)]}' { "log": [ { "commit": "83ba7b071f30f7c01f72518ad72d5cd203c27502", "tree": "4737320dcce72cfff4d87d835e4f78428eca7ef5", "parents": [ "edadfb10ba35da7253541e4155aa92eff758ebe6" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jul 06 08:59:53 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 06 08:59:53 2010 +0200" }, "message": "writeback: simplify the write back thread queue\n\nFirst remove items from work_list as soon as we start working on them. This\nmeans we don\u0027t have to track any pending or visited state and can get\nrid of all the RCU magic freeing the work items - we can simply free\nthem once the operation has finished. Second use a real completion for\ntracking synchronous requests - if the caller sets the completion pointer\nwe complete it, otherwise use it as a boolean indicator that we can free\nthe work item directly. Third unify struct wb_writeback_args and struct\nbdi_work into a single data structure, wb_writeback_work. Previous we\nset all parameters into a struct wb_writeback_args, copied it into\nstruct bdi_work, copied it again on the stack to use it there. Instead\nof just allocate one structure dynamically or on the stack and use it\nall the way through the stack.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "edadfb10ba35da7253541e4155aa92eff758ebe6", "tree": "a3c676f7b2c9b301d7e1948febeaba76ea1c5850", "parents": [ "9c3a8ee8a1d72c5c0d7fbdf426d80e270ddfa54c" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Thu Jun 10 12:07:54 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 06 08:54:08 2010 +0200" }, "message": "writeback: split writeback_inodes_wb\n\nThe case where we have a superblock doesn\u0027t require a loop here as we scan\nover all inodes in writeback_sb_inodes. Split it out into a separate helper\nto make the code simpler. This also allows to get rid of the sb member in\nstruct writeback_control, which was rather out of place there.\n\nAlso update the comments in writeback_sb_inodes that explain the handling\nof inodes from wrong superblocks.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "9c3a8ee8a1d72c5c0d7fbdf426d80e270ddfa54c", "tree": "fa131760a61f66afeede852622ede0d716965489", "parents": [ "06d738fa9155ff16dba3d7e501ba4581d01a98cb" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Thu Jun 10 12:07:27 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 06 08:54:03 2010 +0200" }, "message": "writeback: remove writeback_inodes_wbc\n\nThis was just an odd wrapper around writeback_inodes_wb. Removing this\nalso allows to get rid of the bdi member of struct writeback_control\nwhich was rather out of place there.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "06d738fa9155ff16dba3d7e501ba4581d01a98cb", "tree": "ea1e3a1632207c9b0ad7fedc47eaeb1c35e5d8bc", "parents": [ "19c9a49b432f245c6293508d164a4350f1f2c601" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Thu Jul 01 08:26:34 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Thu Jul 01 08:26:34 2010 +0200" }, "message": "fs-writeback: fix kernel-doc warnings\n\nFix kernel-doc to match the function\u0027s changed args.\n\nWarning(fs/fs-writeback.c:190): No description found for parameter \u0027args\u0027\nWarning(fs/fs-writeback.c:190): Excess function parameter \u0027sb\u0027 description in \u0027bdi_queue_work_onstack\u0027\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "29cb48594b873f6193d6327097e504bd3e2314de", "tree": "1c93364fd70d93d42c6749c261f96f84a66d71e2", "parents": [ "334132ae921a14ac2b2ba48e174136f7f2c9aae1" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Jun 09 15:31:01 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:08 2010 +0200" }, "message": "writeback: fix pin_sb_for_writeback\n\nWe need to check for s_instances to make sure we don\u0027t bother working\nagainst a filesystem that is beeing unmounted, and we need to call\nput_super to make sure a superblock is freed when we race against\numount. Also no need to keep sb_lock after we got a reference on it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "334132ae921a14ac2b2ba48e174136f7f2c9aae1", "tree": "4367a78d60365cc4d8c751c81c06d0b6d736bdbf", "parents": [ "c5444198ca210498e8ac0ba121b4cd3537aa12f7" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Jun 09 14:28:43 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:08 2010 +0200" }, "message": "writeback: add missing requeue_io in writeback_inodes_wb\n\nIn \"writeback: fix writeback_inodes_wb from writeback_inodes_sb\" I\naccidentally removed the requeue_io if we need to skip a superblock\nbecause we can\u0027t pin it. Add it back, otherwise we\u0027re getting spurious\nlockups after multiple xfstests runs.