ia64/linux-2.6.18-xen.hg

view Documentation/RCU/RTFP.txt @ 854:950b9eb27661

usbback: fix urb interval value for interrupt urbs.

Signed-off-by: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com>
author Keir Fraser <keir.fraser@citrix.com>
date Mon Apr 06 13:51:20 2009 +0100 (2009-04-06)
parents 831230e53067
children
line source
1 Read the F-ing Papers!
4 This document describes RCU-related publications, and is followed by
5 the corresponding bibtex entries. A number of the publications may
6 be found at http://www.rdrop.com/users/paulmck/RCU/.
8 The first thing resembling RCU was published in 1980, when Kung and Lehman
9 [Kung80] recommended use of a garbage collector to defer destruction
10 of nodes in a parallel binary search tree in order to simplify its
11 implementation. This works well in environments that have garbage
12 collectors, but current production garbage collectors incur significant
13 read-side overhead.
15 In 1982, Manber and Ladner [Manber82,Manber84] recommended deferring
16 destruction until all threads running at that time have terminated, again
17 for a parallel binary search tree. This approach works well in systems
18 with short-lived threads, such as the K42 research operating system.
19 However, Linux has long-lived tasks, so more is needed.
21 In 1986, Hennessy, Osisek, and Seigh [Hennessy89] introduced passive
22 serialization, which is an RCU-like mechanism that relies on the presence
23 of "quiescent states" in the VM/XA hypervisor that are guaranteed not
24 to be referencing the data structure. However, this mechanism was not
25 optimized for modern computer systems, which is not surprising given
26 that these overheads were not so expensive in the mid-80s. Nonetheless,
27 passive serialization appears to be the first deferred-destruction
28 mechanism to be used in production. Furthermore, the relevant patent has
29 lapsed, so this approach may be used in non-GPL software, if desired.
30 (In contrast, use of RCU is permitted only in software licensed under
31 GPL. Sorry!!!)
33 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
34 were reading a given data structure permitted deferred free to operate
35 in the presence of non-terminating threads. However, this explicit
36 tracking imposes significant read-side overhead, which is undesirable
37 in read-mostly situations. This algorithm does take pains to avoid
38 write-side contention and parallelize the other write-side overheads by
39 providing a fine-grained locking design, however, it would be interesting
40 to see how much of the performance advantage reported in 1990 remains
41 in 2004.
43 At about this same time, Adams [Adams91] described ``chaotic relaxation'',
44 where the normal barriers between successive iterations of convergent
45 numerical algorithms are relaxed, so that iteration $n$ might use
46 data from iteration $n-1$ or even $n-2$. This introduces error,
47 which typically slows convergence and thus increases the number of
48 iterations required. However, this increase is sometimes more than made
49 up for by a reduction in the number of expensive barrier operations,
50 which are otherwise required to synchronize the threads at the end
51 of each iteration. Unfortunately, chaotic relaxation requires highly
52 structured data, such as the matrices used in scientific programs, and
53 is thus inapplicable to most data structures in operating-system kernels.
55 In 1993, Jacobson [Jacobson93] verbally described what is perhaps the
56 simplest deferred-free technique: simply waiting a fixed amount of time
57 before freeing blocks awaiting deferred free. Jacobson did not describe
58 any write-side changes he might have made in this work using SGI's Irix
59 kernel. Aju John published a similar technique in 1995 [AjuJohn95].
60 This works well if there is a well-defined upper bound on the length of
61 time that reading threads can hold references, as there might well be in
62 hard real-time systems. However, if this time is exceeded, perhaps due
63 to preemption, excessive interrupts, or larger-than-anticipated load,
64 memory corruption can ensue, with no reasonable means of diagnosis.
65 Jacobson's technique is therefore inappropriate for use in production
66 operating-system kernels, except when such kernels can provide hard
67 real-time response guarantees for all operations.
69 Also in 1995, Pu et al. [Pu95a] applied a technique similar to that of Pugh's
70 read-side-tracking to permit replugging of algorithms within a commercial
71 Unix operating system. However, this replugging permitted only a single
72 reader at a time. The following year, this same group of researchers
73 extended their technique to allow for multiple readers [Cowan96a].
74 Their approach requires memory barriers (and thus pipeline stalls),
75 but reduces memory latency, contention, and locking overheads.
77 1995 also saw the first publication of DYNIX/ptx's RCU mechanism
78 [Slingwine95], which was optimized for modern CPU architectures,
79 and was successfully applied to a number of situations within the
80 DYNIX/ptx kernel. The corresponding conference paper appeared in 1998
81 [McKenney98].
83 In 1999, the Tornado and K42 groups described their "generations"
84 mechanism, which quite similar to RCU [Gamsa99]. These operating systems
85 made pervasive use of RCU in place of "existence locks", which greatly
86 simplifies locking hierarchies.
