Resource Kernels: Linux/RK
Raj Rajkumar, Kanaka Juvva, Anastasio Molano and Shui Oikawa, “Resource Kernels: A Resource-Centric Approach to Real-Time Systems”, In Proceedings of the SPIE/ACM Conference on Multimedia Computing and Networking, January 1998.
Before we start…
• Unix Scheduling– Mainly for time-sharing– Multilevel feedback queue– Each queue applies Round Robin
scheduling– Priority varies dynamically, e.g., aging
Linux Scheduling
• Provides RT-POSIX interface• Fixed priority real-time scheduling classes
– SCHED_FIFO– SCHED_RR
• 100 priority levels• Timesharing in SCHED_OTHER• Relatively new preemptive Linux kernels• Enough support for real-time applications?
Extend Linux for real-time support
• Why extend Linux?– A large user base– Open-source– But, is the Linux footprint small enough
for embedded applications?
Resource Kernel• A Kernel that provides to applications Timely,
Guaranteed, and Enforced access to System Resources
• Allows Applications to specify only their Resource Demands – leaving the Kernel to satisfy those Demands using
hidden management schemesTask 1
Task 2
Task 3
Resource SetResource Set
Rsv 1 Rsv 2
Rsv 3
DiskBWNetBW
CPU
Reservation Parameters
“T”: Period (1/f)“C”: Execution time
within period“D”: Deadline within
period
Source: Dr. Rajkumar at CMU
Linux/RK Architecture
Hardware
ResourceKernel Linux
KernelKernel
User-Level
LoadableKernelModule
LinuxProcess
LinuxProcess
LinuxProcess
Kernel
Source: Dr. Rajkumar at CMU
• Open source Linux project: – www.fsmlabs.com – http://tldp.org/HOWTO/RTLinux-HOWTO.html
• Supports x86, PowerPC, Alpha
• Available as a patch to the regular Linux kernel
• Provides an RT API for developers
• Runs Linux kernel as lowest priority process
Diversion: RTLinux
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
Linux Kernel
System libraries
Device drivers Linux kernel
Hardware
I/O Hardware Interrupts
User Processes
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
RTLinux Kernel
Hardware
System libraries
Device drivers Linux kernel
I/O Software Interrupts
User Processes
RTLinux Plug-in
Real Time Tasks
RT-Scheduler
I/O Hardware Interrupts
Linux is executed in the background
Direct h/w access
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
Linux Kernel: code perspective
Linux Monolithic kernel core
M1
M2
M3
M4
Kernel Loadable M
odules
RAM DISK
Module M2 service (system call)
User
Process
M2
THE controller
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
RTLinux Kernel: code perspective
Linux Monolithic kernel core
RTM2
RTM3
M1
M2
Kernel Loadable M
odules
RAMDISK
Load RT core
RT Load command
RT-Core Module
RT core
M3
THE controller
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
Getting RTLinux ready• Configure and compile a fresh Linux kernel
(2.4.29)– Download the kernel fromhttp://www.kernel.org/pub/linux/kernel/v2.4/linux-2.4.29.tar.gz
• Patch the RTLinux to the Linux kernel
• Recompile the kernel and reboot the system into the new kernel
• Configure the RTLinux kernel and compile it
Source: Cpre 458/558 by Dr. Manimaran at Iowa State University
Linux/RK AbstractionsCMU’s Linux/RK supports several abstractions and primitives
for real-time scheduling of processes with real-time and QoS requirements:
• Resource reservations with latency guarantees– CPU cycles– Network bandwidth– Disk bandwidth
• Support for periodic tasks.• Support for 256 real-time fixed-priority levels. • High-resolution timers and clocks. • Bounding of priority inversion during synchronization
operations– Also works with reservations (reservation inheritance,
etc.) • Wiring down of memory pages.
