)]}' { "log": [ { "commit": "c0bbbc73d58f1b774cd987b5687a478a027f137c", "tree": "b07538753116e6e4792e2a283318694e3cbbc614", "parents": [ "650fb8382287f7990d5127a82a54295139224606" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jun 11 15:22:26 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jun 11 15:27:37 2006 -0700" }, "message": "[PATCH] typo in vmscan.c\n\nFrom: Christoph Lameter \u003cclameter@sgi.com\u003e\n\nLooks like a comma was left from the conversion from a struct to an\nassignment.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "83d722f7e198b034699b1500d98729beff930efd", "tree": "7d790a2fd62165373ec7bacde704837288e0bec3", "parents": [ "649bbaa484bcdce94f40a1b97a6a2ded0549e8a2" ], "author": { "name": "Chandra Seetharaman", "email": "sekharan@us.ibm.com", "time": "Mon Apr 24 19:35:21 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Apr 26 08:30:03 2006 -0700" }, "message": "[PATCH] Remove __devinit and __cpuinit from notifier_call definitions\n\nFew of the notifier_chain_register() callers use __init in the definition\nof notifier_call. It is incorrect as the function definition should be\navailable after the initializations (they do not unregister them during\ninitializations).\n\nThis patch fixes all such usages to _not_ have the notifier_call __init\nsection.\n\nSigned-off-by: Chandra Seetharaman \u003csekharan@us.ibm.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ec936fc563715a9e2b2e363eb060655b49529325", "tree": "72e77aefeeda3c6ff396f080a5c6a82f25d52bf0", "parents": [ "679bc9fbb508a0aac9539b2de747eb5849feb428" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Mon Mar 27 01:15:59 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Mar 27 08:44:48 2006 -0800" }, "message": "[PATCH] for_each_online_pgdat: renaming for_each_pgdat\n\nReplace for_each_pgdat() with for_each_online_pgdat().\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "05eeae208d08a05a6980cf2ff61f02843c0955fd", "tree": "be6c6c4e16cfac07edf437a1f74ef027ada8ccc7", "parents": [ "c1f5a1944657ba6abe375e3bb2a3238a46849f70" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sat Mar 25 03:07:48 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 08:22:57 2006 -0800" }, "message": "[PATCH] find_task_by_pid() needs tasklist_lock\n\nA couple of places are forgetting to take it.\n\nThe kswapd case is probably unimportant. keventd_create_kthread() was racy.\n\nThe whole thing is a bit flakey: you start a kernel thread, get its pid from\nkernel_thread() then look up its task_struct.\n\na) It assumes that pid recycling takes a \"long\" time.\n\nb) We get a task_struct but no reference was taken on it. The owner of the\n kswapd and kthread task_struct*\u0027s must assume that the new thread won\u0027t\n exit unexpectedly. Because if it does, they\u0027re left holding dead memory\n and any attempt to control or stop that task will crash.\n\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b20a35035f983f4ac7e29c4a68f30e43510007e0", "tree": "fdf090ddddbcc275349f62f71adc98649e2c683b", "parents": [ "442295c94bf650221af3ef20fc68fa3e93876818" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Mar 22 00:09:12 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:06 2006 -0800" }, "message": "[PATCH] page migration reorg\n\nCentralize the page migration functions in anticipation of additional\ntinkering. Creates a new file mm/migrate.c\n\n1. Extract buffer_migrate_page() from fs/buffer.c\n\n2. Extract central migration code from vmscan.c\n\n3. Extract some components from mempolicy.c\n\n4. Export pageout() and remove_from_swap() from vmscan.c\n\n5. Make it possible to configure NUMA systems without page migration\n and non-NUMA systems with page migration.\n\nI had to so some #ifdeffing in mempolicy.c that may need a cleanup.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "248a0301e703cbf781aa02a91bcfc6da75870dd7", "tree": "74168da24983ec948fb25f92c2b3a1b9d76a5f13", "parents": [ "d5d4b0aa4e1430d73050babba999365593bdb9d2" ], "author": { "name": "Rafael J. Wysocki", "email": "rjw@sisk.pl", "time": "Wed Mar 22 00:09:04 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:05 2006 -0800" }, "message": "[PATCH] mm: make shrink_all_memory try harder\n\nMake shrink_all_memory() repeat the attempts to free more memory if there\nseems to be no pages to free.\n\nSigned-off-by: Rafael J. Wysocki \u003crjw@sisk.pl\u003e\nCc: Pavel Machek \u003cpavel@ucw.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6e5ef1a96e6e3b123da56292bc35017c8c401491", "tree": "db9532c53013bccd7ac9d186784bbc6fd343bca4", "parents": [ "a7290ee08e434399660ace34427c17696e47c562" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Mar 22 00:08:45 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:02 2006 -0800" }, "message": "[PATCH] vmscan: emove obsolete checks from shrink_list() and fix unlikely in refill_inactive_zone()\n\nAs suggested by Marcelo:\n\n1. The optimization introduced recently for not calling\n page_referenced() during zone reclaim makes two additional checks in\n shrink_list unnecessary.\n\n2. The if (unlikely(sc-\u003emay_swap)) in refill_inactive_zone is optimized\n for the zone_reclaim case. However, most peoples system only does swap.\n Undo that.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Marcelo Tosatti \u003cmarcelo.tosatti@cyclades.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0f8053a509ceba4a077a50ea7b77039b5559b428", "tree": "5a66021540395e20256f38a3a45174617428a832", "parents": [ "4fa4f53bf92139595cae6f1a3d972fc0a3451d29" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Mar 22 00:08:33 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:01 2006 -0800" }, "message": "[PATCH] mm: make __put_page internal\n\nRemove __put_page from outside the core mm/. It is dangerous because it does\nnot handle compound pages nicely, and misses 1-\u003e0 transitions. If a user\nlater appears that really needs the extra speed we can reevaluate.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "fb8d14e172a29ba5ac69a73b61196be86fdfc3e1", "tree": "5b31eac00f8fc5860170d7f8b2e7e961dbda0ddf", "parents": [ "c9b02d970c385a253edb36c87643b0df706b50b4" ], "author": { "name": "Wu Fengguang", "email": "wfg@mail.ustc.edu.cn", "time": "Wed Mar 22 00:08:28 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] mm: shrink_inactive_lis() nr_scan accounting fix\n\nIn shrink_inactive_list(), nr_scan is not accounted when nr_taken is 0.\nBut 0 pages taken does not mean 0 pages scanned.\n\nMove the goto statement below the accounting code to fix it.\n\nSigned-off-by: Wu Fengguang \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c9b02d970c385a253edb36c87643b0df706b50b4", "tree": "0e1990c1ced842a923221b36ee1546bf9aac8509", "parents": [ "7fb2d46d396b2491818f8e43b01049b3234e6c07" ], "author": { "name": "Wu Fengguang", "email": "wfg@mail.ustc.edu.cn", "time": "Wed Mar 22 00:08:23 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] mm: isolate_lru_pages() scan count fix\n\nIn isolate_lru_pages(), *scanned reports one more scan because the scan\ncounter is increased one more time on exit of the while-loop.\n\nChange the while-loop to for-loop to fix it.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7fb2d46d396b2491818f8e43b01049b3234e6c07", "tree": "d5826a4d1c3b1853be20c6049311eb52f1a98360", "parents": [ "1742f19fa920cdd6905f0db5898524dde22ab2a4" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Mar 22 00:08:22 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] zone_reclaim: additional comments and cleanup\n\nAdd some comments to explain how zone reclaim works. And it fixes the\nfollowing issues:\n\n- PF_SWAPWRITE needs to be set for RECLAIM_SWAP to be able to write\n out pages to swap. Currently RECLAIM_SWAP may not do that.\n\n- remove setting nr_reclaimed pages after slab reclaim since the slab shrinking\n code does not use that and the nr_reclaimed pages is just right for the\n intended follow up action.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1742f19fa920cdd6905f0db5898524dde22ab2a4", "tree": "90a490795f29f96e89503ead5affb4c8f99e5e75", "parents": [ "05ff51376f01fd8837946a4f8144a84f6cc71c19" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Wed Mar 22 00:08:21 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] vmscan: rename functions\n\nWe have:\n\n\ttry_to_free_pages\n\t-\u003eshrink_caches(struct zone **zones, ..)\n\t -\u003eshrink_zone(struct zone *, ...)\n\t -\u003eshrink_cache(struct zone *, ...)\n\t -\u003eshrink_list(struct list_head *, ...)\n\t -\u003erefill_inactive_list((struct zone *, ...)\n\nwhich is fairly irrational.\n\nRename things so that we have\n\n \ttry_to_free_pages\n \t-\u003eshrink_zones(struct zone **zones, ..)\n \t -\u003eshrink_zone(struct zone *, ...)\n \t -\u003eshrink_inactive_list(struct zone *, ...)\n \t -\u003eshrink_page_list(struct list_head *, ...)\n\t -\u003eshrink_active_list(struct zone *, ...)\n\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Christoph Lameter \u003cchristoph@lameter.