88 2001 saw the first RCU presentation involving Linux [McKenney01a]
89 at OLS. The resulting abundance of RCU patches was presented the
90 following year [McKenney02a], and use of RCU in dcache was first
91 described that same year [Linder02a].
93 Also in 2002, Michael [Michael02b,Michael02a] presented "hazard-pointer"
94 techniques that defer the destruction of data structures to simplify
95 non-blocking synchronization (wait-free synchronization, lock-free
96 synchronization, and obstruction-free synchronization are all examples of
97 non-blocking synchronization). In particular, this technique eliminates
98 locking, reduces contention, reduces memory latency for readers, and
99 parallelizes pipeline stalls and memory latency for writers. However,
100 these techniques still impose significant read-side overhead in the
101 form of memory barriers. Researchers at Sun worked along similar lines
102 in the same timeframe [HerlihyLM02,HerlihyLMS03]. These techniques
103 can be thought of as inside-out reference counts, where the count is
104 represented by the number of hazard pointers referencing a given data
105 structure (rather than the more conventional counter field within the
106 data structure itself).
108 In 2003, the K42 group described how RCU could be used to create
109 hot-pluggable implementations of operating-system functions. Later that
110 year saw a paper describing an RCU implementation of System V IPC
111 [Arcangeli03], and an introduction to RCU in Linux Journal [McKenney03a].
113 2004 has seen a Linux-Journal article on use of RCU in dcache
114 [McKenney04a], a performance comparison of locking to RCU on several
115 different CPUs [McKenney04b], a dissertation describing use of RCU in a
116 number of operating-system kernels [PaulEdwardMcKenneyPhD], a paper
117 describing how to make RCU safe for soft-realtime applications [Sarma04c],
118 and a paper describing SELinux performance with RCU [JamesMorris04b].
120 2005 has seen further adaptation of RCU to realtime use, permitting
121 preemption of RCU realtime critical sections [PaulMcKenney05a,
122 PaulMcKenney05b].
124 Bibtex Entries
126 @article{Kung80
127 ,author="H. T. Kung and Q. Lehman"
128 ,title="Concurrent Maintenance of Binary Search Trees"
129 ,Year="1980"
130 ,Month="September"
131 ,journal="ACM Transactions on Database Systems"
132 ,volume="5"
133 ,number="3"
134 ,pages="354-382"
135 }
137 @techreport{Manber82
138 ,author="Udi Manber and Richard E. Ladner"
139 ,title="Concurrency Control in a Dynamic Search Structure"
140 ,institution="Department of Computer Science, University of Washington"
141 ,address="Seattle, Washington"
142 ,year="1982"
143 ,number="82-01-01"
144 ,month="January"
145 ,pages="28"
146 }
148 @article{Manber84
149 ,author="Udi Manber and Richard E. Ladner"
150 ,title="Concurrency Control in a Dynamic Search Structure"
151 ,Year="1984"
152 ,Month="September"
153 ,journal="ACM Transactions on Database Systems"
154 ,volume="9"
155 ,number="3"
156 ,pages="439-455"
157 }
159 @techreport{Hennessy89
160 ,author="James P. Hennessy and Damian L. Osisek and Joseph W. {Seigh II}"
161 ,title="Passive Serialization in a Multitasking Environment"
162 ,institution="US Patent and Trademark Office"
163 ,address="Washington, DC"
164 ,year="1989"
165 ,number="US Patent 4,809,168 (lapsed)"
166 ,month="February"
167 ,pages="11"
168 }
170 @techreport{Pugh90
171 ,author="William Pugh"
172 ,title="Concurrent Maintenance of Skip Lists"
173 ,institution="Institute of Advanced Computer Science Studies, Department of Computer Science, University of Maryland"
174 ,address="College Park, Maryland"
175 ,year="1990"
176 ,number="CS-TR-2222.1"
177 ,month="June"
178 }
