Home
last modified time | relevance | path

Searched refs:reclaim (Results 1 – 25 of 70) sorted by relevance

123

/Linux-v4.19/Documentation/core-api/
Dgfp_mask-from-fs-io.rst13 memory reclaim calling back into the FS or IO paths and blocking on
23 of GFP_NOFS/GFP_NOIO can lead to memory over-reclaim or other memory
24 reclaim issues.
42 any critical section with respect to the reclaim is started - e.g.
43 lock shared with the reclaim context or when a transaction context
44 nesting would be possible via reclaim. The restore function should be
46 explanation what is the reclaim context for easier maintenance.
Dworkqueue.rst143 on code paths that handle memory reclaim are required to be queued on
190 All wq which might be used in the memory reclaim paths **MUST**
330 items which are used during memory reclaim. Each wq with
333 reclaim, they should be queued to separate wq each with
344 which are not involved in memory reclaim and don't need to be
/Linux-v4.19/drivers/md/
Ddm-zoned-target.c52 struct dmz_reclaim *reclaim; member
403 dmz_schedule_reclaim(dmz->reclaim); in dmz_handle_bio()
620 dmz_reclaim_bio_acc(dmz->reclaim); in dmz_map()
813 ret = dmz_ctr_reclaim(dev, dmz->metadata, &dmz->reclaim); in dmz_ctr()
851 dmz_dtr_reclaim(dmz->reclaim); in dmz_dtr()
917 dmz_suspend_reclaim(dmz->reclaim); in dmz_suspend()
929 dmz_resume_reclaim(dmz->reclaim); in dmz_resume()
Ddm-zoned-reclaim.c483 struct dmz_reclaim **reclaim) in dmz_ctr_reclaim() argument
513 *reclaim = zrc; in dmz_ctr_reclaim()
/Linux-v4.19/Documentation/sysctl/
Dvm.txt246 reclaim to satisfy a high-order allocation. The extfrag/extfrag_index file in
457 A percentage of the total pages in each zone. On Zone reclaim
461 systems that rarely perform global reclaim.
465 Note that slab reclaim is triggered in a per zone / node fashion.
475 This is a percentage of the total pages in each zone. Zone reclaim will
841 This percentage value controls the tendency of the kernel to reclaim
845 reclaim dentries and inodes at a "fair" rate with respect to pagecache and
846 swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
848 never reclaim dentries and inodes due to memory pressure and this can easily
850 causes the kernel to prefer to reclaim dentries and inodes.
[all …]
/Linux-v4.19/include/linux/
Dpage-flags.h319 PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) in PAGEFLAG()
320 TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) in PAGEFLAG()
321 PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) in PAGEFLAG()
322 TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) in PAGEFLAG()
/Linux-v4.19/Documentation/device-mapper/
Ddm-zoned.txt26 internally for storing metadata and performaing reclaim operations.
103 situation, a reclaim process regularly scans used conventional zones and
104 tries to reclaim the least recently used zones by copying the valid
123 (for both incoming BIO processing and reclaim process) and all dirty
/Linux-v4.19/include/linux/lockd/
Dxdr.h66 u32 reclaim; member
/Linux-v4.19/drivers/media/mmc/siano/
Dsmssdio.c308 goto reclaim; in smssdio_probe()
312 reclaim: in smssdio_probe()
/Linux-v4.19/drivers/usb/host/
Doxu210hp-hcd.c1646 struct ehci_qh *qh = oxu->reclaim; in end_unlink_async()
1656 next = qh->reclaim; in end_unlink_async()
1657 oxu->reclaim = next; in end_unlink_async()
1659 qh->reclaim = NULL; in end_unlink_async()
1678 oxu->reclaim = NULL; in end_unlink_async()
1693 BUG_ON(oxu->reclaim || (qh->qh_state != QH_STATE_LINKED in start_unlink_async()
1701 && !oxu->reclaim) { in start_unlink_async()
1712 oxu->reclaim = qh = qh_get(qh); in start_unlink_async()
1776 else if (!oxu->reclaim in scan_async()
2394 && oxu->reclaim in unlink_async()
[all …]
Doxu210hp.h302 struct ehci_qh *reclaim; /* next to reclaim */ member
394 struct ehci_qh *reclaim; member
/Linux-v4.19/Documentation/accounting/