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "05ff51376f01fd8837946a4f8144a84f6cc71c19", "tree": "ca91bcabe6b4bfa71801a39e2921a44ec0bb1003", "parents": [ "69e05944af39fc6c97b09380c8721e38433bd828" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Wed Mar 22 00:08:20 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] vmscan return nr_reclaimed\n\nChange all the vmscan functions to retunr the number-of-reclaimed pages and\nremove scan_conrtol.nr_reclaimed.\n\nSaves ten-odd bytes of text and makes things clearer and more consistent.\n\nThe patch also changes the behaviour of zone_reclaim() when it falls back to slab shrinking. Christoph says\n\n \"Setting this to one means that we will rescan and shrink the slab for\n each allocation if we are out of zone memory and RECLAIM_SLAB is set. Plus\n if we do an order 0 allocation we do not go off node as intended.\n\n \"We better set this to zero. This means the allocation will go offnode\n despite us having potentially freed lots of memory on the zone. Future\n allocations can then again be done from this zone.\"\n\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Christoph Lameter \u003cchristoph@lameter.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "69e05944af39fc6c97b09380c8721e38433bd828", "tree": "165e594ed5cd34c3a2b2ec236f75ac5b192ade7a", "parents": [ "179e96395b1f01e95ebe1ff5ef306b810dbbd147" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Wed Mar 22 00:08:19 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] vmscan: use unsigned longs\n\nTurn basically everything in vmscan.c into `unsigned long\u0027. This is to avoid\nthe possibility that some piece of code in there might decide to operate upon\nmore than 4G (or even 2G) of pages in one hit.\n\nThis might be silly, but we\u0027ll need it one day.\n\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Rafael J. Wysocki \u003crjw@sisk.pl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "179e96395b1f01e95ebe1ff5ef306b810dbbd147", "tree": "c21157905aa04dc37b531a1deaacd022932fa48e", "parents": [ "8695949a1d7c99e039595db00af8e0fe4722307d" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Wed Mar 22 00:08:18 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:54:00 2006 -0800" }, "message": "[PATCH] vmscan: scan_control cleanup\n\nInitialise as much of scan_control as possible at the declaration site. This\ntidies things up a bit and assures us that all unmentioned fields are zeroed\nout.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8695949a1d7c99e039595db00af8e0fe4722307d", "tree": "ac845804aeabdeb19963b5907df921cb9ba8839e", "parents": [ "a07fa3944bf924881450884224cbb2f1269cb9fa" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Mar 22 00:08:18 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:53:59 2006 -0800" }, "message": "[PATCH] Thin out scan_control: remove nr_to_scan and priority\n\nMake nr_to_scan and priority a parameter instead of putting it into scan\ncontrol. This allows various small optimizations and IMHO makes the code\neasier to read.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7c8ee9a86340db686cd4314e9944dc9b6111bda9", "tree": "80638e1658556b4fd7c0b92d571aaac854245bd3", "parents": [ "f205b2fe62d321403525065a4cb31b6bff1bbe53" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Mar 22 00:08:03 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:53:57 2006 -0800" }, "message": "[PATCH] mm: simplify vmscan vs release refcounting\n\nThe VM has an interesting race where a page refcount can drop to zero, but it\nis still on the LRU lists for a short time. This was solved by testing a 0-\u003e1\nrefcount transition when picking up pages from the LRU, and dropping the\nrefcount in that case.\n\nInstead, use atomic_add_unless to ensure we never pick up a 0 refcount page\nfrom the LRU, thus a 0 refcount page will never have its refcount elevated\nuntil it is allocated again.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4c84cacfa424264f7ad5287298d3ea4a3e935278", "tree": "8cefe97dfd0cdfbdebe5636ccc68b14ab3ae1207", "parents": [ "8d438f96d2b8eade6cbcd8adfc22dae6f5cbd6c0" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Mar 22 00:08:00 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:53:57 2006 -0800" }, "message": "[PATCH] mm: PageActive no testset\n\nPG_active is protected by zone-\u003elru_lock, it does not need TestSet/TestClear\noperations.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8d438f96d2b8eade6cbcd8adfc22dae6f5cbd6c0", "tree": "5248caf52ed9ba1dbb172d9e3bd3216c97ab3b84", "parents": [ "46453a6e194a8c55fe6cf3dc8e1c4f24e2abc013" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Mar 22 00:07:59 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:53:56 2006 -0800" }, "message": "[PATCH] mm: PageLRU no testset\n\nPG_lru is protected by zone-\u003elru_lock. It does not need TestSet/TestClear\noperations.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "46453a6e194a8c55fe6cf3dc8e1c4f24e2abc013", "tree": "e407665e6c8cdf33814007750c49fdbea0a21e0e", "parents": [ "2492ecc1a16b8ccf679d2999dca4f1b48aef07ee" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Mar 22 00:07:58 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Mar 22 07:53:56 2006 -0800" }, "message": "[PATCH] mm: never ClearPageLRU released pages\n\nIf vmscan finds a zero refcount page on the lru list, never ClearPageLRU\nit. This means the release code need not hold -\u003elru_lock to stabilise\nPageLRU, so that lock may be skipped entirely when releasing !PageLRU pages\n(because we know PageLRU won\u0027t have been temporarily cleared by vmscan,\nwhich was previously guaranteed by holding the lock to synchronise against\nvmscan).\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4983da07f1e2e8dc81cb9d640fbf35b899cdbdf2", "tree": "9c238114f029d1d22bc55f47e8d95ef7335c540d", "parents": [ "e843e280cbe218fc8387339806d344708dee348a" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Tue Mar 14 19:50:19 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Mar 14 21:43:02 2006 -0800" }, "message": "[PATCH] page migration: fail if page is in a vma flagged VM_LOCKED\n\npage migration currently simply retries a couple of times if try_to_unmap()\nfails without inspecting the return code.\n\nHowever, SWAP_FAIL indicates that the page is in a vma that has the\nVM_LOCKED flag set (if ignore_refs \u003d\u003d1). We can check for that return code\nand avoid retrying the migration.\n\nmigrate_page_remove_references() now needs to return a reason why the\nfailure occured. So switch migrate_page_remove_references to use -Exx\nstyle error messages.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "a6bf527091b1dd40f1b6a496812ce7520621c282", "tree": "bed2341cbb2e4bf71d29f2e8b6ab7affa72aabd5", "parents": [ "04b857f74cec5efc7730e9db47e291310f4708a4" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Thu Mar 09 17:33:47 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Mar 09 19:47:37 2006 -0800" }, "message": "[PATCH] vmscan: no zone_reclaim if PF_MALLOC is set\n\nIf the process has already set PF_MALLOC and is already using\ncurrent-\u003ereclaim_state then do not try to reclaim memory from the zone.\nThis is set by kswapd and/or synchrononous global reclaim which will not\ntake it lightly if we zap the reclaim_state.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sig.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d4f7796e9b387e471ab0e8ed4e0c2bd616b3c193", "tree": "e68b20c1952e3d1bfc6bb51c1b38cd6323e2c771", "parents": [ "c04030e16dbea2f7581f82cc6688695927f6ac5b" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Fri Feb 24 13:04:22 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Feb 24 14:31:39 2006 -0800" }, "message": "[PATCH] vmscan: fix zone_reclaim\n\n- PF_SWAPWRITE needs to be set for RECLAIM_SWAP to be able to write\n out pages to swap. Currently RECLAIM_SWAP may not do that.\n\n- remove setting nr_reclaimed pages after slab reclaim since the slab shrinking\n code does not use that and the nr_reclaimed pages is just right for the\n intended follow up action.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2903fb1694dcb08a3c1d9d823cfae7ba30e66cd3", "tree": "7d794e0997e935033354f3c3ffd81c1f31354db3", "parents": [ "072eaa5d9cc3e63f567ffd9ad87b36194fdd8010" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Sat Feb 11 17:55:55 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Feb 11 21:41:11 2006 -0800" }, "message": "[PATCH] vmscan: skip reclaim_mapped determination if we do not swap\n\nThis puts the variables and the way to get to reclaim_mapped in one block.\nAnd allows zone_reclaim or other things to skip the determination (maybe\nthis whole block of code does not belong into refill_inactive_zone()?)