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "c5444198ca210498e8ac0ba121b4cd3537aa12f7", "tree": "c423d38fe1ac7f51a48e455a19ecbe2354811fca", "parents": [ "b8c2f3474f1077599ec6e90c2f263f17055cc3d8" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:15:15 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:08 2010 +0200" }, "message": "writeback: simplify and split bdi_start_writeback\n\nbdi_start_writeback now never gets a superblock passed, so we can just remove\nthat case. And to further untangle the code and flatten the call stack\nsplit it into two trivial helpers for it\u0027s two callers.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "b8c2f3474f1077599ec6e90c2f263f17055cc3d8", "tree": "aedccfc59c7fd5592311534395eacf8afd1c956f", "parents": [ "d19de7edf59cdd586777b009e0e8fbe5412dd35f" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:15:07 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:07 2010 +0200" }, "message": "writeback: simplify wakeup_flusher_threads\n\nbdi_writeback_all only has one caller, so fold it to simplify the code and\nflatten the call stack.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "d19de7edf59cdd586777b009e0e8fbe5412dd35f", "tree": "8b6b56c705d7ed6fc22fe53b4d49b41372874afa", "parents": [ "cf37e972478ec58a8a54a6b4f951815f0ae28f78" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:14:58 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:07 2010 +0200" }, "message": "writeback: fix writeback_inodes_wb from writeback_inodes_sb\n\nWhen we call writeback_inodes_wb from writeback_inodes_sb we always have\ns_umount held, which currently makes the whole operation a no-op.\n\nBut if we are called to write out inodes for a specific superblock we always\nhave s_umount held, so replace the incorrect logic checking for WB_SYNC_ALL\nwhich only worked by coincidence with the proper check for an explicit\nsuperblock argument.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "cf37e972478ec58a8a54a6b4f951815f0ae28f78", "tree": "b14d75074692ddb213e22e098a64087950f4cf78", "parents": [ "3c4d716538f3eefb1c1f10961a047a6456a2b590" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:14:51 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:07 2010 +0200" }, "message": "writeback: enforce s_umount locking in writeback_inodes_sb\n\nMake sure that not only sync_filesystem but all callers of writeback_inodes_sb\nhave the superblock protected against remount. As-is this disables all\nfunctionality for these callers, but the next patch relies on this locking to\nfix writeback_inodes_sb for sync_filesystem.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "3c4d716538f3eefb1c1f10961a047a6456a2b590", "tree": "3cfc50c18cc3d2351ddac4309e8f228e22faed71", "parents": [ "7f0e7bed936a0c422641a046551829a01341dd80" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:14:43 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:07 2010 +0200" }, "message": "writeback: queue work on stack in writeback_inodes_sb\n\nIf we want to rely on s_umount in the caller we need to wait for completion\nof the I/O submission before returning to the caller. Refactor\nbdi_sync_writeback into a bdi_queue_work_onstack helper and use it for this\ncase.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "7f0e7bed936a0c422641a046551829a01341dd80", "tree": "6b5fd4a8e11253819c883e409b612fc26c57235e", "parents": [ "7908a9e5fc3f9a679b1777ed231a03636c068446" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:14:34 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:07 2010 +0200" }, "message": "writeback: fix writeback completion notifications\n\nThe code dealing with bdi_work-\u003estate and completion of a bdi_work is a\nmajor mess currently. This patch makes sure we directly use one set of\nflags to deal with it, and use it consistently, which means:\n\n - always notify about completion from the rcu callback. We only ever\n wait for it from on-stack callers, so this simplification does not\n even cause a theoretical slowdown currently. It also makes sure we\n don\u0027t miss out on the notification if we ever add other callers to\n wait for it.\n - make earlier completion notification depending on the on-stack\n allocation, not the sync mode. If we introduce new callers that\n want to do WB_SYNC_NONE writeback from on-stack callers this will\n be nessecary.\n\nAlso rename bdi_wait_on_work_clear to bdi_wait_on_work_done and inline\na few small functions into their only caller to make the code\nunderstandable.