180 @Book{Adams91
181 ,Author="Gregory R. Adams"
182 ,title="Concurrent Programming, Principles, and Practices"
183 ,Publisher="Benjamin Cummins"
184 ,Year="1991"
185 }
187 @unpublished{Jacobson93
188 ,author="Van Jacobson"
189 ,title="Avoid Read-Side Locking Via Delayed Free"
190 ,year="1993"
191 ,month="September"
192 ,note="Verbal discussion"
193 }
195 @Conference{AjuJohn95
196 ,Author="Aju John"
197 ,Title="Dynamic vnodes -- Design and Implementation"
198 ,Booktitle="{USENIX Winter 1995}"
199 ,Publisher="USENIX Association"
200 ,Month="January"
201 ,Year="1995"
202 ,pages="11-23"
203 ,Address="New Orleans, LA"
204 }
206 @techreport{Slingwine95
207 ,author="John D. Slingwine and Paul E. McKenney"
208 ,title="Apparatus and Method for Achieving Reduced Overhead Mutual
209 Exclusion and Maintaining Coherency in a Multiprocessor System
210 Utilizing Execution History and Thread Monitoring"
211 ,institution="US Patent and Trademark Office"
212 ,address="Washington, DC"
213 ,year="1995"
214 ,number="US Patent 5,442,758 (contributed under GPL)"
215 ,month="August"
216 }
218 @techreport{Slingwine97
219 ,author="John D. Slingwine and Paul E. McKenney"
220 ,title="Method for maintaining data coherency using thread
221 activity summaries in a multicomputer system"
222 ,institution="US Patent and Trademark Office"
223 ,address="Washington, DC"
224 ,year="1997"
225 ,number="US Patent 5,608,893 (contributed under GPL)"
226 ,month="March"
227 }
229 @techreport{Slingwine98
230 ,author="John D. Slingwine and Paul E. McKenney"
231 ,title="Apparatus and method for achieving reduced overhead
232 mutual exclusion and maintaining coherency in a multiprocessor
233 system utilizing execution history and thread monitoring"
234 ,institution="US Patent and Trademark Office"
235 ,address="Washington, DC"
236 ,year="1998"
237 ,number="US Patent 5,727,209 (contributed under GPL)"
238 ,month="March"
239 }
241 @Conference{McKenney98
242 ,Author="Paul E. McKenney and John D. Slingwine"
243 ,Title="Read-Copy Update: Using Execution History to Solve Concurrency
244 Problems"
245 ,Booktitle="{Parallel and Distributed Computing and Systems}"
246 ,Month="October"
247 ,Year="1998"
248 ,pages="509-518"
249 ,Address="Las Vegas, NV"
250 }
252 @Conference{Gamsa99
253 ,Author="Ben Gamsa and Orran Krieger and Jonathan Appavoo and Michael Stumm"
254 ,Title="Tornado: Maximizing Locality and Concurrency in a Shared Memory
255 Multiprocessor Operating System"
256 ,Booktitle="{Proceedings of the 3\textsuperscript{rd} Symposium on
257 Operating System Design and Implementation}"
258 ,Month="February"
259 ,Year="1999"
260 ,pages="87-100"
261 ,Address="New Orleans, LA"
262 }
264 @techreport{Slingwine01
265 ,author="John D. Slingwine and Paul E. McKenney"
266 ,title="Apparatus and method for achieving reduced overhead
267 mutual exclusion and maintaining coherency in a multiprocessor
268 system utilizing execution history and thread monitoring"
269 ,institution="US Patent and Trademark Office"
270 ,address="Washington, DC"
271 ,year="2001"
272 ,number="US Patent 5,219,690 (contributed under GPL)"
273 ,month="April"
274 }
276 @Conference{McKenney01a
277 ,Author="Paul E. McKenney and Jonathan Appavoo and Andi Kleen and
278 Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni"
279 ,Title="Read-Copy Update"
280 ,Booktitle="{Ottawa Linux Symposium}"
281 ,Month="July"
282 ,Year="2001"
283 ,note="Available:
284 \url{http://www.linuxsymposium.org/2001/abstracts/readcopy.php}
285 \url{http://www.rdrop.com/users/paulmck/rclock/rclock_OLS.2001.05.01c.pdf}
286 [Viewed June 23, 2004]"
287 annotation="
288 Described RCU, and presented some patches implementing and using it in
289 the Linux kernel.