\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "072eaa5d9cc3e63f567ffd9ad87b36194fdd8010", "tree": "27b4acaea0ed57a839148e8d33d7ea5952c704d1", "parents": [ "80e4342601abfafacb5f20571e40b56d73d10819" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Sat Feb 11 17:55:54 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Feb 11 21:41:11 2006 -0800" }, "message": "[PATCH] vmscan: remove duplicate increment of reclaim_in_progress\n\nshrink_zone() already increments reclaim_in_progress. No need to do it in\nbalance_pgdat.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "80e4342601abfafacb5f20571e40b56d73d10819", "tree": "c03c988860aa8b6a1cc24ba8adff3778c1705928", "parents": [ "643a654540579b0dcc7a206a4a7475276a41aff0" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Sat Feb 11 17:55:53 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Feb 11 21:41:11 2006 -0800" }, "message": "[PATCH] zone reclaim: do not check references to a page during zone reclaim\n\nshrink_list() and refill_inactive() check all ptes pointing to a page for\nreference bits in order to decide if the page should be put on the active\nlist. This is not necessary for zone_reclaim since we are only interested\nin removing unmapped pages. Skip the checks in both functions.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "418aade459f03318defd18ef0b11981a63bd81b0", "tree": "b13a46e3d7050fa92e390b3374910882ae867254", "parents": [ "8977d929e49021d9a6e031310aab01fa72f849c2" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Fri Feb 10 01:51:15 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Feb 10 08:13:13 2006 -0800" }, "message": "[PATCH] Updates for page migration\n\nThis adds some additional comments in order to help others figure out how\nexactly the code works. And fix a variable name.\n\nAlso swap_page does need to ignore all reference bits when unmapping a\npage. Otherwise we may have to repeatedly unmap a frequently touched page.\nSo change the try_to_unmap parameter to 1.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e965f9630c651fa4249039fd4b80c9392d07a856", "tree": "1353dd536d0ee549c30e462086624c21788ee9d2", "parents": [ "7e2ab150d1b3b286a4c864c60a549b2601777b63" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Feb 01 03:05:41 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:17 2006 -0800" }, "message": "[PATCH] Direct Migration V9: Avoid writeback / page_migrate() method\n\nMigrate a page with buffers without requiring writeback\n\nThis introduces a new address space operation migratepage() that may be used\nby a filesystem to implement its own version of page migration.\n\nA version is provided that migrates buffers attached to pages. Some\nfilesystems (ext2, ext3, xfs) are modified to utilize this feature.\n\nThe swapper address space operation are modified so that a regular\nmigrate_page() will occur for anonymous pages without writeback (migrate_pages\nforces every anonymous page to have a swap entry).\n\nSigned-off-by: Mike Kravetz \u003ckravetz@us.ibm.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "a3351e525e4768c29aa5d22ef59b5b38e0361e53", "tree": "457ab54f402b471c5158e8b361d059e88ab8cd62", "parents": [ "a48d07afdf18212de22b959715b16793c5a6e57a" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Feb 01 03:05:39 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] Direct Migration V9: remove_from_swap() to remove swap ptes\n\nAdd remove_from_swap\n\nremove_from_swap() allows the restoration of the pte entries that existed\nbefore page migration occurred for anonymous pages by walking the reverse\nmaps. This reduces swap use and establishes regular pte\u0027s without the need\nfor page faults.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "a48d07afdf18212de22b959715b16793c5a6e57a", "tree": "36d5963c29ceb5c2f6df53036cef5c0d30383dbf", "parents": [ "b16664e44c54525be89dc07ad15a13b4eeec5634" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Feb 01 03:05:38 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] Direct Migration V9: migrate_pages() extension\n\nAdd direct migration support with fall back to swap.\n\nDirect migration support on top of the swap based page migration facility.\n\nThis allows the direct migration of anonymous pages and the migration of file\nbacked pages by dropping the associated buffers (requires writeout).\n\nFall back to swap out if necessary.\n\nThe patch is based on lots of patches from the hotplug project but the code\nwas restructured, documented and simplified as much as possible.\n\nNote that an additional patch that defines the migrate_page() method for\nfilesystems is necessary in order to avoid writeback for anonymous and file\nbacked pages.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Mike Kravetz \u003ckravetz@us.ibm.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2a16e3f4b0c408b9e50297d2ec27e295d490267a", "tree": "71569cfdf06fb83497e88e4e6543fbe624488aa3", "parents": [ "1b2ffb7896ad46067f5b9ebf7de1891d74a4cdef" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:35 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] Reclaim slab during zone reclaim\n\nIf large amounts of zone memory are used by empty slabs then zone_reclaim\nbecomes uneffective. This patch shakes the slab a bit.\n\nThe problem with this patch is that the slab reclaim is not containable to a\nzone. Thus slab reclaim may affect the whole system and be extremely slow.\nThis also means that we cannot determine how many pages were freed in this\nzone. Thus we need to go off node for at least one allocation.\n\nThe functionality is disabled by default.\n\nWe could modify the shrinkers to take a zone parameter but that would be quite\ninvasive. Better ideas are welcome.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1b2ffb7896ad46067f5b9ebf7de1891d74a4cdef", "tree": "a8f257639d4041bf0e7d61eda3fb72f2eb69f4bc", "parents": [ "2a11ff06d7d12be5d1bbcf592fff649b45ac2388" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:34 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] Zone reclaim: Allow modification of zone reclaim behavior\n\nIn some situations one may want zone_reclaim to behave differently. For\nexample a process writing large amounts of memory will spew unto other nodes\nto cache the writes if many pages in a zone become dirty. This may impact the\nperformance of processes running on other nodes.\n\nAllowing writes during reclaim puts a stop to that behavior and throttles the\nprocess by restricting the pages to the local zone.\n\nSimilarly one may want to contain processes to local memory by enabling\nregular swap behavior during zone_reclaim. Off node memory allocation can\nthen be controlled through memory policies and cpusets.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2a11ff06d7d12be5d1bbcf592fff649b45ac2388", "tree": "cef86d3f60b6ae5b3dab277a554a92a8e08d903b", "parents": [ "a92f71263af9d0ab77c260f709c0c079656221aa" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:33 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] zone_reclaim: configurable off node allocation period.\n\nCurrently the zone_reclaim code has a fixed window of 30 seconds of off node\nallocations should a local zone have no unused pagecache pages left. Reclaim\nwill be attempted again after this timeout period to avoid repeated useless\nscans for memory. This is also useful to established sufficiently large off\nnode allocation chunks to relieve the local node.\n\nIt may be beneficial to adjust that time period for some special situations.\nFor example if memory use was exceeding node capacity one may want to give up\nfor longer periods of time. If memory spikes intermittendly then one may want\nto shorten the time period to reduce the number of off node allocations.\n\nThis patch allows just that....\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "a92f71263af9d0ab77c260f709c0c079656221aa", "tree": "93aa7bf968ba108cc893b0dcc4de36fbf3b733bf", "parents": [ "aa3f18b3391ac305baa01faead3fdf9147daf54b" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:32 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:16 2006 -0800" }, "message": "[PATCH] zone_reclaim: partial scans instead of full scan\n\nInstead of scanning all the pages in a zone, imitate real swap and scan\nonly a portion of the pages and gradually scan more if we do not free up\nenough pages. This avoids a zone suddenly loosing all unused pagecache\npages (we may after all access some of these again so they deserve another\nchance) but it still frees up large chunks of memory if a zone only\ncontains unused pagecache pages.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "aa3f18b3391ac305baa01faead3fdf9147daf54b", "tree": "7e5e1f300058279bafdf7b576e072ced3e5f45d3", "parents": [ "4e6a510a74145585f4111d60d1b5fd450d795dd8" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:32 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:15 2006 -0800" }, "message": "[PATCH] zone_reclaim: do not unmap file backed pages\n\nzone_reclaim should leave that to the real swapper. We are only interested\nin evicting unmapped pages.