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "b4ca761577535b2b4d153689ee97342797dfff05", "tree": "29054d55508f1faa22ec32acf7c245751af03348", "parents": [ "28f4197e5d4707311febeec8a0eb97cb5fd93c97", "67a3e12b05e055c0415c556a315a3d3eb637e29e" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 12:42:12 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 12:42:12 2010 +0200" }, "message": "Merge branch \u0027master\u0027 into for-linus\n\nConflicts:\n\tfs/pipe.c\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "0e3c9a2284f5417f196e327c254d0b84c9ee8929", "tree": "e3fb40ebe7d042b4b3c1042bc7f2edaf7fb6eee0", "parents": [ "f17625b318d9b151e7bd41e31223e9d89b2aaa77" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 11:08:43 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 11:08:43 2010 +0200" }, "message": "Revert \"writeback: fix WB_SYNC_NONE writeback from umount\"\n\nThis reverts commit e913fc825dc685a444cb4c1d0f9d32f372f59861.\n\nWe are investigating a hang associated with the WB_SYNC_NONE changes,\nso revert them for now.\n\nConflicts:\n\n\tfs/fs-writeback.c\n\tmm/page-writeback.c\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "f17625b318d9b151e7bd41e31223e9d89b2aaa77", "tree": "6b4f04ff35d9bfcc73fc4d3f08120347b0ab4706", "parents": [ "0ae0b5d0557264bad65e22f1e2da4b83a02c4535" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 01 11:05:22 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 01 11:05:22 2010 +0200" }, "message": "Revert \"writeback: ensure that WB_SYNC_NONE writeback with sb pinned is sync\"\n\nThis reverts commit 7c8a3554c683f512dbcee26faedb42e4c05f12fa.\n\nWe are investigating a hang associated with the WB_SYNC_NONE changes,\nso revert them for now.\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "58a9d3d8db06ca2ec31f64ec49ab0aeb89971b85", "tree": "70c695b6473d4d25b32a2946e053742f6c49755e", "parents": [ "ec95f53aa6ed62ba68660cb19c8474ebe9025cce" ], "author": { "name": "Richard Kennedy", "email": "richard@rsk.demon.co.uk", "time": "Mon May 24 14:32:38 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "fs-writeback: check sync bit earlier in inode_wait_for_writeback\n\nWhen wb_writeback() hasn\u0027t written anything it will re-acquire the inode\nlock before calling inode_wait_for_writeback.\n\nThis change tests the sync bit first so that is doesn\u0027t need to drop \u0026\nre-acquire the lock if the inode became available while wb_writeback() was\nwaiting to get the lock.\n\nSigned-off-by: Richard Kennedy \u003crichard@rsk.demon.co.uk\u003e\nCc: Alexander Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e8bebe2f71d26871b0970ae1d9cf0ed3cdd9569d", "tree": "c0d82cbd11daaf579b74121c6641d58947091094", "parents": [ "6109e2ce2600e2db26cd0424bb9c6ed019723288", "82f3952c02add60b15eea9151d4d99b6b82066c6" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 21 19:37:45 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 21 19:37:45 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (69 commits)\n fix handling of offsets in cris eeprom.c, get rid of fake on-stack files\n get rid of home-grown mutex in cris eeprom.c\n switch ecryptfs_write() to struct inode *, kill on-stack fake files\n switch ecryptfs_get_locked_page() to struct inode *\n simplify access to ecryptfs inodes in -\u003ereadpage() and friends\n AFS: Don\u0027t put struct file on the stack\n Ban ecryptfs over ecryptfs\n logfs: replace inode uid,gid,mode initialization with helper function\n ufs: replace inode uid,gid,mode initialization with helper function\n udf: replace inode uid,gid,mode init with helper\n ubifs: replace inode uid,gid,mode initialization with helper function\n sysv: replace inode uid,gid,mode initialization with helper function\n reiserfs: replace inode uid,gid,mode initialization with helper function\n ramfs: replace inode uid,gid,mode initialization with helper function\n omfs: replace inode uid,gid,mode initialization with helper function\n bfs: replace inode uid,gid,mode initialization with helper function\n ocfs2: replace inode uid,gid,mode initialization with helper function\n nilfs2: replace inode uid,gid,mode initialization with helper function\n minix: replace inode uid,gid,mode init with helper\n ext4: replace inode uid,gid,mode init with helper\n ...\n\nTrivial conflict in fs/fs-writeback.c (mark bitfields unsigned)\n" }, { "commit": "52957fe1c709d5ca3732456d73f4e4d95492c72c", "tree": "c1e1f92cefbc9c03620af6c97ba50d8de1011f8e", "parents": [ "9a2296832c43da93a88e1edd59f3d17acffca36c" ], "author": { "name": "H Hartley Sweeten", "email": "hartleys@visionengravers.com", "time": "Thu Apr 01 20:36:30 2010 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri May 21 18:31:22 2010 -0400" }, "message": "fs-writeback.c: bitfields should be unsigned\n\nThis fixes sparse noise:\n error: dubious one-bit signed bitfield\n\nSigned-off-by: H Hartley Sweeten \u003chsweeten@visionengravers.com\u003e\nCc: Alexander Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "f9eadbbd424c083b8005c7b738f644611b9ef489", "tree": "edc73e0fa56de566af7672f6f80579ec317d373f", "parents": [ "7c8a3554c683f512dbcee26faedb42e4c05f12fa" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 18 14:31:45 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 21 20:00:25 2010 +0200" }, "message": "writeback: bdi_writeback_task() must set task state before calling schedule()\n\nCalling schedule without setting the task state to non-running will\nreturn immediately, so ensure that we set it properly and check our\nsleep conditions after doing so.