Commit | Line | Data |
---|---|---|
8f0aa2f2 DH |
1 | ==================================== |
2 | SLOW WORK ITEM EXECUTION THREAD POOL | |
3 | ==================================== | |
4 | ||
5 | By: David Howells <dhowells@redhat.com> | |
6 | ||
7 | The slow work item execution thread pool is a pool of threads for performing | |
8 | things that take a relatively long time, such as making mkdir calls. | |
9 | Typically, when processing something, these items will spend a lot of time | |
10 | blocking a thread on I/O, thus making that thread unavailable for doing other | |
11 | work. | |
12 | ||
13 | The standard workqueue model is unsuitable for this class of work item as that | |
14 | limits the owner to a single thread or a single thread per CPU. For some | |
15 | tasks, however, more threads - or fewer - are required. | |
16 | ||
17 | There is just one pool per system. It contains no threads unless something | |
18 | wants to use it - and that something must register its interest first. When | |
19 | the pool is active, the number of threads it contains is dynamic, varying | |
20 | between a maximum and minimum setting, depending on the load. | |
21 | ||
22 | ||
23 | ==================== | |
24 | CLASSES OF WORK ITEM | |
25 | ==================== | |
26 | ||
27 | This pool support two classes of work items: | |
28 | ||
29 | (*) Slow work items. | |
30 | ||
31 | (*) Very slow work items. | |
32 | ||
33 | The former are expected to finish much quicker than the latter. | |
34 | ||
35 | An operation of the very slow class may do a batch combination of several | |
36 | lookups, mkdirs, and a create for instance. | |
37 | ||
38 | An operation of the ordinarily slow class may, for example, write stuff or | |
39 | expand files, provided the time taken to do so isn't too long. | |
40 | ||
41 | Operations of both types may sleep during execution, thus tying up the thread | |
42 | loaned to it. | |
43 | ||
6b8268b1 JA |
44 | A further class of work item is available, based on the slow work item class: |
45 | ||
46 | (*) Delayed slow work items. | |
47 | ||
48 | These are slow work items that have a timer to defer queueing of the item for | |
49 | a while. | |
50 | ||
8f0aa2f2 DH |
51 | |
52 | THREAD-TO-CLASS ALLOCATION | |
53 | -------------------------- | |
54 | ||
55 | Not all the threads in the pool are available to work on very slow work items. | |
56 | The number will be between one and one fewer than the number of active threads. | |
57 | This is configurable (see the "Pool Configuration" section). | |
58 | ||
59 | All the threads are available to work on ordinarily slow work items, but a | |
60 | percentage of the threads will prefer to work on very slow work items. | |
61 | ||
62 | The configuration ensures that at least one thread will be available to work on | |
63 | very slow work items, and at least one thread will be available that won't work | |
64 | on very slow work items at all. | |
65 | ||
66 | ||
67 | ===================== | |
68 | USING SLOW WORK ITEMS | |
69 | ===================== | |
70 | ||
71 | Firstly, a module or subsystem wanting to make use of slow work items must | |
72 | register its interest: | |
73 | ||
3d7a641e | 74 | int ret = slow_work_register_user(struct module *module); |
8f0aa2f2 | 75 | |
3d7a641e DH |
76 | This will return 0 if successful, or a -ve error upon failure. The module |
77 | pointer should be the module interested in using this facility (almost | |
78 | certainly THIS_MODULE). | |
8f0aa2f2 DH |
79 | |
80 | ||
81 | Slow work items may then be set up by: | |
82 | ||
83 | (1) Declaring a slow_work struct type variable: | |
84 | ||
85 | #include <linux/slow-work.h> | |
86 | ||
87 | struct slow_work myitem; | |
88 | ||
89 | (2) Declaring the operations to be used for this item: | |
90 | ||
91 | struct slow_work_ops myitem_ops = { | |
92 | .get_ref = myitem_get_ref, | |
93 | .put_ref = myitem_put_ref, | |
94 | .execute = myitem_execute, | |
95 | }; | |
96 | ||
97 | [*] For a description of the ops, see section "Item Operations". | |
98 | ||
99 | (3) Initialising the item: | |
100 | ||
101 | slow_work_init(&myitem, &myitem_ops); | |
102 | ||
6b8268b1 JA |
103 | or: |
104 | ||
105 | delayed_slow_work_init(&myitem, &myitem_ops); | |