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c84db23c6e587d3ab00a41c51fedf758e1f6ecd4", "tree": "f1e31810b14a71ccbb9963e018076212eb267ee9", "parents": [ "52a8363eae3872af15880292ff4e06d0fab36986" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:29 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:15 2006 -0800" }, "message": "[PATCH] zone_reclaim: minor fixes\n\n- If we only reclaim nr_pages then its okay to stay on node.\n Switch from \u003e to \u003e\u003d for the comparison.\n\n- vm_table[] entry for zone_reclaim_mode is a bit screwed up.\n\n- Add empty lines around shrink_zone to show that this is the\n central function to be called.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "52a8363eae3872af15880292ff4e06d0fab36986", "tree": "9ac9d0f00cc2e35e5d95c7be77874477e25847b4", "parents": [ "ce2ea89ba101d976907128441ba3aca72a8804b9" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:28 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:15 2006 -0800" }, "message": "[PATCH] mm: improve function of sc-\u003emay_writepage\n\nMake sc-\u003emay_writepage control the writeout behavior of shrink_list.\n\nRemove the laptop_mode trick from shrink_list and instead set may_writepage\nin try_to_free_pages properly.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "42c722d4cb4022e56ff200f3f5a58c0dfd7edac6", "tree": "a954fe12587951c01c61c0fc1ad2219a74adbbcb", "parents": [ "8928862398fef04a137e5673ac5fa9e797960c87" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:26 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:14 2006 -0800" }, "message": "[PATCH] zone_reclaim: reclaim on memory only node support\n\nZone reclaim is usually only run on the local node. Headless nodes do not\nhave any local processors. This patch checks for headless nodes and\nperforms zone reclaim on them.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8928862398fef04a137e5673ac5fa9e797960c87", "tree": "141f91c4dd56d323e6f5ce2d47cd1f1d22177aa7", "parents": [ "537421be79b94bcf620467f50dd9e38b739c2a00" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Wed Feb 01 03:05:25 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Feb 01 08:53:14 2006 -0800" }, "message": "[PATCH] Optimize off-node performance of zone reclaim\n\nEnsure that the performance of off node pages stays the same as before.\nOff node pagefault tests showed an 18% drop in performance without this\npatch.\n\n- Increase the timeout to 30 seconds to reduce the overhead.\n\n- Move all code possible out of the off node hot path for zone reclaim\n (Sorry Andrew, the struct initialization had to be sacrificed).\n The read_page_state() bit us there.\n\n- Check first for the timeout before any other checks.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9eeff2395e3cfd05c9b2e6074ff943a34b0c5c21", "tree": "20160098ec6ed8738cfecfc5f81181ad22b44e60", "parents": [ "f1fd1067ece574ab56e4a70878b9a5a1ed4c3c42" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Jan 18 17:42:31 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 18 19:20:17 2006 -0800" }, "message": "[PATCH] Zone reclaim: Reclaim logic\n\nSome bits for zone reclaim exists in 2.6.15 but they are not usable. This\npatch fixes them up, removes unused code and makes zone reclaim usable.\n\nZone reclaim allows the reclaiming of pages from a zone if the number of\nfree pages falls below the watermarks even if other zones still have enough\npages available. Zone reclaim is of particular importance for NUMA\nmachines. It can be more beneficial to reclaim a page than taking the\nperformance penalties that come with allocating a page on a remote zone.\n\nZone reclaim is enabled if the maximum distance to another node is higher\nthan RECLAIM_DISTANCE, which may be defined by an arch. By default\nRECLAIM_DISTANCE is 20. 20 is the distance to another node in the same\ncomponent (enclosure or motherboard) on IA64. The meaning of the NUMA\ndistance information seems to vary by arch.\n\nIf zone reclaim is not successful then no further reclaim attempts will\noccur for a certain time period (ZONE_RECLAIM_INTERVAL).\n\nThis patch was discussed before. See\n\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d113519961504207\u0026w\u003d2\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d113408418232531\u0026w\u003d2\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d113389027420032\u0026w\u003d2\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d113380938612205\u0026w\u003d2\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f1fd1067ece574ab56e4a70878b9a5a1ed4c3c42", "tree": "f7f9d092ac0ed8bd734245d803b563b5e751c8ad", "parents": [ "fc3012896337c83a056c496d7cfb0072e1591181" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Jan 18 17:42:30 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 18 19:20:17 2006 -0800" }, "message": "[PATCH] Zone reclaim: resurrect may_swap\n\nZone reclaim has a huge impact on NUMA performance (f.e. our maximum\nthroughput with XFS is raised from 4GB to 6GB/sec / page cache contamination\nof numa nodes destroys locality if one just does a large copy operation which\nresults in performance dropping for good until reboot).\n\nThis patch:\n\nResurrect may_swap in struct scan_control\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "053837fce7aa79025ed57656855df09f80175527", "tree": "05d7615894131a368fc4943f641b11acdd2ae694", "parents": [ "e236a166b2bc437769a9b8b5d19186a3761bde48" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Jan 18 17:42:27 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 18 19:20:17 2006 -0800" }, "message": "[PATCH] mm: migration page refcounting fix\n\nMigration code currently does not take a reference to target page\nproperly, so between unlocking the pte and trying to take a new\nreference to the page with isolate_lru_page, anything could happen to\nit.\n\nFix this by holding the pte lock until we get a chance to elevate the\nrefcount.\n\nOther small cleanups while we\u0027re here.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d0d963281ccb22e6f339bfdd75c6b2e31351929f", "tree": "ddeb3d1cf73675d71b21be8893b16cf5014c1bc5", "parents": [ "d498471133ff1f9586a06820beaeebc575fe2814" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Sun Jan 08 01:00:55 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:42 2006 -0800" }, "message": "[PATCH] SwapMig: Switch error handling in migrate_pages to use -Exx\n\nUse -Exxx instead of numeric return codes and cleanup the code in\nmigrate_pages() using -Exx error codes.\n\nConsolidate successful migration handling\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d498471133ff1f9586a06820beaeebc575fe2814", "tree": "c7cde93441692e3b32d83dfbf85858ab2d85e481", "parents": [ "ee27497df36823f2793212cad0997c044eb0e1eb" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:55 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:42 2006 -0800" }, "message": "[PATCH] SwapMig: Extend parameters for migrate_pages()\n\nExtend the parameters of migrate_pages() to allow the caller control over the\nfate of successfully migrated or impossible to migrate pages.\n\nSwap migration and direct migration will have the same interface after this\npatch so that patches can be independently applied to the policy layer and the\ncore migration code.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@muc.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ee27497df36823f2793212cad0997c044eb0e1eb", "tree": "854dded3b0277b0962b3c9a39c9cdb446654154b", "parents": [ "1480a540c98525640174a7eadd712378fcd6fd63" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:54 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:42 2006 -0800" }, "message": "[PATCH] SwapMig: Drop unused pages immediately\n\nDrop unused pages immediately\n\nIf a page is encountered that is only referenced by the migration code then\nthere is no reason to swap or migrate the page. Release the page by calling\nmove_to_lru().\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1480a540c98525640174a7eadd712378fcd6fd63", "tree": "28f2cc0aa819ff0aed30dd85bb16177d4a73002b", "parents": [ "8419c3181086c86664e8246bc997afc2e4ffba4f" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:53 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:42 2006 -0800" }, "message": "[PATCH] SwapMig: add_to_swap() avoid atomic allocations\n\nAdd gfp_mask to add_to_swap\n\nadd_to_swap does allocations with GFP_ATOMIC in order not to interfere with\nswapping. During migration we may have use add_to_swap extensively which may\nlead to out of memory errors.\n\nThis patch makes add_to_swap take a parameter that specifies the gfp mask.\nThe page migration code can then make add_to_swap use GFP_KERNEL.\n\nSigned-off-by: Hirokazu Takahashi \u003ctaka@valinux.co.jp\u003e\nSigned-off-by: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8419c3181086c86664e8246bc997afc2e4ffba4f", "tree": "25938e6f99bdaaffe8f6d357582eca56692b091c", "parents": [ "39743889aaf76725152f16aa90ca3c45f6d52da3" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:52 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:42 2006 -0800" }, "message": "[PATCH] SwapMig: CONFIG_MIGRATION fixes\n\nMove move_to_lru, putback_lru_pages and isolate_lru in section surrounded by\nCONFIG_MIGRATION saving some codesize for single processor kernels.