Date | Commit message (Collapse) |
|
It's slow, but at least it works.
|
|
No reason to have an extra method. This also speeds up
the multi-listener case for tcp_listener_stats since it
avoids expensive sendmsg() syscalls.
|
|
|
|
netlink is fast and predictable in response times, so permitting
interrupts would just complicate things and lead to errors.
|
|
Fewer places to check for errors, we think.
|
|
Be stricter about invalid inputs.
|
|
This is a work-in-progress and will probably be modified
before the next release.
|
|
64-bit counters are unnecessarily large for tracking
active or queued connections until we have IP_ROFLSCALE
support :>
|
|
Oops :x
|
|
Too hard to maintain.
|
|
We can't have negative values
|
|
We don't care for this address.
|
|
Oops, strings are always true :x
|
|
We're going to experiment with something...
|
|
Yes we love Linux more than other systems :>
|
|
OK, not to non-Unix but I'll never care :>
|
|
It's useful, yes.
|
|
raindrops_ext.c never existed :o
|
|
"Advanced" GCs are typically less aggressive and typically allow
much more memory to be used.
|
|
Oops, it could give the GC problems.
|
|
Raindrops is designed to work with forking servers after all.
|
|
This allows limited resizing of the Raindrops memory
area since we always over-allocate due to the required
page aligment for mmap.
It would be nice if mremap() worked with MAP_SHARED,
but it does not and triggers a bus error when attempting
to access the new area.
ref: https://bugzilla.kernel.org/show_bug.cgi?id=8691
|
|
Of course, RDoc doesn't know quantity vs quality :)
|
|
Oops, don't let GC close our listener before Unicorn
can inherit it.
|
|
It seems nice
|
|
POSIX message queues needs native threads to function.
|
|
fcntl() locks are per-process, so we also need something
to protect individual threads within a process from stepping
over each other.
|
|
This is only useful when looped inside screen or something
similar...
|
|
USR1 dumps histograms, and USR2 resets the counters
|
|
No need to make eyes drift :)
|
|
Seems to basically work
|
|
|
|
|
|
|
|
They are useful
|
|
UGH...
|
|
It's more complete for people on ancient systems where
"struct tcp_info" is defined in netinet/tcp and missing
tcp_ircv_rtt, tcpi_rcv_space and tcpi_total_retrans.
|
|
Matches my common usage patterns
|
|
Sometimes sleeping for one second between reads is too much...
|
|
This can now be used to monitor UNIX domain socket queues, too.
|
|
We want any pipe readers to see this immediately
|
|
People actually need to load modules manually on older kernels :<
|
|
It's easier to find this way.
|
|
Oops!
|
|
We need to do this for apps that depend on things like the
sendfile() optimizations in Rainbows!
|
|
No need for people to download glibc to get the LGPL :>
|
|
This is the highest number a counter may be incremented to
before it overflows.
|
|
This returns a Raindrops::TCP_Info object
that wraps a tcp_info struct.
|
|
We might reuse that for other code...
|
|
We'll be doing more Linux-only stuff
|