File:  [NetBSD Developer Wiki] / wikisrc / projects / project / smp_networking.mdwn
Revision 1.5: download - view: text, annotated - select for diffs
Mon Nov 28 22:51:22 2011 UTC (5 years, 11 months ago) by jmmv
Branches: MAIN
CVS tags: HEAD
Mark atomic_pcq as done; matt@ had implemented this already three years ago.
Also avoid showing completed projects in the smp_networking list.

Reported by private mail.

    1: [[!template id=project
    2: 
    3: title="SMP Networking (aka remove the big network lock)"
    4: 
    5: contact="""
    6: [tech-kern](mailto:tech-kern@NetBSD.org),
    7: [tech-net](mailto:tech-net@NetBSD.org),
    8: [board](mailto:board@NetBSD.org),
    9: [core](mailto:core@NetBSD.org)
   10: """
   11: 
   12: category="networking"
   13: difficulty="hard"
   14: funded="The NetBSD Foundation"
   15: 
   16: description="""
   17: Traditionally, the NetBSD kernel code had been protected by a single,
   18: global lock.  This lock ensured that, on a multiprocessor system, two
   19: different threads of execution did not access the kernel concurrently and
   20: thus simplified the internal design of the kernel.  However, such design
   21: does not scale to multiprocessor machines because, effectively, the kernel
   22: is restricted to run on a single processor at any given time.
   23: 
   24: The NetBSD kernel has been modified to use fine grained locks in many of
   25: its different subsystems, achieving good performance on today's
   26: multiprocessor machines.  Unfotunately, these changes have not yet been
   27: applied to the networking code, which remains protected by the single lock.
   28: In other words: NetBSD networking has evolved to work in a uniprocessor
   29: envionment; switching it to use fine-grained locked is a hard and complex
   30: problem.
   31: 
   32: # Funding
   33: 
   34: At this time, The NetBSD Foundation is accepting project specifications to
   35: remove the single networking lock.  If you want to apply for this project,
   36: please send your proposal to the contact addresses listed above.
   37: 
   38: Due to the size of this project, your proposal does not need to cover
   39: everything to qualify for funding.  We have attempted to split the work
   40: into smaller units, and **you can submit funding applications for these
   41: smaller subtasks independently** as long as the work you deliver fits in
   42: the grand order of this project.  For example, you could send an
   43: application to make the network interfaces alone MP-friendly (see the *work
   44: plan* below).
   45: 
   46: What follows is a particular design proposal, extracted from an
   47: [original text](http://www.NetBSD.org/~matt/smpnet.html) written by
   48: [Matt Thomas](mailto:matt@NetBSD.org).  You may choose to work on this
   49: particular proposal or come up with your own.
   50: 
   51: # Tentative specification
   52: 
   53: The future of NetBSD network infrastructure has to efficiently embrace two
   54: major design criteria: Symmetric Multi-Processing (SMP) and modularity.
   55: Other design considerations include not only supporting but taking
   56: advantage of the capability of newer network devices to do packet
   57: classification, payload splitting, and even full connection offload.
   58: 
   59: You can divide the network infrastructure into 5 major components:
   60: 
   61: * Interfaces (both real devices and pseudo-devices)
   62: * Socket code
   63: * Protocols
   64: * Routing code
   65: * mbuf code.
   66: 
   67: Part of the complexity is that, due to the monolithic nature of the kernel,
   68: each layer currently feels free to call any other layer.  This makes
   69: designing a lock hierarchy difficult and likely to fail.
   70: 
   71: Part of the problem are asynchonous upcalls, among which include:
   72: 
   73: * `ifa->ifa_rtrequest` for route changes.
   74: * `pr_ctlinput` for interface events.
   75: 
   76: Another source of complexity is the large number of global variables
   77: scattered throughout the source files.  This makes putting locks around
   78: them difficult.