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7cbe34cf86c673503b177ff47cfa2c7030dabb50", "tree": "9b39d7e8f11fed68242d1cb1f0c85dfcf96e3250", "parents": [ "49d2e9cc4544369635cd6f4ef6d5bb0f757079a7" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Sun Jan 08 01:00:49 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:41 2006 -0800" }, "message": "[PATCH] Swap Migration V5: Add CONFIG_MIGRATION for page migration support\n\nInclude page migration if the system is NUMA or having a memory model that\nallows distinct areas of memory (SPARSEMEM, DISCONTIGMEM).\n\nAnd:\n- Only include lru_add_drain_per_cpu if building for an SMP system.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "49d2e9cc4544369635cd6f4ef6d5bb0f757079a7", "tree": "d8c76c5224b05b812f96424a18b1e9205d90feae", "parents": [ "930d915252edda7042c944ed3c30194a2f9fe163" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:48 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:41 2006 -0800" }, "message": "[PATCH] Swap Migration V5: migrate_pages() function\n\nThis adds the basic page migration function with a minimal implementation that\nonly allows the eviction of pages to swap space.\n\nPage eviction and migration may be useful to migrate pages, to suspend\nprograms or for remapping single pages (useful for faulty pages or pages with\nsoft ECC failures)\n\nThe process is as follows:\n\nThe function wanting to migrate pages must first build a list of pages to be\nmigrated or evicted and take them off the lru lists via isolate_lru_page().\nisolate_lru_page determines that a page is freeable based on the LRU bit set.\n\nThen the actual migration or swapout can happen by calling migrate_pages().\n\nmigrate_pages does its best to migrate or swapout the pages and does multiple\npasses over the list. Some pages may only be swappable if they are not dirty.\n migrate_pages may start writing out dirty pages in the initial passes over\nthe pages. However, migrate_pages may not be able to migrate or evict all\npages for a variety of reasons.\n\nThe remaining pages may be returned to the LRU lists using putback_lru_pages().\n\nChangelog V4-\u003eV5:\n- Use the lru caches to return pages to the LRU\n\nChangelog V3-\u003eV4:\n- Restructure code so that applying patches to support full migration does\n require minimal changes. Rename swapout_pages() to migrate_pages().\n\nChangelog V2-\u003eV3:\n- Extract common code from shrink_list() and swapout_pages()\n\nSigned-off-by: Mike Kravetz \u003ckravetz@us.ibm.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: \"Michael Kerrisk\" \u003cmtk-manpages@gmx.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "930d915252edda7042c944ed3c30194a2f9fe163", "tree": "620452f11a9949943765b7a28e5b919f40f32b12", "parents": [ "21eac81f252fe31c3cf64b805a1e8652192f3a3b" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:47 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:41 2006 -0800" }, "message": "[PATCH] Swap Migration V5: PF_SWAPWRITE to allow writing to swap\n\nAdd PF_SWAPWRITE to control a processes permission to write to swap.\n\n- Use PF_SWAPWRITE in may_write_to_queue() instead of checking for kswapd\n and pdflush\n\n- Set PF_SWAPWRITE flag for kswapd and pdflush\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "21eac81f252fe31c3cf64b805a1e8652192f3a3b", "tree": "255662bda67f54ffde484046fd9ab9b0900ab409", "parents": [ "15316ba81aee6775d6079fb46c66c801989e7d10" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun Jan 08 01:00:45 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:41 2006 -0800" }, "message": "[PATCH] Swap Migration V5: LRU operations\n\nThis is the start of the `swap migration\u0027 patch series.\n\nSwap migration allows the moving of the physical location of pages between\nnodes in a numa system while the process is running. This means that the\nvirtual addresses that the process sees do not change. However, the system\nrearranges the physical location of those pages.\n\nThe main intent of page migration patches here is to reduce the latency of\nmemory access by moving pages near to the processor where the process\naccessing that memory is running.\n\nThe patchset allows a process to manually relocate the node on which its\npages are located through the MF_MOVE and MF_MOVE_ALL options while\nsetting a new memory policy.\n\nThe pages of process can also be relocated from another process using the\nsys_migrate_pages() function call. Requires CAP_SYS_ADMIN. The migrate_pages\nfunction call takes two sets of nodes and moves pages of a process that are\nlocated on the from nodes to the destination nodes.\n\nManual migration is very useful if for example the scheduler has relocated a\nprocess to a processor on a distant node. A batch scheduler or an\nadministrator can detect the situation and move the pages of the process\nnearer to the new processor.\n\nsys_migrate_pages() could be used on non-numa machines as well, to force all\nof a particualr process\u0027s pages out to swap, if someone thinks that\u0027s useful.\n\nLarger installations usually partition the system using cpusets into sections\nof nodes. Paul has equipped cpusets with the ability to move pages when a\ntask is moved to another cpuset. This allows automatic control over locality\nof a process. If a task is moved to a new cpuset then also all its pages are\nmoved with it so that the performance of the process does not sink\ndramatically (as is the case today).\n\nSwap migration works by simply evicting the page. The pages must be faulted\nback in. The pages are then typically reallocated by the system near the node\nwhere the process is executing.\n\nFor swap migration the destination of the move is controlled by the allocation\npolicy. Cpusets set the allocation policy before calling sys_migrate_pages()\nin order to move the pages as intended.\n\nNo allocation policy changes are performed for sys_migrate_pages(). This\nmeans that the pages may not faulted in to the specified nodes if no\nallocation policy was set by other means. The pages will just end up near the\nnode where the fault occurred.\n\nThere\u0027s another patch series in the pipeline which implements \"direct\nmigration\".\n\nThe direct migration patchset extends the migration functionality to avoid\ngoing through swap. The destination node of the relation is controllable\nduring the actual moving of pages. The crutch of using the allocation policy\nto relocate is not necessary and the pages are moved directly to the target.\nIts also faster since swap is not used.\n\nAnd sys_migrate_pages() can then move pages directly to the specified node.\nImplement functions to isolate pages from the LRU and put them back later.\n\nThis patch:\n\nAn earlier implementation was provided by Hirokazu Takahashi\n\u003ctaka@valinux.co.jp\u003e and IWAMOTO Toshihiro \u003ciwamoto@valinux.co.jp\u003e for the\nmemory hotplug project.\n\nFrom: Magnus\n\nThis breaks out isolate_lru_page() and putpack_lru_page(). Needed for swap\nmigration.\n\nSigned-off-by: Magnus Damm \u003cmagnus.damm@gmail.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9d0243bca345d5ce25d3f4b74b7facb3a6df1232", "tree": "a3a0a763bf83a483282dc1c3caab587941a98fc2", "parents": [ "bec6b0c89b234090681a4516e20ac5debe3e7c59" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sun Jan 08 01:00:39 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jan 08 20:12:40 2006 -0800" }, "message": "[PATCH] drop-pagecache\n\nAdd /proc/sys/vm/drop_caches. When written to, this will cause the kernel to\ndiscard as much pagecache and/or reclaimable slab objects as it can. THis\noperation requires root permissions.\n\nIt won\u0027t drop dirty data, so the user should run `sync\u0027 first.\n\nCaveats:\n\na) Holds inode_lock for exorbitant amounts of time.\n\nb) Needs to be taught about NUMA nodes: propagate these all the way through\n so the discarding can be controlled on a per-node basis.\n\nThis is a debugging feature: useful for getting consistent results between\nfilesystem benchmarks. We could possibly put it under a config option, but\nit\u0027s less than 300 bytes.\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "a74609fafa2e5cc31d558012abaaa55ec9ad9da4", "tree": "0be653692864d99da345b575dfe2083994ee1d21", "parents": [ "d3cb487149bd706aa6aeb02042332a450978dc1c" ], "author": { "name": "Nick Piggin", "email": "nickpiggin@yahoo.com.au", "time": "Fri Jan 06 00:11:20 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jan 06 08:33:29 2006 -0800" }, "message": "[PATCH] mm: page_state opt\n\nOptimise page_state manipulations by introducing interrupt unsafe accessors\nto page_state fields. Callers must provide their own locking (either\ndisable interrupts or not update from interrupt context).