\n\nThis is a fixup for commit 69b62d01.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "7c8a3554c683f512dbcee26faedb42e4c05f12fa", "tree": "ece0d1b79ccc1f596b0ccd0217b584c27a3ff414", "parents": [ "2db4e42eaceabec42f738f3895300632cd375e67" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 18 14:29:29 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 21 20:00:25 2010 +0200" }, "message": "writeback: ensure that WB_SYNC_NONE writeback with sb pinned is sync\n\nEven if the writeout itself isn\u0027t a data integrity operation, we need\nto ensure that the caller doesn\u0027t drop the sb umount sem before we\nhave actually done the writeback.\n\nThis is a fixup for commit e913fc82.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5547e8aac6f71505d621a612de2fca0dd988b439", "tree": "36bb4a62fe5773c5acd43c9e72dca1c2f32b1bff", "parents": [ "e913fc825dc685a444cb4c1d0f9d32f372f59861" ], "author": { "name": "Dmitry Monakhov", "email": "dmonakhov@openvz.org", "time": "Fri May 07 13:35:44 2010 +0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 17 13:00:41 2010 +0200" }, "message": "writeback: Update dirty flags in two steps\n\nFilesystems with delalloc support may dirty inode during writepages.\nAs result inode will have dirty metadata flags even after write_inode.\nIn fact we have two dedicated functions for proper data and metadata\nwriteback. It is reasonable to separate flags updates in two stages.\n\nhttps://bugzilla.kernel.org/show_bug.cgi?id\u003d15906\n\nSigned-off-by: Dmitry Monakhov \u003cdmonakhov@openvz.org\u003e\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "e913fc825dc685a444cb4c1d0f9d32f372f59861", "tree": "e470697e43ffe4028ac81c17d3ef90ee9f30bcfb", "parents": [ "69b62d01ec44fe0d505d89917392347732135a4d" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 17 12:55:07 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 17 12:55:07 2010 +0200" }, "message": "writeback: fix WB_SYNC_NONE writeback from umount\n\nWhen umount calls sync_filesystem(), we first do a WB_SYNC_NONE\nwriteback to kick off writeback of pending dirty inodes, then follow\nthat up with a WB_SYNC_ALL to wait for it. Since umount already holds\nthe sb s_umount mutex, WB_SYNC_NONE ends up doing nothing and all\nwriteback happens as WB_SYNC_ALL. This can greatly slow down umount,\nsince WB_SYNC_ALL writeback is a data integrity operation and thus\na bigger hammer than simple WB_SYNC_NONE. For barrier aware file systems\nit\u0027s a lot slower.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "69b62d01ec44fe0d505d89917392347732135a4d", "tree": "da40561f3d87ee1073e92ca925ed3ed36708a1d7", "parents": [ "2395e463fefd4aa8b784787e926e9b84e216d14f" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 17 12:51:03 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 17 12:51:03 2010 +0200" }, "message": "writeback: disable periodic old data writeback for !dirty_writeback_centisecs\n\nPrior to 2.6.32, setting /proc/sys/vm/dirty_writeback_centisecs disabled\nperiodic dirty writeback from kupdate. This got broken and now causes\nexcessive sys CPU usage if set to zero, as we\u0027ll keep beating on\nschedule().\n\nCc: stable@kernel.org\nReported-by: Justin Maggard \u003cjmaggard10@gmail.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "2f4084209adc77f9a1c9f38db3019a509e167882", "tree": "775657114c885505ecc46605e29ea1470e986f76", "parents": [ "2f10ffcfb28beb35137d9e86992c771b4a6c5f2a", "3440c49f5c5ecb4f29b0544aa87da71888404f8f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Apr 09 11:50:29 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Apr 09 11:50:29 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block: (34 commits)\n cfq-iosched: Fix the incorrect timeslice accounting with forced_dispatch\n loop: Update mtime when writing using aops\n block: expose the statistics in blkio.time and blkio.sectors for the root cgroup\n backing-dev: Handle class_create() failure\n Block: Fix block/elevator.c elevator_get() off-by-one error\n drbd: lc_element_by_index() never returns NULL\n cciss: unlock on error path\n cfq-iosched: Do not merge queues of BE and IDLE classes\n cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging\n i2o: Remove the dangerous kobj_to_i2o_device macro\n block: remove 16 bytes of padding from struct request on 64bits\n cfq-iosched: fix a kbuild regression\n block: make CONFIG_BLK_CGROUP visible\n Remove GENHD_FL_DRIVERFS\n block: Export max number of segments and max segment size in sysfs\n block: Finalize conversion of block limits functions\n block: Fix overrun in lcm() and move it to lib\n vfs: improve writeback_inodes_wb()\n paride: fix off-by-one test\n drbd: fix al-to-on-disk-bitmap for 4k logical_block_size\n ...