290 "
291 }
293 @Conference{Linder02a
294 ,Author="Hanna Linder and Dipankar Sarma and Maneesh Soni"
295 ,Title="Scalability of the Directory Entry Cache"
296 ,Booktitle="{Ottawa Linux Symposium}"
297 ,Month="June"
298 ,Year="2002"
299 ,pages="289-300"
300 }
302 @Conference{McKenney02a
303 ,Author="Paul E. McKenney and Dipankar Sarma and
304 Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
305 ,Title="Read-Copy Update"
306 ,Booktitle="{Ottawa Linux Symposium}"
307 ,Month="June"
308 ,Year="2002"
309 ,pages="338-367"
310 ,note="Available:
311 \url{http://www.linux.org.uk/~ajh/ols2002_proceedings.pdf.gz}
312 [Viewed June 23, 2004]"
313 }
315 @article{Appavoo03a
316 ,author="J. Appavoo and K. Hui and C. A. N. Soules and R. W. Wisniewski and
317 D. M. {Da Silva} and O. Krieger and M. A. Auslander and D. J. Edelsohn and
318 B. Gamsa and G. R. Ganger and P. McKenney and M. Ostrowski and
319 B. Rosenburg and M. Stumm and J. Xenidis"
320 ,title="Enabling Autonomic Behavior in Systems Software With Hot Swapping"
321 ,Year="2003"
322 ,Month="January"
323 ,journal="IBM Systems Journal"
324 ,volume="42"
325 ,number="1"
326 ,pages="60-76"
327 }
329 @Conference{Arcangeli03
330 ,Author="Andrea Arcangeli and Mingming Cao and Paul E. McKenney and
331 Dipankar Sarma"
332 ,Title="Using Read-Copy Update Techniques for {System V IPC} in the
333 {Linux} 2.5 Kernel"
334 ,Booktitle="Proceedings of the 2003 USENIX Annual Technical Conference
335 (FREENIX Track)"
336 ,Publisher="USENIX Association"
337 ,year="2003"
338 ,month="June"
339 ,pages="297-310"
340 }
342 @article{McKenney03a
343 ,author="Paul E. McKenney"
344 ,title="Using {RCU} in the {Linux} 2.5 Kernel"
345 ,Year="2003"
346 ,Month="October"
347 ,journal="Linux Journal"
348 ,volume="1"
349 ,number="114"
350 ,pages="18-26"
351 }
353 @techreport{Friedberg03a
354 ,author="Stuart A. Friedberg"
355 ,title="Lock-Free Wild Card Search Data Structure and Method"
356 ,institution="US Patent and Trademark Office"
357 ,address="Washington, DC"
358 ,year="2003"
359 ,number="US Patent 6,662,184 (contributed under GPL)"
360 ,month="December"
361 ,pages="112"
362 }
364 @article{McKenney04a
365 ,author="Paul E. McKenney and Dipankar Sarma and Maneesh Soni"
366 ,title="Scaling dcache with {RCU}"
367 ,Year="2004"
368 ,Month="January"
369 ,journal="Linux Journal"
370 ,volume="1"
371 ,number="118"
372 ,pages="38-46"
373 }
375 @Conference{McKenney04b
376 ,Author="Paul E. McKenney"
377 ,Title="{RCU} vs. Locking Performance on Different {CPUs}"
378 ,Booktitle="{linux.conf.au}"
379 ,Month="January"
380 ,Year="2004"
381 ,Address="Adelaide, Australia"
382 ,note="Available:
383 \url{http://www.linux.org.au/conf/2004/abstracts.html#90}
384 \url{http://www.rdrop.com/users/paulmck/rclock/lockperf.2004.01.17a.pdf}
385 [Viewed June 23, 2004]"
386 }
388 @phdthesis{PaulEdwardMcKenneyPhD
389 ,author="Paul E. McKenney"
390 ,title="Exploiting Deferred Destruction:
391 An Analysis of Read-Copy-Update Techniques
392 in Operating System Kernels"
393 ,school="OGI School of Science and Engineering at
394 Oregon Health and Sciences University"
395 ,year="2004"
396 ,note="Available:
397 \url{http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf}
398 [Viewed October 15, 2004]"
399 }
401 @Conference{Sarma04c
402 ,Author="Dipankar Sarma and Paul E. McKenney"
403 ,Title="Making RCU Safe for Deep Sub-Millisecond Response Realtime Applications"
404 ,Booktitle="Proceedings of the 2004 USENIX Annual Technical Conference
405 (FREENIX Track)"
406 ,Publisher="USENIX Association"
407 ,year="2004"
408 ,month="June"
409 ,pages="182-191"
410 }
412 @unpublished{JamesMorris04b
413 ,Author="James Morris"
414 ,Title="Recent Developments in {SELinux} Kernel Performance"
415 ,month="December"
416 ,year="2004"
417 ,note="Available:
418 \url{http://www.livejournal.com/users/james_morris/2153.html}
419 [Viewed December 10, 2004]"
420 }
422 @unpublished{PaulMcKenney05a
423 ,Author="Paul E. McKenney"
424 ,Title="{[RFC]} {RCU} and {CONFIG\_PREEMPT\_RT} progress"
425 ,month="May"
426 ,year="2005"
427 ,note="Available:
428 \url{http://lkml.org/lkml/2005/5/9/185}
429 [Viewed May 13, 2005]"
430 ,annotation="
431 First publication of working lock-based deferred free patches
432 for the CONFIG_PREEMPT_RT environment.
433 "
434 }
436 @conference{PaulMcKenney05b
437 ,Author="Paul E. McKenney and Dipankar Sarma"
438 ,Title="Towards Hard Realtime Response from the Linux Kernel on SMP Hardware"
439 ,Booktitle="linux.conf.au 2005"
440 ,month="April"
441 ,year="2005"
442 ,address="Canberra, Australia"
443 ,note="Available:
444 \url{http://www.rdrop.com/users/paulmck/RCU/realtimeRCU.2005.04.23a.pdf}
445 [Viewed May 13, 2005]"
446 ,annotation="
447 Realtime turns into making RCU yet more realtime friendly.
448 "
449 }