106 | ||
8f0aa2f2 DH |
107 | or: |
108 | ||
109 | vslow_work_init(&myitem, &myitem_ops); | |
110 | ||
111 | depending on its class. | |
112 | ||
113 | A suitably set up work item can then be enqueued for processing: | |
114 | ||
115 | int ret = slow_work_enqueue(&myitem); | |
116 | ||
117 | This will return a -ve error if the thread pool is unable to gain a reference | |
6b8268b1 JA |
118 | on the item, 0 otherwise, or (for delayed work): |
119 | ||
120 | int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay); | |
8f0aa2f2 DH |
121 | |
122 | ||
123 | The items are reference counted, so there ought to be no need for a flush | |
01609502 JA |
124 | operation. But as the reference counting is optional, means to cancel |
125 | existing work items are also included: | |
126 | ||
127 | cancel_slow_work(&myitem); | |
6b8268b1 | 128 | cancel_delayed_slow_work(&myitem); |
01609502 JA |
129 | |
130 | can be used to cancel pending work. The above cancel function waits for | |
131 | existing work to have been executed (or prevent execution of them, depending | |
132 | on timing). | |
133 | ||
134 | ||
135 | When all a module's slow work items have been processed, and the | |
8f0aa2f2 DH |
136 | module has no further interest in the facility, it should unregister its |
137 | interest: | |
138 | ||
3d7a641e DH |
139 | slow_work_unregister_user(struct module *module); |
140 | ||
141 | The module pointer is used to wait for all outstanding work items for that | |
142 | module before completing the unregistration. This prevents the put_ref() code | |
143 | from being taken away before it completes. module should almost certainly be | |
144 | THIS_MODULE. | |
8f0aa2f2 DH |
145 | |
146 | ||
147 | =============== | |
148 | ITEM OPERATIONS | |
149 | =============== | |
150 | ||
151 | Each work item requires a table of operations of type struct slow_work_ops. | |
4d8bb2cb | 152 | Only ->execute() is required, getting and putting of a reference are optional. |
8f0aa2f2 DH |
153 | |
154 | (*) Get a reference on an item: | |
155 | ||
156 | int (*get_ref)(struct slow_work *work); | |
157 | ||
158 | This allows the thread pool to attempt to pin an item by getting a | |
159 | reference on it. This function should return 0 if the reference was | |
160 | granted, or a -ve error otherwise. If an error is returned, | |
161 | slow_work_enqueue() will fail. | |
162 | ||
163 | The reference is held whilst the item is queued and whilst it is being | |
164 | executed. The item may then be requeued with the same reference held, or | |
165 | the reference will be released. | |
166 | ||
167 | (*) Release a reference on an item: | |
168 | ||
169 | void (*put_ref)(struct slow_work *work); | |
170 | ||
171 | This allows the thread pool to unpin an item by releasing the reference on | |
172 | it. The thread pool will not touch the item again once this has been | |
173 | called. | |
174 | ||
175 | (*) Execute an item: | |
176 | ||
177 | void (*execute)(struct slow_work *work); | |
178 | ||
179 | This should perform the work required of the item. It may sleep, it may | |
180 | perform disk I/O and it may wait for locks. | |
181 | ||
182 | ||
183 | ================== | |
184 | POOL CONFIGURATION | |
185 | ================== | |
186 | ||
187 | The slow-work thread pool has a number of configurables: | |
188 | ||
189 | (*) /proc/sys/kernel/slow-work/min-threads | |
190 | ||
191 | The minimum number of threads that should be in the pool whilst it is in | |
192 | use. This may be anywhere between 2 and max-threads. | |
193 | ||
194 | (*) /proc/sys/kernel/slow-work/max-threads | |
195 | ||
196 | The maximum number of threads that should in the pool. This may be | |
197 | anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. | |
198 | ||
199 | (*) /proc/sys/kernel/slow-work/vslow-percentage | |
200 | ||
201 | The percentage of active threads in the pool that may be used to execute | |
202 | very slow work items. This may be between 1 and 99. The resultant number | |
203 | is bounded to between 1 and one fewer than the number of active threads. | |
204 | This ensures there is always at least one thread that can process very | |
205 | slow work items, and always at least one thread that won't. |