\n" }, { "commit": "5a0e3ad6af8660be21ca98a971cd00f331318c05", "tree": "5bfb7be11a03176a87296a43ac6647975c00a1d1", "parents": [ "ed391f4ebf8f701d3566423ce8f17e614cde9806" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Mar 24 17:04:11 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Mar 30 22:02:32 2010 +0900" }, "message": "include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h\n\npercpu.h is included by sched.h and module.h and thus ends up being\nincluded when building most .c files. percpu.h includes slab.h which\nin turn includes gfp.h making everything defined by the two files\nuniversally available and complicating inclusion dependencies.\n\npercpu.h -\u003e slab.h dependency is about to be removed. Prepare for\nthis change by updating users of gfp and slab facilities include those\nheaders directly instead of assuming availability. As this conversion\nneeds to touch large number of source files, the following script is\nused as the basis of conversion.\n\n http://userweb.kernel.org/~tj/misc/slabh-sweep.py\n\nThe script does the followings.\n\n* Scan files for gfp and slab usages and update includes such that\n only the necessary includes are there. ie. if only gfp is used,\n gfp.h, if slab is used, slab.h.\n\n* When the script inserts a new include, it looks at the include\n blocks and try to put the new include such that its order conforms\n to its surrounding. It\u0027s put in the include block which contains\n core kernel includes, in the same order that the rest are ordered -\n alphabetical, Christmas tree, rev-Xmas-tree or at the end if there\n doesn\u0027t seem to be any matching order.\n\n* If the script can\u0027t find a place to put a new include (mostly\n because the file doesn\u0027t have fitting include block), it prints out\n an error message indicating which .h file needs to be added to the\n file.\n\nThe conversion was done in the following steps.\n\n1. The initial automatic conversion of all .c files updated slightly\n over 4000 files, deleting around 700 includes and adding ~480 gfp.h\n and ~3000 slab.h inclusions. The script emitted errors for ~400\n files.\n\n2. Each error was manually checked. Some didn\u0027t need the inclusion,\n some needed manual addition while adding it to implementation .h or\n embedding .c file was more appropriate for others. This step added\n inclusions to around 150 files.\n\n3. The script was run again and the output was compared to the edits\n from #2 to make sure no file was left behind.\n\n4. Several build tests were done and a couple of problems were fixed.\n e.g. lib/decompress_*.c used malloc/free() wrappers around slab\n APIs requiring slab.h to be added manually.\n\n5. The script was run on all .h files but without automatically\n editing them as sprinkling gfp.h and slab.h inclusions around .h\n files could easily lead to inclusion dependency hell. Most gfp.h\n inclusion directives were ignored as stuff from gfp.h was usually\n wildly available and often used in preprocessor macros. Each\n slab.h inclusion directive was examined and added manually as\n necessary.\n\n6. percpu.h was updated not to include slab.h.\n\n7. Build test were done on the following configurations and failures\n were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my\n distributed build env didn\u0027t work with gcov compiles) and a few\n more options had to be turned off depending on archs to make things\n build (like ipr on powerpc/64 which failed due to missing writeq).\n\n * x86 and x86_64 UP and SMP allmodconfig and a custom test config.\n * powerpc and powerpc64 SMP allmodconfig\n * sparc and sparc64 SMP allmodconfig\n * ia64 SMP allmodconfig\n * s390 SMP allmodconfig\n * alpha SMP allmodconfig\n * um on x86_64 SMP allmodconfig\n\n8. percpu.h modifications were reverted so that it could be applied as\n a separate patch and serve as bisection point.\n\nGiven the fact that I had only a couple of failures from tests on step\n6, I\u0027m fairly confident about the coverage of this conversion patch.\nIf there is a breakage, it\u0027s likely to be something in one of the arch\nheaders which should be easily discoverable easily on most builds of\nthe specific arch.