\n\nSwitch over the hot callsites that can easily be moved under interrupts off\nsections.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f3fe65122da05e1cd4c9140340d96ea2f95d0c49", "tree": "65f2bcdb0a9665123b5083d3aea7dae483593cbc", "parents": [ "80bfed904c690642db9d4178950735299160950b" ], "author": { "name": "Con Kolivas", "email": "kernel@kolivas.org", "time": "Fri Jan 06 00:11:15 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jan 06 08:33:28 2006 -0800" }, "message": "[PATCH] mm: add populated_zone() helper\n\nThere are numerous places we check whether a zone is populated or not.\n\nProvide a helper function to check for populated zones and convert all\nchecks for zone-\u003epresent_pages.\n\nSigned-off-by: Con Kolivas \u003ckernel@kolivas.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "210fe530305ee50cd889fe9250168228b2994f32", "tree": "4d22a28cf28abded5f77daef5b025c04d1ffea56", "parents": [ "41e9b63b35b52cf918a4ffdb8d77862ab824aa8b" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Fri Jan 06 00:11:14 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jan 06 08:33:27 2006 -0800" }, "message": "[PATCH] vmscan: balancing fix\n\nRevert a patch which went into 2.6.8-rc1. The changelog for that patch was:\n\n The shrink_zone() logic can, under some circumstances, cause far too many\n pages to be reclaimed. Say, we\u0027re scanning at high priority and suddenly\n hit a large number of reclaimable pages on the LRU.\n\n Change things so we bale out when SWAP_CLUSTER_MAX pages have been\n reclaimed.\n\nProblem is, this change caused significant imbalance in inter-zone scan\nbalancing by truncating scans of larger zones.\n\nSuppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone\nbalancing algorithm would require that if we\u0027re scanning 100 pages of\nZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will\ncause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are\nreclaimed. Thus effectively causing smaller zones to be scanned relatively\nharder than large ones.\n\nNow I need to remember what the workload was which caused me to write this\npatch originally, then fix it up in a different way...\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7756b9e4e321c3c83c7aa5b9532d3e7fd7ddeb4a", "tree": "fe59fcd970e97e3878a743a5b476420501f99f00", "parents": [ "bbfbb7cec9dd7266534b2b4b9c8be2fa425bbfc9" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Fri Jan 06 00:11:09 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jan 06 08:33:26 2006 -0800" }, "message": "[PATCH] kill last zone_reclaim() bits\n\nRemove the last bits of Martin\u0027s ill-fated sys_set_zone_reclaim().\n\nCc: Martin Hicks \u003cmort@wildopensource.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "994fc28c7b1e697ac56befe4aecabf23f0689f46", "tree": "da36d162e9bd077e9b5be385b28e2db90475c263", "parents": [ "7063fbf2261194f72ee75afca67b3b38b554b5fa" ], "author": { "name": "Zach Brown", "email": "zach.brown@oracle.com", "time": "Thu Dec 15 14:28:17 2005 -0800" }, "committer": { "name": "Joel Becker", "email": "joel.becker@oracle.com", "time": "Tue Jan 03 11:45:42 2006 -0800" }, "message": "[PATCH] add AOP_TRUNCATED_PAGE, prepend AOP_ to WRITEPAGE_ACTIVATE\n\nreadpage(), prepare_write(), and commit_write() callers are updated to\nunderstand the special return code AOP_TRUNCATED_PAGE in the style of\nwritepage() and WRITEPAGE_ACTIVATE. AOP_TRUNCATED_PAGE tells the caller that\nthe callee has unlocked the page and that the operation should be tried again\nwith a new page. OCFS2 uses this to detect and work around a lock inversion in\nits aop methods. There should be no change in behaviour for methods that don\u0027t\nreturn AOP_TRUNCATED_PAGE.\n\nWRITEPAGE_ACTIVATE is also prepended with AOP_ for consistency and they are\nmade enums so that kerneldoc can be used to document their semantics.\n\nSigned-off-by: Zach Brown \u003czach.brown@oracle.com\u003e\n" }, { "commit": "ea164d73a7a0b2b2be3a1d8c2a8a4dab8999fa9c", "tree": "60ad3933633f1e1858f9c506546daaa077e1f81d", "parents": [ "154f484b92e5c25c400f6903512c511644a49322" ], "author": { "name": "Andrea Arcangeli", "email": "andrea@suse.de", "time": "Mon Nov 28 13:44:15 2005 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Nov 28 14:42:26 2005 -0800" }, "message": "[PATCH] shrinker-\u003enr \u003d LONG_MAX means deadlock for icache\n\nWith Andrew Morton \u003cakpm@osdl.org\u003e\n\nThe slab scanning code tries to balance the scanning rate of slabs versus the\nscanning rate of LRU pages. To do this, it retains state concerning how many\nslabs have been scanned - if a particular slab shrinker didn\u0027t scan enough\nobjects, we remember that for next time, and scan more objects on the next\npass.\n\nThe problem with this is that with (say) a huge number of GFP_NOIO\ndirect-reclaim attempts, the number of objects which are to be scanned when we\nfinally get a GFP_KERNEL request can be huge. Because some shrinker handlers\njust bail out if !__GFP_FS.\n\nSo the patch clamps the number of objects-to-be-scanned to 2* the total number\nof objects in the slab cache.\n\nSigned-off-by: Andrea Arcangeli \u003candrea@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f7b7fd8f3ebbb2810d6893295aa984acd0fd30db", "tree": "01afc1edafc50a3c65ec8576c05c60da53d8d242", "parents": [ "a93a117eaa0bec426d4671a49bfa96a6fdcd2ac9" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Mon Nov 28 13:44:07 2005 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Nov 28 14:42:25 2005 -0800" }, "message": "[PATCH] temporarily disable swap token on memory pressure\n\nSome users (hi Zwane) have seen a problem when running a workload that\neats nearly all of physical memory - th system does an OOM kill, even\nwhen there is still a lot of swap free.\n\nThe problem appears to be a very big task that is holding the swap\ntoken, and the VM has a very hard time finding any other page in the\nsystem that is swappable.\n\nInstead of ignoring the swap token when sc-\u003epriority reaches 0, we could\nsimply take the swap token away from the memory hog and make sure we\ndon\u0027t give it back to the memory hog for a few seconds.\n\nThis patch resolves the problem Zwane ran into.\n\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7fb1d9fca5c6e3b06773b69165a73f3fb786b8ee", "tree": "21f8b7deeb8a7e1197edfccc610365a12d60322e", "parents": [ "51c6f666fceb3184eeff045dad4432b602cd648e" ], "author": { "name": "Rohit Seth", "email": "rohit.seth@intel.com", "time": "Sun Nov 13 16:06:43 2005 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Nov 13 18:14:12 2005 -0800" }, "message": "[PATCH] mm: __alloc_pages cleanup\n\nClean up of __alloc_pages.\n\nRestoration of previous behaviour, plus further cleanups by introducing an\n\u0027alloc_flags\u0027, removing the last of should_reclaim_zone.\n\nSigned-off-by: Rohit Seth \u003crohit.seth@intel.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4c21e2f2441dc5fbb957b030333f5a3f2d02dea7", "tree": "1f76d33bb1d76221c6424bc5fed080a4f91349a6", "parents": [ "b38c6845b695141259019e2b7c0fe6c32a6e720d" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Sat Oct 29 18:16:40 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Oct 29 21:40:42 2005 -0700" }, "message": "[PATCH] mm: split page table lock\n\nChristoph Lameter demonstrated very poor scalability on the SGI 512-way, with\na many-threaded application which concurrently initializes different parts of\na large anonymous area.\n\nThis patch corrects that, by using a separate spinlock per page table page, to\nguard the page table entries in that page, instead of using the mm\u0027s single\npage_table_lock. (But even then, page_table_lock is still used to guard page\ntable allocation, and anon_vma allocation.)\n\nIn this implementation, the spinlock is tucked inside the struct page of the\npage table page: with a BUILD_BUG_ON in case it overflows - which it would in\nthe case of 32-bit PA-RISC with spinlock debugging enabled.\n\nSplitting the lock is not quite for free: another cacheline access. Ideally,\nI suppose we would use split ptlock only for multi-threaded processes on\nmulti-cpu machines; but deciding that dynamically would have its own costs.\nSo for now enable it by config, at some number of cpus - since the Kconfig\nlanguage doesn\u0027t support inequalities, let preprocessor compare that with\nNR_CPUS. But I don\u0027t think it\u0027s worth being user-configurable: for good\ntesting of both split and unsplit configs, split now at 4 cpus, and perhaps\nchange that to 8 later.\n\nThere is a benefit even for singly threaded processes: kswapd can be attacking\none part of the mm while another part is busy faulting.