   79: 
   80: ## Subtasks
   81: 
   82: The proposed solution presented here include the following tasks (in no
   83: particular order) to achieve the desired goals of SMP support and
   84: modularity:
   85: 
   86: [[!map show="title" pages="projects/project/* and tagged(project) and tagged(smp_networking) and tagged(status:active)"]]
   87: 
   88: ## Work plan
   89: 
   90: Aside from the list of tasks above, the work to be done for this project
   91: can be achieved by following these steps:
   92: 
   93: 1. Move ARP out of the routing table.  See the [[nexthop_cache]] project.
   94: 
   95: 1. Make the network interfaces MP, which are one of the few users of the
   96:    big kernel lock left.  This needs to support multiple receive and
   97:    transmit queues to help reduce locking contention.  This also includes
   98:    changing more of the common interfaces to do what the `tsec` driver does
   99:    (basically do everything with softints).  This also needs to change the
  100:    `*_input` routines to use a table to do dispatch instead of the current
  101:    switch code so domain can be dynamically loaded.
  102: 
  103: 1. Collect global variables in the IP/UDP/TCP protocols into structures.
  104:    This helps the following items.
  105: 
  106: 1. Make IPV4/ICMP/IGMP/REASS MP-friendly.
  107: 
  108: 1. Make IPV6/ICMP/IGMP/ND MP-friendly.
  109: 
  110: 1. Make TCP MP-friendly.
  111: 
  112: 1. Make UDP MP-friendly.
  113: 
  114: # Radical thoughts
  115: 
  116: You should also consider the following ideas:
  117: 
  118: ## LWPs in user space do not need a kernel stack
  119: 
  120: Those pages are only being used in case the an exception happens.
  121: Interrupts are probably going to their own dedicated stack.  One could just
  122: keep a set of kernel stacks around.  Each CPU has one, when a user
  123: exception happens, that stack is assigned to the current LWP and removed as
  124: the active CPU one.  When that CPU next returns to user space, the kernel
  125: stack it was using is saved to be used for the next user exception.  The
  126: idle lwp would just use the current kernel stack.
  127: 
  128: ## LWPs waiting for kernel condition shouldn't need a kernel stack
  129: 
  130: If an LWP is waiting on a kernel condition variable, it is expecting to be
  131: inactive for some time, possibly a long time.  During this inactivity, it
  132: does not really need a kernel stack.
  133: 
  134: When the exception handler get an usermode exeception, it sets LWP
  135: restartable flag that indicates that the exception is restartable, and then
  136: services the exception as normal.  As routines are called, they can clear
  137: the LWP restartable flag as needed.  When an LWP needs to block for a long
  138: time, instead of calling `cv_wait`, it could call `cv_restart`.  If
  139: `cv_restart` returned false, the LWPs restartable flag was clear so
  140: `cv_restart` acted just like `cv_wait`.  Otherwise, the LWP and CV would
  141: have been tied together (big hand wave), the lock had been released and the
  142: routine should have returned `ERESTART`.  `cv_restart` could also wait for
  143: a small amount of time like .5 second, and only if the timeout expires.
  144: 
  145: As the stack unwinds, eventually, it would return to the last the exception
  146: handler.  The exception would see the LWP has a bound CV, save the LWP's
  147: user state into the PCB, set the LWP to sleeping, mark the lwp's stack as
  148: idle, and call the scheduler to find more work.  When called,
  149: `cpu_switchto` would notice the stack is marked idle, and detach it from
  150: the LWP.
  151: 
  152: When the condition times out or is signalled, the first LWP attached to the
  153: condition variable is marked runnable and detached from the CV.  When the
  154: `cpu_switchto` routine is called, the it would notice the lack of a stack
  155: so it would grab one, restore the trapframe, and reinvoke the exception
  156: handler.
  157: """
  158: ]]

CVSweb for NetBSD wikisrc <wikimaster@NetBSD.org> software: FreeBSD-CVSweb