Dtaskstats-struct.txt29 6) Extended delay accounting fields for memory reclaim
176 6) Extended delay accounting fields for memory reclaim
177 /* Delay waiting for memory reclaim */
Ddelay-accounting.txt14 d) memory reclaim
45 delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
/Linux-v4.19/fs/lockd/
Dclntproc.c276 if (host->h_reclaiming && !argp->reclaim) in nlmclnt_call()
306 if (argp->reclaim) { in nlmclnt_call()
312 if (!argp->reclaim) { in nlmclnt_call()
630 req->a_args.reclaim = 1; in nlmclnt_reclaim()
Dsvclock.c401 struct nlm_cookie *cookie, int reclaim) in nlmsvc_lock() argument
447 if (locks_in_grace(SVC_NET(rqstp)) && !reclaim) { in nlmsvc_lock()
451 if (reclaim && !locks_in_grace(SVC_NET(rqstp))) { in nlmsvc_lock()
/Linux-v4.19/Documentation/cgroup-v1/
Dmemory.txt161 charged is over its limit. If it is, then reclaim is invoked on the cgroup.
162 More details can be found in the reclaim section of this document.
245 to reclaim memory from the cgroup so as to make space for the new
246 pages that the cgroup has touched. If the reclaim is unsuccessful,
250 The reclaim algorithm has not been modified for cgroups, except that
295 to trigger slab reclaim when those limits are reached.
335 WARNING: In the current implementation, memory reclaim will NOT be
340 Since kmem charges will also be fed to the user counter and reclaim will be
537 Please note that unlike during the global reclaim, limit reclaim
540 if there are no file pages to reclaim.
[all …]
Dhugetlb.txt6 support page reclaim, enforcing the limit at page fault time implies that,
/Linux-v4.19/Documentation/vm/
Dz3fold.rst29 depend on MMU enabled and provides more predictable reclaim behavior
Dunevictable-lru.rst32 reclaim in Linux. The problems have been observed at customer sites on large
110 not attempt to reclaim pages on the unevictable list. This has a couple of
113 (1) Because the pages are "hidden" from reclaim on the unevictable list, the
114 reclaim process can be more efficient, dealing only with pages that have a
267 reclaim a page in a VM_LOCKED VMA via try_to_unmap()
329 it later if and when it attempts to reclaim the page.
404 This is fine, because we'll catch it later if and if vmscan tries to reclaim
532 try_to_unmap() is always called, by either vmscan for reclaim or for page
539 When trying to reclaim, if try_to_unmap_one() finds the page in a VM_LOCKED
546 munlock or munmap system calls, mm teardown (munlock_vma_pages_all), reclaim,
/Linux-v4.19/Documentation/ABI/testing/
Dpstore28 device that it can reclaim the space for later re-use.
/Linux-v4.19/net/ipv4/
Dtcp_metrics.c153 bool reclaim = false; in tcpm_new() local
163 reclaim = true; in tcpm_new()
171 if (unlikely(reclaim)) { in tcpm_new()
192 if (likely(!reclaim)) { in tcpm_new()
/Linux-v4.19/Documentation/admin-guide/mm/
Dconcepts.rst182 repurposing them is called (surprise!) `reclaim`. Linux can reclaim
193 will trigger the `direct reclaim`. In this case allocation is stalled
211 Like reclaim, the compaction may happen asynchronously in ``kcompactd``
Dtranshuge.rst125 allocation failure and directly reclaim pages and compact
132 to reclaim pages and wake kcompactd to compact memory so that
137 will enter direct reclaim and compaction like ``always``, but
139 other regions will wake kswapd in the background to reclaim
144 will enter direct reclaim like ``always`` but only for regions
/Linux-v4.19/drivers/net/wireless/intel/iwlwifi/pcie/
Drx.c1206 bool reclaim; in iwl_pcie_rx_handle_rb() local
1253 reclaim = !(pkt->hdr.sequence & SEQ_RX_FRAME); in iwl_pcie_rx_handle_rb()
1254 if (reclaim && !pkt->hdr.group_id) { in iwl_pcie_rx_handle_rb()
1260 reclaim = false; in iwl_pcie_rx_handle_rb()
1277 if (reclaim) { in iwl_pcie_rx_handle_rb()
1287 if (reclaim) { in iwl_pcie_rx_handle_rb()
/Linux-v4.19/Documentation/filesystems/
Dfuse-io.txt31 reclaim on memory pressure) or explicitly (invoked by close(2), fsync(2) and

123