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nGuess-its-ok-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\n" }, { "commit": "f11c9c5c259cb2c3d698548dc3936f773ab1f5b9", "tree": "c6461c9d6981122e1507dafa0394901903eb2ca1", "parents": [ "c12ec0a2d94001003dfb929ce14c287fca0522b0" ], "author": { "name": "Edward Shishkin", "email": "edward.shishkin@gmail.com", "time": "Thu Mar 11 14:09:47 2010 -0800" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Mar 12 10:03:42 2010 +0100" }, "message": "vfs: improve writeback_inodes_wb()\n\nDo not pin/unpin superblock for every inode in writeback_inodes_wb(), pin\nit for the whole group of inodes which belong to the same superblock and\ncall writeback_sb_inodes() handler for them.\n\nSigned-off-by: Edward Shishkin \u003cedward.shishkin@gmail.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a9185b41a4f84971b930c519f0c63bd450c4810d", "tree": "268cf4e206cca12fb9e1dd68984e7c190e465b46", "parents": [ "26821ed40b4230259e770c9911180f38fcaa6f59" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Fri Mar 05 09:21:37 2010 +0100" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Mar 05 13:25:52 2010 -0500" }, "message": "pass writeback_control to -\u003ewrite_inode\n\nThis gives the filesystem more information about the writeback that\nis happening. Trond requested this for the NFS unstable write handling,\nand other filesystems might benefit from this too by beeing able to\ndistinguish between the different callers in more detail.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "26821ed40b4230259e770c9911180f38fcaa6f59", "tree": "40cd0fed705ec59dd3c909b96452bae1fc532796", "parents": [ "64ba9926759792cf7b95f823402e2781edd1b5d4" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Fri Mar 05 09:21:21 2010 +0100" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Mar 05 13:25:10 2010 -0500" }, "message": "make sure data is on disk before calling -\u003ewrite_inode\n\nSimilar to the fsync issue fixed a while ago in commit\n2daea67e966dc0c42067ebea015ddac6834cef88 we need to write for data to\nactually hit the disk before writing out the metadata to guarantee\ndata integrity for filesystems that modify the inode in the data I/O\ncompletion path. Currently XFS and NFS handle this manually, and AFS\nhas a write_inode method that does nothing but waiting for data, while\nothers are possibly missing out on this.\n\nFortunately this change has a lot less impact than the fsync change\nas none of the write_inode methods starts data writeout of any form\nby itself.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "4b6764fa9e25cf628e42bbd192eca1e0b8e59061", "tree": "7f583f864daf939a4dcadd50a6119629110943bc", "parents": [ "cd6e125c58ae1561bedb6ea6f70b00d6c2599d62" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Fri Jan 01 20:35:23 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jan 02 10:09:44 2010 -0800" }, "message": "writeback: add missing kernel-doc notation\n\nFix the following htmldocs warning:\n\n Warning(fs/fs-writeback.c:255): No description found for parameter \u0027sb\u0027\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nAcked-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "17bd55d037a02b04d9119511cfd1a4b985d20f63", "tree": "ddbc227fffb84d1b95f5f8c48b627f88f3fd56ed", "parents": [ "d3533d72e7478a61a3e1936956fc825289a2acf4" ], "author": { "name": "Eric Sandeen", "email": "sandeen@redhat.com", "time": "Wed Dec 23 07:57:07 2009 -0500" }, "committer": { "name": "Theodore Ts\u0027o", "email": "tytso@mit.edu", "time": "Wed Dec 23 07:57:07 2009 -0500" }, "message": "fs-writeback: Add helper function to start writeback if idle\n\next4, at least, would like to start pushing on writeback if it starts\nto get close to ENOSPC when reserving worst-case blocks for delalloc\nwrites. Writing out delalloc data will convert those worst-case\npredictions into usually smaller actual usage, freeing up space\nbefore we hit ENOSPC based on this speculation.\n\nThanks to Jens for the suggestion for the helper function,\n\u0026 the naming help.\n\nI\u0027ve made the helper return status on whether writeback was\nstarted even though I don\u0027t plan to use it in the ext4 patch;\nit seems like it would be potentially useful to test this\nin some cases.\n\nSigned-off-by: Eric Sandeen \u003csandeen@redhat.com\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "0d99519efef15fd0cf84a849492c7b1deee1e4b7", "tree": "d0f9d922ef73f6b9c4529826878f3cc5567848fd", "parents": [ "b17621fed6aa039387e35f9b4d34d98f213e5673" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@gmail.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "message": "writeback: remove unused nonblocking and congestion checks\n\n- no one is calling wb_writeback and write_cache_pages with\n wbc.nonblocking\u003d1 any more\n- lumpy pageout will want to do nonblocking writeback without the\n congestion wait\n\nSo remove the congestion checks as suggested by Chris.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Chris Mason \u003cchris.mason@oracle.