| /linux-4.4.14/fs/ubifs/ |
| D | shrinker.c | 70 static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention) in shrink_tnc() argument
120 *contention = 1; in shrink_tnc()
156 static int shrink_tnc_trees(int nr, int age, int *contention) in shrink_tnc_trees() argument
179 *contention = 1; in shrink_tnc_trees()
189 *contention = 1; in shrink_tnc_trees()
199 freed += shrink_tnc(c, nr, age, contention); in shrink_tnc_trees()
295 int contention = 0; in ubifs_shrink_scan() local
311 freed = shrink_tnc_trees(nr, OLD_ZNODE_AGE, &contention); in ubifs_shrink_scan()
316 freed += shrink_tnc_trees(nr - freed, YOUNG_ZNODE_AGE, &contention); in ubifs_shrink_scan()
321 freed += shrink_tnc_trees(nr - freed, 0, &contention); in ubifs_shrink_scan()
[all …]
|
| /linux-4.4.14/Documentation/locking/ |
| D | lockstat.txt | 10 Because things like lock contention can severely impact performance.
45 con-bounces - number of lock contention that involved x-cpu data
61 It also tracks 4 contention points per class. A contention point is a call site
122 short separator (line 08, 13) from the contention points.
124 Lines 09-12 show the first 4 recorded contention points (the code
130 short separator. The contention points don't match the column descriptors,
131 they have two: contentions and [<IP>] symbol. The second set of contention
|
| D | 00-INDEX | 6 - info on collecting statistics on locks (and contention).
|
| D | locktorture.txt | 16 different critical region behaviors. The amount of contention on the lock
|
| D | rt-mutex-design.txt | 566 If there is contention on the lock, whether it is owned or pending owner
580 contention).
719 CMPXCHG. Since the taking of a mutex on contention always sets the
|
| D | ww-mutex-design.txt | 312 In general, not much contention is expected. The locks are typically used to
|
| /linux-4.4.14/tools/perf/scripts/python/bin/ |
| D | futex-contention-report | 4 perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py
|
| /linux-4.4.14/kernel/ |
| D | Kconfig.hz | 13 contention and cacheline bounces as a result of timer interrupts.
|
| /linux-4.4.14/Documentation/trace/ |
| D | events-kmem.txt | 64 contention on the zone->lru_lock.
72 for order-0 pages, reduces contention on the zone->lock and reduces the
|
| /linux-4.4.14/Documentation/vm/ |
| D | split_page_table_lock | 6 multi-threaded applications due high contention on the lock. To improve
|
| D | slub.txt | 126 contention may occur.
|
| /linux-4.4.14/Documentation/networking/ |
| D | scaling.txt | 177 during CPU contention by dropping packets from large flows slightly
194 and cache contention) and toggled per CPU by setting the relevant bit
373 provides two benefits. First, contention on the device queue lock is
375 (contention can be eliminated completely if each CPU has its own
419 experience no contention. If there are fewer queues than CPUs, then the
|
| /linux-4.4.14/Documentation/arm/ |
| D | vlocks.txt | 147 reducing bus contention in contended cases.
|
| /linux-4.4.14/drivers/block/paride/ |
| D | Transition-notes | 113 that the only possible contention is between scheduling ps_tq followed by
|
| /linux-4.4.14/fs/squashfs/ |
| D | Kconfig | 51 it eliminates a memcpy and it also removes the lock contention
|
| /linux-4.4.14/Documentation/filesystems/ |
| D | xfs-delayed-logging-design.txt | 642 items, it will get held for a significant time and so spin contention is a
658 possible that this lock will become a contention point, but given the short
659 hold time once per transaction I think that contention is unlikely.
679 much contention on the CIL lock, or too many context switches as a result of
681 given separate wait lists to reduce lock contention and the number of processes
|
| D | path-lookup.txt | 31 (usually, the root "/" or current working directory). So contention on these
|
| /linux-4.4.14/Documentation/ |
| D | robust-futexes.txt | 12 field. If userspace notices contention (the lock is already owned and
|
| D | kernel-parameters.txt | 3450 xtime_lock contention on larger systems, and/or RCU lock
3451 contention on all systems with CONFIG_MAXSMP set.
|
| /linux-4.4.14/Documentation/cgroups/ |
| D | memory.txt | 635 a. There is no memory contention
638 When the system detects memory contention or low memory, control groups
|
| D | cpusets.txt | 82 memory placement to reduce memory access times and contention,
|
| /linux-4.4.14/init/ |
| D | Kconfig | 597 against lock contention. Systems that synchronize their
600 lock contention levels acceptably low. Very large systems
606 skew them, which reduces lock contention enough that large
|
| /linux-4.4.14/mm/ |
| D | Kconfig | 205 # space can be handled with less contention: split it at this NR_CPUS.
|
| /linux-4.4.14/Documentation/RCU/ |
| D | RTFP.txt | 47 write-side contention and parallelize the other write-side overheads by
89 but reduces memory latency, contention, and locking overheads.
115 contention, reduces memory latency for readers, and parallelizes pipeline
|
| D | trace.txt | 326 due to contention on ->fqslock.
|
| D | whatisRCU.txt | 98 SMP computer systems, even in absence of lock contention.
|
| /linux-4.4.14/lib/ |
| D | Kconfig.debug | 1037 This feature enables tracking lock contention points
|