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c340010e4bf824d969a89fa192ecc7a526c0cd24", "tree": "a459fba71b05b3b14dc1e32739cc2520dd0e57be", "parents": [ "b57b98d147ef98758886a39efb94f3254542c39b" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Sat Oct 29 18:15:51 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Oct 29 21:40:36 2005 -0700" }, "message": "[PATCH] shrink_list(): skip anon pages if not may_swap\n\nMartin Hicks\u0027 page cache reclaim patch added the \u0027may_swap\u0027 flag to the\nscan_control struct; and modified shrink_list() not to add anon pages to\nthe swap cache if may_swap is not asserted.\n\nRef: http://marc.theaimsgroup.com/?l\u003dlinux-mm\u0026m\u003d111461480725322\u0026w\u003d4\n\nHowever, further down, if the page is mapped, shrink_list() calls\ntry_to_unmap() which will call try_to_unmap_one() via try_to_unmap_anon ().\n try_to_unmap_one() will BUG_ON() an anon page that is NOT in the swap\ncache. Martin says he never encountered this path in his testing, but\nagrees that it might happen.\n\nThis patch modifies shrink_list() to skip anon pages that are not already\nin the swap cache when !may_swap, rather than just not adding them to the\ncache.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6daa0e28627abf362138244a620a821a9027d816", "tree": "5ca9cbc421cc1adf228cdd30cd627bca8be6242c", "parents": [ "af4ca457eaf2d6682059c18463eb106e2ce58198" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Oct 21 03:18:50 2005 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Oct 28 08:16:47 2005 -0700" }, "message": "[PATCH] gfp_t: mm/* (easy parts)\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3d80636a0d5f056ffc26472d05b6027a7a9f6e1c", "tree": "39b3dbae53938728c55b2312190561b858431d92", "parents": [ "688ce17b8599abc548b406c00e4d18ae0dec954f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 16 17:36:06 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 16 17:36:06 2005 -0700" }, "message": "Fix memory ordering bug in page reclaim\n\nAs noticed by Nick Piggin, we need to make sure that we check the page\ncount before we check for PageDirty, since the dirty check is only valid\nif the count implies that we\u0027re the only possible ones holding the page.\n\nWe always did do this, but the code needs a read-memory-barrier to make\nsure that the orderign is also honored by the CPU.\n\n(The writer side is ordered due to the atomic decrement and test on the\npage count, see the discussion on linux-kernel)\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8d0986e289a4b018fec87fcc49538945fb401f37", "tree": "f81d6343e3722605eb662b85f0ad3ba25b71919a", "parents": [ "7979aca38b78ffe6a65ef309f26721c527104eaf" ], "author": { "name": "Con Kolivas", "email": "kernel@kolivas.org", "time": "Tue Sep 13 01:25:07 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Sep 13 08:22:28 2005 -0700" }, "message": "[PATCH] vm: kswapd cleanup: use pgdat\n\nUse the pgdat pointer we\u0027ve already defined in wakeup_kswapd\n\nSigned-off-by: Con Kolivas \u003ckernel@kolivas.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9bf2229f8817677127a60c177aefce1badd22d7b", "tree": "06e95863a26b197233081db1dafd869dfd231950", "parents": [ "f90b1d2f1aaaa40c6519a32e69615edc25bb97d5" ], "author": { "name": "Paul Jackson", "email": "pj@sgi.com", "time": "Tue Sep 06 15:18:12 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Sep 07 16:57:40 2005 -0700" }, "message": "[PATCH] cpusets: formalize intermediate GFP_KERNEL containment\n\nThis patch makes use of the previously underutilized cpuset flag\n\u0027mem_exclusive\u0027 to provide what amounts to another layer of memory placement\nresolution. With this patch, there are now the following four layers of\nmemory placement available:\n\n 1) The whole system (interrupt and GFP_ATOMIC allocations can use this),\n 2) The nearest enclosing mem_exclusive cpuset (GFP_KERNEL allocations can use),\n 3) The current tasks cpuset (GFP_USER allocations constrained to here), and\n 4) Specific node placement, using mbind and set_mempolicy.\n\nThese nest - each layer is a subset (same or within) of the previous.\n\nLayer (2) above is new, with this patch. The call used to check whether a\nzone (its node, actually) is in a cpuset (in its mems_allowed, actually) is\nextended to take a gfp_mask argument, and its logic is extended, in the case\nthat __GFP_HARDWALL is not set in the flag bits, to look up the cpuset\nhierarchy for the nearest enclosing mem_exclusive cpuset, to determine if\nplacement is allowed. The definition of GFP_USER, which used to be identical\nto GFP_KERNEL, is changed to also set the __GFP_HARDWALL bit, in the previous\ncpuset_gfp_hardwall_flag patch.\n\nGFP_ATOMIC and GFP_KERNEL allocations will stay within the current tasks\ncpuset, so long as any node therein is not too tight on memory, but will\nescape to the larger layer, if need be.\n\nThe intended use is to allow something like a batch manager to handle several\njobs, each job in its own cpuset, but using common kernel memory for caches\nand such. Swapper and oom_kill activity is also constrained to Layer (2). A\ntask in or below one mem_exclusive cpuset should not cause swapping on nodes\nin another non-overlapping mem_exclusive cpuset, nor provoke oom_killing of a\ntask in another such cpuset. Heavy use of kernel memory for i/o caching and\nsuch by one job should not impact the memory available to jobs in other\nnon-overlapping mem_exclusive cpusets.\n\nThis patch enables providing hardwall, inescapable cpusets for memory\nallocations of each job, while sharing kernel memory allocations between\nseveral jobs, in an enclosing mem_exclusive cpuset.\n\nLike Dinakar\u0027s patch earlier to enable administering sched domains using the\ncpu_exclusive flag, this patch also provides a useful meaning to a cpuset flag\nthat had previously done nothing much useful other than restrict what cpuset\nconfigurations were allowed.\n\nSigned-off-by: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "53e9a6159fdc6419874ce4d86d3577dbedc77b62", "tree": "7c7f15325569cf5e02dafc1974fb080154616058", "parents": [ "bce5f6ba340b09d8b29902add204bb95a6d3d88b" ], "author": { "name": "Martin Hicks", "email": "mort@bork.org", "time": "Sat Sep 03 15:54:51 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@evo.osdl.org", "time": "Mon Sep 05 00:05:44 2005 -0700" }, "message": "[PATCH] VM: zone reclaim atomic ops cleanup\n\nChristoph Lameter and Marcelo Tosatti asked to get rid of the\natomic_inc_and_test() to cleanup the atomic ops in the zone reclaim code.\n\nSigned-off-by: Martin Hicks \u003cmort@sgi.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bce5f6ba340b09d8b29902add204bb95a6d3d88b", "tree": "1cfeea969fa5848f0a8d31394829aec5c8571a79", "parents": [ "242e54686257493f0b10ac557e730419d9af7d24" ], "author": { "name": "Martin Hicks", "email": "mort@sgi.com", "time": "Sat Sep 03 15:54:50 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@evo.osdl.org", "time": "Mon Sep 05 00:05:44 2005 -0700" }, "message": "[PATCH] VM: add capabilites check to set_zone_reclaim\n\nAdd a capability check to sys_set_zone_reclaim(). This syscall is not\nsomething that should be available to a user.\n\nSigned-off-by: Martin Hicks \u003cmort@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "687a21cee17000177b1935896b9b475acf136678", "tree": "41e59684ae6479e84b34edc46972ce32c2cc58b7", "parents": [ "05133fc498e788e1c1ca4e906f9e05d9779fd63b" ], "author": { "name": "Pekka J Enberg", "email": "penberg@cs.Helsinki.FI", "time": "Tue Jun 28 20:44:55 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 28 21:20:31 2005 -0700" }, "message": "[PATCH] rename wakeup_bdflush to wakeup_pdflush\n\nSigned-off-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3e1d1d28d99dabe63c64f7f40f1ca1d646de1f73", "tree": "d1e7c1e2e8902072042aefc3a7976b271cf76021", "parents": [ "b3e112bcc19abd8e9657dca34a87316786e096f3" ], "author": { "name": "Christoph Lameter", "email": "christoph@lameter.com", "time": "Fri Jun 24 23:13:50 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Jun 25 17:10:13 2005 -0700" }, "message": "[PATCH] Cleanup patch for process freezing\n\n1. Establish a simple API for process freezing defined in linux/include/sched.h:\n\n frozen(process)\t\tCheck for frozen process\n freezing(process)\t\tCheck if a process is being frozen\n freeze(process)\t\tTell a process to freeze (go to refrigerator)\n thaw_process(process)\tRestart process\n frozen_process(process)\tProcess is frozen now\n\n2. Remove all references to PF_FREEZE and PF_FROZEN from all\n kernel sources except sched.h\n\n3. Fix numerous locations where try_to_freeze is manually done by a driver\n\n4. Remove the argument that is no longer necessary from two function calls.\n\n5. Some whitespace cleanup\n\n6. Clear potential race in refrigerator (provides an open window of PF_FREEZE\n cleared before setting PF_FROZEN, recalc_sigpending does not check\n PF_FROZEN).\n\nThis patch does not address the problem of freeze_processes() violating the rule\nthat a task may only modify its own flags by setting PF_FREEZE. This is not clean\nin an SMP environment. freeze(process) is therefore not SMP safe!