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: Dave Chinner \u003cdavid@fromorbit.com\u003e\nCc: Evgeniy Polyakov \u003czbr@ioremap.net\u003e\nCc: Alex Elder \u003caelder@sgi.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "b17621fed6aa039387e35f9b4d34d98f213e5673", "tree": "bc755d1aa204518600a6d82dd51d970c685dc68c", "parents": [ "951c30d135390a108f102b0f6e3cfa6241f2a1aa" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@gmail.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "message": "writeback: introduce wbc.for_background\n\nIt will lower the flush priority for NFS, and maybe more in future.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "951c30d135390a108f102b0f6e3cfa6241f2a1aa", "tree": "d3184e177a7b47094ddf5a1e7540214de5b3a5e5", "parents": [ "bf7ec5bb6114b2f086e536e24486fdacd1c0d339" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@gmail.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Dec 03 13:54:25 2009 +0100" }, "message": "writeback: remove the always false bdi_cap_writeback_dirty() test\n\nThis is dead code because no bdi flush thread will be started for\n!bdi_cap_writeback_dirty bdi.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a72bfd4dea053bb8e2233902c3f1893ef5485802", "tree": "1246fc000adfee6d2874b9324eaf7383ad4413bb", "parents": [ "6d7f18f6ea3a13af95bdf507fc54d42b165e1712" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Sep 26 00:07:46 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Sep 26 00:10:40 2009 +0200" }, "message": "writeback: pass in super_block to bdi_start_writeback()\n\nSometimes we only want to write pages from a specific super_block,\nso allow that to be passed in.\n\nThis fixes a problem with commit 56a131dcf7ed36c3c6e36bea448b674ea85ed5bb\ncausing writeback on all super_blocks on a bdi, where we only really\nwant to sync a specific sb from writeback_inodes_sb().\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "56a131dcf7ed36c3c6e36bea448b674ea85ed5bb", "tree": "d62d83e8ef4108753f557f25e8d7e89a42adf227", "parents": [ "b3af9468aebf5fcb573d0a116b31d2be1d43c0e9" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 17:15:03 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:26 2009 +0200" }, "message": "writeback: writeback_inodes_sb() should use bdi_start_writeback()\n\nPointless to iterate other devices looking for a super, when\nwe have a bdi mapping.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "b3af9468aebf5fcb573d0a116b31d2be1d43c0e9", "tree": "3af10b5fa82213345ea61d4ee23ba4a550a6077e", "parents": [ "9ecc2738ac2371f88dff5d48914b4e35c45203cd" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Fri Sep 25 06:04:10 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:26 2009 +0200" }, "message": "writeback: don\u0027t delay inodes redirtied by a fast dirtier\n\nDebug traces show that in per-bdi writeback, the inode under writeback\nalmost always get redirtied by a busy dirtier. We used to call\nredirty_tail() in this case, which could delay inode for up to 30s.\n\nThis is unacceptable because it now happens so frequently for plain cp/dd,\nthat the accumulated delays could make writeback of big files very slow.\n\nSo let\u0027s distinguish between data redirty and metadata only redirty.\nThe first one is caused by a busy dirtier, while the latter one could\nhappen in XFS, NFS, etc. when they are doing delalloc or updating isize.\n\nThe inode being busy dirtied will now be requeued for next io, while\nthe inode being redirtied by fs will continue to be delayed to avoid\nrepeated IO.\n\nCC: Jan Kara \u003cjack@suse.cz\u003e\nCC: Theodore Ts\u0027o \u003ctytso@mit.edu\u003e\nCC: Dave Chinner \u003cdavid@fromorbit.com\u003e\nCC: Chris Mason \u003cchris.mason@oracle.com\u003e\nCC: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9ecc2738ac2371f88dff5d48914b4e35c45203cd", "tree": "12cd500172561fb43e5cbe1ee1993945a4ac2c5c", "parents": [ "cf137307cd9827495b65e7d74ea2b610daa9898b" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Sep 24 15:25:11 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:26 2009 +0200" }, "message": "writeback: make the super_block pinning more efficient\n\nCurrently we pin the inode-\u003ei_sb for every single inode. This\nincreases cache traffic on sb-\u003es_umount sem. Lets instead\ncache the inode sb pin state and keep the super_block pinned\nfor as long as keep writing out inodes from the same\nsuper_block.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "cf137307cd9827495b65e7d74ea2b610daa9898b", "tree": "231053bd1730527ea91133ed923756c67739e71d", "parents": [ "5c03449d34debca0deab58046377e1175c1bcd7e" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Sep 24 15:12:57 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:26 2009 +0200" }, "message": "writeback: don\u0027t resort for a single super_block in move_expired_inodes()\n\nIf we only moved inodes from a single super_block to the temporary\nlist, there\u0027s no point in doing a resort for multiple super_blocks.