,701/sec)
async2: 11.65 sec (85,862/sec)
async4: 5.20 sec (192,154/sec)
async8: 9.97 sec (100,315/sec)
async_pummel_1: 1,000,000 callbacks in 2.56 seconds (389,919/sec)
async_pummel_2: 1,000,000 callbacks in 2.65 seconds (377,205/sec)
async_pummel_4: 1,000,000 callbacks in 2.18 seconds (457,704/sec)
async_pummel_8: 1,000,000 callbacks in 4.19 seconds (238,632/sec)

After:

16,168,081 async events in 5.0 seconds (3,233,616/s, 1,048,576 unique
async1: 11.08 sec (90,213/sec)
async2: 10.17 sec (98,297/sec)
async4: 4.81 sec (207,789/sec)
async8: 8.98 sec (111,419/sec)
async_pummel_1: 1,000,000 callbacks in 1.16 seconds (863,296/sec)
async_pummel_2: 1,000,000 callbacks in 1.45 seconds (691,459/sec)
async_pummel_4: 1,000,000 callbacks in 0.66 seconds (1,514,770/sec)
async_pummel_8: 1,000,000 callbacks in 1.42 seconds (704,549/sec)

That's a speedup from anywhere between 10% to 330%.

show more ...

unix: abstract away async pipe infrastructure

This commit lays the groundwork for the switch to eventfds on Linux.