Source: Dr. Rajkumar at CMU
Reservation Types
• Hard reservation: On depletion, it cannot be scheduled until it is replenished
• Firm reservation: On depletion, it can be scheduled if no other undepleted reservation or unreserved threads are ready to run
• Soft reservation: On depletion, it can be scheduled with other unreserved threads and depleted reservations
Hard reservation
Firm reservation
Soft reservation
Scheduling & Admission Control
• Each reservation receives a fixed priority according to period (RMS) or deadline (DMS)
• Admission control overhead
Disk Scheduling• Traditional RT systems avoided to use disk
– Unpredictable latencies– Disk access requests should be scheduled in conjunction
with the processor scheduling• Multiple resource problem with deadlines is NP-complete
[5]
• Disk bandwidth reservations in addition to CPU cycle reservations– EDF: Pick the reservation with the earliest deadline
• Immediate preemption of a disk access is impossible• EDF is not optimal in a non-preemptive model• A lot of disk head movements
– EDF + Just-in-time scheduling• High priority tasks may finish early• Exploit “slack” to serve requests close to the current head
position, similar to SCAN
Workload with both CPU and Disk requirements
Commercialized Linux/RK: TimeSys Linux
• Resource kernel and QoS Support– guaranteed, timely and enforced
access to CPU cycles and network bandwidth
• SMP support with QoS Reservations• Fully preemptive kernel• Fixed-priority scheduling (POSIX-
compliant)• High-resolution timer and clock support
(microsecond resolution)• Periodic processes• Message queues• Priority inheritance and priority ceiling
protocol emulation support to avoid unbounded priority inversion TimeSys Linux/RT
Real-Time Java
RT-App
App App
RT-App
TimeSys Corporation Source: Dr. Rajkumar at CMU
TimeSys Linux• TimeSys Linux/GPL
– Basic TimeSys Linux kernel– Full preemption at the kernel level, prioritized interrupt handlers,
unlimited priorities, ... • TimeSys Linux/Real-time
– Support priority inheritance and a POSIX-based high-resolution timer API
• TimeSys Linux/CPU – Support CPU reservation, which gives a thread, process, or process
group exclusive use of the CPU. • TimeSys Linux/Net
– Support network bandwidth reservation to guarantee that your thread or process will get the bandwidth it requires, regardless of network activity in other processes
• TimeSys Linux GPL: Downloadable from sourceforge.net/projects/timesysgpl • TimeSys Linux Install mini HOWTO:
http://doc.ece.uci.edu/~tharmon/files/TimeSys-Linux-Install-mini-HOWTO.html
#Priority levels and EDF
• EDF is hard to implement because most operating systems only support a fixed number of priority levels (typically <= 256)
• Deadline scheduling, e.g., EDF, can be better fixed priority scheduling which is oblivious to deadlines– Example: Consider the following scenario in
RMS DH
DL
TH
TL
Fixed priority vs. Dynamic priority
• Fixed priority– Supported by most kernels– Simple & little overhead– Low utilization bound
• RMS: 0.69
• Dynamic priority– Deadline is the first class citizen– High utilization bound: 1 in EDF– Limited priority levels in most kernels– More complex; High overhead
Average kernel preemption latency comparison
OS Average latency (us)
Average latency (us)
Linux < 10,000 100,000
Linux with preemptive kernel
< 1,000 100,000
TimeSys Linux/GPL
< 50 1,000
TimeSys Linux/Real-Time
< 10 51
Source: http://linuxdevices.com/articles/AT6106723802.html
Others
• Unix-based: QNX, LynxOS, …• Proprietary: pSOS, VxWorks, VRTX, …• More recently
– eCos– L4– μcOS-II
Announcement: Midterm Exam
• Midterm Exam on Oct. 12, 2006 for both on-campus and EngiNet students
• Format: In-Class, Closed-book, Closed-note exam
• Study Real-Time Scheduling, Synchronization, and Real-Time Operating Systems covered up to today’s lecture
• Focus on my lecture slides (supplemented by the papers on the reading list)
• From Oct. 2, we will discuss RTDB – Read paper [D1] in the reading list