\n\nSigned-off-by: Christoph Lameter \u003cchristoph@lameter.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1ad539b2bd89bf2e129123eb24d5bcc4484a35de", "tree": "e416e208cdbd5d9890d39e39384e4ec913c26ef6", "parents": [ "cbe37d093707762fc0abb280781e6a82a9d8d568" ], "author": { "name": "Darren Hart", "email": "dvhltc@us.ibm.com", "time": "Tue Jun 21 17:14:53 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 21 18:46:17 2005 -0700" }, "message": "[PATCH] vm: try_to_free_pages unused argument\n\ntry_to_free_pages accepts a third argument, order, but hasn\u0027t used it since\nbefore 2.6.0. The following patch removes the argument and updates all the\ncalls to try_to_free_pages.\n\nSigned-off-by: Darren Hart \u003cdvhltc@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1e7e5a9048b30c57ba1ddaa6cdf59b21b65cde99", "tree": "26eb9c483718ca1a0fad23597c0dfd3a69e9f080", "parents": [ "0c35bbadc59f5ed105c34471143eceb4c0dd9c95" ], "author": { "name": "Martin Hicks", "email": "mort@sgi.com", "time": "Tue Jun 21 17:14:43 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 21 18:46:14 2005 -0700" }, "message": "[PATCH] VM: rate limit early reclaim\n\nWhen early zone reclaim is turned on the LRU is scanned more frequently when a\nzone is low on memory. This limits when the zone reclaim can be called by\nskipping the scan if another thread (either via kswapd or sync reclaim) is\nalready reclaiming from the zone.\n\nSigned-off-by: Martin Hicks \u003cmort@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "753ee728964e5afb80c17659cc6c3a6fd0a42fe0", "tree": "41c9a7700d0858c1f77c5bdaba97e5b636f69b06", "parents": [ "bfbb38fb808ac23ef44472d05d9bb36edfb49ed0" ], "author": { "name": "Martin Hicks", "email": "mort@sgi.com", "time": "Tue Jun 21 17:14:41 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 21 18:46:14 2005 -0700" }, "message": "[PATCH] VM: early zone reclaim\n\nThis is the core of the (much simplified) early reclaim. The goal of this\npatch is to reclaim some easily-freed pages from a zone before falling back\nonto another zone.\n\nOne of the major uses of this is NUMA machines. With the default allocator\nbehavior the allocator would look for memory in another zone, which might be\noff-node, before trying to reclaim from the current zone.\n\nThis adds a zone tuneable to enable early zone reclaim. It is selected on a\nper-zone basis and is turned on/off via syscall.\n\nAdding some extra throttling on the reclaim was also required (patch\n4/4). Without the machine would grind to a crawl when doing a \"make -j\"\nkernel build. Even with this patch the System Time is higher on\naverage, but it seems tolerable. Here are some numbers for kernbench\nruns on a 2-node, 4cpu, 8Gig RAM Altix in the \"make -j\" run:\n\n\t\t\twall user sys %cpu ctx sw. sleeps\n\t\t\t---- ---- --- ---- ------ ------\nNo patch\t\t1009 1384 847 258 298170 504402\nw/patch, no reclaim 880 1376 667 288 254064 396745\nw/patch \u0026 reclaim 1079 1385 926 252 291625 548873\n\nThese numbers are the average of 2 runs of 3 \"make -j\" runs done right\nafter system boot. Run-to-run variability for \"make -j\" is huge, so\nthese numbers aren\u0027t terribly useful except to seee that with reclaim\nthe benchmark still finishes in a reasonable amount of time.\n\nI also looked at the NUMA hit/miss stats for the \"make -j\" runs and the\nreclaim doesn\u0027t make any difference when the machine is thrashing away.\n\nDoing a \"make -j8\" on a single node that is filled with page cache pages\ntakes 700 seconds with reclaim turned on and 735 seconds without reclaim\n(due to remote memory accesses).\n\nThe simple zone_reclaim syscall program is at\nhttp://www.bork.org/~mort/sgi/zone_reclaim.c\n\nSigned-off-by: Martin Hicks \u003cmort@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bfbb38fb808ac23ef44472d05d9bb36edfb49ed0", "tree": "19d26b575bf0ff1e2b3ec2c8ee12310154fdead5", "parents": [ "295ab93497ec703f7d6eaf0787dd9768b83035fe" ], "author": { "name": "Martin Hicks", "email": "mort@sgi.com", "time": "Tue Jun 21 17:14:40 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 21 18:46:14 2005 -0700" }, "message": "[PATCH] VM: add may_swap flag to scan_control\n\nHere\u0027s the next round of these patches. These are totally different in\nan attempt to meet the \"simpler\" request after the last patches. For\nreference the earlier threads are:\n\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d110839604924587\u0026w\u003d2\nhttp://marc.theaimsgroup.com/?l\u003dlinux-mm\u0026m\u003d111461480721249\u0026w\u003d2\n\nThis set of patches replaces my other vm- patches that are currently in\n-mm. So they\u0027re against 2.6.12-rc5-mm1 about half way through the -mm\npatchset.\n\nAs I said already this patch is a lot simpler. The reclaim is turned on\nor off on a per-zone basis using a syscall. I haven\u0027t tested the x86\nsyscall, so it might be wrong. It uses the existing reclaim/pageout\ncode with the small addition of a may_swap flag to scan_control\n(patch 1/4).\n\nI also added __GFP_NORECLAIM (patch 3/4) so that certain allocation\ntypes can be flagged to never cause reclaim. This was a deficiency\nthat was in all of my earlier patch sets. Previously, doing a big\nbuffered read would fill one zone with page cache and then start to\nreclaim from that same zone, leaving the other zones untouched.\n\nAdding some extra throttling on the reclaim was also required (patch\n4/4). Without the machine would grind to a crawl when doing a \"make -j\"\nkernel build. Even with this patch the System Time is higher on\naverage, but it seems tolerable. Here are some numbers for kernbench\nruns on a 2-node, 4cpu, 8Gig RAM Altix in the \"make -j\" run:\n\n\t\t\twall user sys %cpu ctx sw. sleeps\n\t\t\t---- ---- --- ---- ------ ------\nNo patch\t\t1009 1384 847 258 298170 504402\nw/patch, no reclaim 880 1376 667 288 254064 396745\nw/patch \u0026 reclaim 1079 1385 926 252 291625 548873\n\nThese numbers are the average of 2 runs of 3 \"make -j\" runs done right\nafter system boot. Run-to-run variability for \"make -j\" is huge, so\nthese numbers aren\u0027t terribly useful except to seee that with reclaim\nthe benchmark still finishes in a reasonable amount of time.\n\nI also looked at the NUMA hit/miss stats for the \"make -j\" runs and the\nreclaim doesn\u0027t make any difference when the machine is thrashing away.\n\nDoing a \"make -j8\" on a single node that is filled with page cache pages\ntakes 700 seconds with reclaim turned on and 735 seconds without reclaim\n(due to remote memory accesses).\n\nThe simple zone_reclaim syscall program is at\nhttp://www.bork.org/~mort/sgi/zone_reclaim.c\n\nThis patch:\n\nThis adds an extra switch to the scan_control struct. It simply lets the\nreclaim code know if its allowed to swap pages out.\n\nThis was required for a simple per-zone reclaimer. Without this addition\npages would be swapped out as soon as a zone ran out of memory and the early\nreclaim kicked in.\n\nSigned-off-by: Martin Hicks \u003cmort@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b15e0905f2b9964fc7426fecab57445e96021b61", "tree": "bc1b3606cf282f88cd6598de22190eff6708affa", "parents": [ "39c715b71740c4a78ba4769fb54826929bac03cb" ], "author": { "name": "akpm@osdl.org", "email": "akpm@osdl.org", "time": "Tue Jun 21 17:14:35 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Tue Jun 21 18:46:13 2005 -0700" }, "message": "[PATCH] vmscan: notice slab shrinking\n\nFix a problem identified by Andrea Arcangeli \u003candrea@suse.de\u003e\n\nkswapd will set a zone into all_unreclaimable state if it sees that we\u0027re not\nsuccessfully reclaiming LRU pages. But that fails to notice that we\u0027re\nsuccessfully reclaiming slab obects, so we can set all_unreclaimable too soon.\n\nSo change shrink_slab() to return a success indication if it actually\nreclaimed some objects, and don\u0027t assume that the zone is all_unreclaimable if\nthat is true. This means that we won\u0027t enter all_unreclaimable state if we\nare successfully freeing slab objects but we\u0027re not yet actually freeing slab\npages, due to internal fragmentation.\n\n(hm, this has a shortcoming. We could be successfully freeing ZONE_NORMAL\nslab objects while being really oom on ZONE_DMA. If that happens then kswapd\nmight burn a lot of CPU. But given that there might be some slab objects in\nZONE_DMA, perhaps that is appropriate.)\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "323aca6c0bda611d0f31b3234d9fe291d31a9207", "tree": "d1ece2a5bd91f56981f7773f264843828e9b71c6", "parents": [ "79befd0c08c4766f8fa27e37ac2a70e40840a56a" ], "author": { "name": "akpm@osdl.org", "email": "akpm@osdl.org", "time": "Sat Apr 16 15:24:06 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:24:06 2005 -0700" }, "message": "[PATCH] vmscan: pageout(): remove unneeded test\n\n\r)\n\n\n\nWe only call pageout() for dirty pages, so this test is redundant.\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }