Reference BSDCon'03 papers:
Jeffrey Hsu's "Reasoning about SMP in FreeBSD"
Jeff Roberson's "ULE: A Modern Scheduler for FreeBSD"
Update WIP timestamps due to ongoing progress:
Newbus
VM
Buffer Cache
VFS
Socket locking
IPv4, IPv6
Network stack infrastructure
UNIX domain sockets
Socket infrastructure
Move to done status:
Pipe IPC (VM optimizations now done)
Mutex profiling
Pipe VM optimizations
Raw IP
DIVERT sockets
IPFW2
DUMMYNET
Ethernet bridge
IP fragment queues
Routing entries
FAST_IPSEC
Add new WIP:
Peter's device driver API changes for fast interrupt handling
is no longer a future event.
- Change the subsystem locking table to use status entities. Add status to
items having no status.
- Update a few new and WIP tasks that have been completed in the past six
months or so.
- Add an item about the p_ucred locking finally being done.
- Add a WIP item about my work in the jhb_proc branch to lock the sigacts
structure and finally get the signal handling code out from under Giant.
and IPv6. Indicate IPv4, UDP, and TCP was committed into the tree
June of last year.
Add some more completed and already committed networking items:
ifaddr ref counts, syncache, the ifnet list, radix trees, and ARP.
Add some completed, not yet committed, networking work: raw IP,
divert sockets, and Unix domain protocols.
Add some networking work in progress: routing.
Add some networking todo items: IPv6.
Add a new "Subsystems and Staffing" section to identify some of the major
subsystems, their SMPng status, and current developers working on them.
This is not intended to be a complete list, I may well have left off
several substantial sub-systems, important contributions, etc. If so,
please let me know. The goal is to identify at a higher level what is
being done, what is planned to be done, and what has been done so that
developers interested in tackling a chunk of the work larger than a
small task can do so more easily.
o Move two VFS locking cleanups/tasks into the WIP sections from the
New section, update timestamps. Jeff has been actively working on
VFS locking for a while now, and has addressed sizable chunks of
these tasks.
o Add kan as an owner on the i386 lazy context switch task.
o Add a sparc64 lazy context switch task and assign to Jake.
o Remove green from VM task, leaving just alc, update timestamp,
and mark as a WIP.
when interacting with subsystems such as VFS, Sockets, and the Network
Stack, the basic framework structures and components are MP-safe.
Update the SMP task relating to this to switch it to Done status.
scheduling) for i386" from "wip" to "suspended" for now. The truth is,
the work is sitting in my p4 branch ('interrupt') but is a little stale
and requires merging to post-KSEIII world - actually, the merging itself
is done but it needs to be unbroken.
Right now, I decided to dedicate more time to helping get -CURRENT
stabilized for 5.0 instead of adding Yet Another New Feature rush-rush
for 5.0. While lightweight interrupts are a really good thing for i386,
and I do plan to finish this after 5.0 is released, I (and others) need
to look at things realistically right now and focus more on knocking
the bugs out of what we already have (KSEIII, TrustedBSD, pmap, etc.)
in time for 5.0, as well as getting performance back to sane levels
with what we already have.
I have the code, it needs fixing but has worked before and has been
discussed at the last Devel. Summit; this is now a post-5.0 feature.
- Turn the kernel linker locking task into two different ones,
locking the globals and locking down linker_file_t's.
- Mark the globals task as done.
- Mark the linker_file_t's task as WIP.
- alc did the push down of Giant into readv/writev.
- Move networking stack related items out of the main list and into the
networking list.
- Add some new entries:
- wip for turnstiles
- new for sleep queue abstraction
- new for atomic_fetchadd()
- new for a reference count API
- The cleanup of the MI abuse of cpu_critical_*() is done.
- Note the VM change salc has been comitting.
- Note that jeffr finished making malloc() and free() not require Giant.
- I've just about finished all the td_ucred and p_ucred stuff now.
- Mark all the mutex changes I committed today as done.
- Add two new WIP entries for the work alc is still doing in the VM.
- Make the eventhandler locking task more generic (don't require sx locks)
and move it to still being a wip and assign it to both Mike Smith
(who did the original locking) and to Jon Mini (who is reworking it into
its hopefully final form).