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5c03449d34debca0deab58046377e1175c1bcd7e", "tree": "ff4dd7b01548dca8602ed9449b8708400e3f47ad", "parents": [ "5b0830cb9085f4b69f9d57d7f3aaff322ffbec26" ], "author": { "name": "Shaohua Li", "email": "shaohua.li@intel.com", "time": "Thu Sep 24 14:42:33 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:25 2009 +0200" }, "message": "writeback: move inodes from one super_block together\n\n__mark_inode_dirty adds inode to wb dirty list in random order. If a disk has\nseveral partitions, writeback might keep spindle moving between partitions.\nTo reduce the move, better write big chunk of one partition and then move to\nanother. Inodes from one fs usually are in one partion, so idealy move indoes\nfrom one fs together should reduce spindle move. This patch tries to address\nthis. Before per-bdi writeback is added, the behavior is write indoes\nfrom one fs first and then another, so the patch restores previous behavior.\nThe loop in the patch is a bit ugly, should we add a dirty list for each\nsuperblock in bdi_writeback?\n\nTest in a two partition disk with attached fio script shows about 3% ~ 6%\nimprovement.\n\nSigned-off-by: Shaohua Li \u003cshaohua.li@intel.com\u003e\nReviewed-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5b0830cb9085f4b69f9d57d7f3aaff322ffbec26", "tree": "10040eb359269d4cd05487790b758144a69e8e39", "parents": [ "71fd05a887e0f3f6bfff76ff81b33776177d0606" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 23 19:37:09 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:25 2009 +0200" }, "message": "writeback: get rid to incorrect references to pdflush in comments\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "71fd05a887e0f3f6bfff76ff81b33776177d0606", "tree": "74f03e70445425da3cd441392ad72232ab32eb5a", "parents": [ "ae1b7f7d4b9ea587fda95c38301f4e72e8146634" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 23 19:32:26 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:25 2009 +0200" }, "message": "writeback: improve readability of the wb_writeback() continue/break logic\n\nAnd throw some comments in there, too.\n\nReviewed-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "ae1b7f7d4b9ea587fda95c38301f4e72e8146634", "tree": "7b6861974a64c2251f3f8abd7f4edc4f7434a02c", "parents": [ "7fbdea32328312c65870c397a0a436c3226c8631" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Sep 23 20:33:42 2009 +0800" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:25 2009 +0200" }, "message": "writeback: cleanup writeback_single_inode()\n\nMake the if-else straight in writeback_single_inode().\nNo behavior change.\n\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Michael Rubin \u003cmrubin@google.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "7fbdea32328312c65870c397a0a436c3226c8631", "tree": "a92cbf127bca8925afd7c2b22b372d02b32e48f3", "parents": [ "d3ddec7635b6fb37cb49e3553bdeea59642be653" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Sep 23 20:33:41 2009 +0800" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:25 2009 +0200" }, "message": "writeback: kupdate writeback shall not stop when more io is possible\n\nFix the kupdate case, which disregards wbc.more_io and stop writeback\nprematurely even when there are more inodes to be synced.\n\nwbc.more_io should always be respected.\n\nAlso remove the pages_skipped check. It will set when some page(s) of some\ninode(s) cannot be written for now. Such inodes will be delayed for a while.\nThis variable has nothing to do with whether there are other writeable inodes.\n\nCC: Jan Kara \u003cjack@suse.cz\u003e\nCC: Dave Chinner \u003cdavid@fromorbit.com\u003e\nCC: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "d3ddec7635b6fb37cb49e3553bdeea59642be653", "tree": "662a1ea9c0eac6aa9bb07d4f67b6aad84709600c", "parents": [ "3a2e9a5a2afc1a2d2c548b8987f133235cebe933" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Sep 23 20:33:40 2009 +0800" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:24 2009 +0200" }, "message": "writeback: stop background writeback when below background threshold\n\nTreat bdi_start_writeback(0) as a special request to do background write,\nand stop such work when we are below the background dirty threshold.\n\nAlso simplify the (nr_pages \u003c\u003d 0) checks. Since we already pass in\nnr_pages\u003dLONG_MAX for WB_SYNC_ALL and background writes, we don\u0027t\nneed to worry about it being decreased to zero.\n\nReported-by: Richard Kennedy \u003crichard@rsk.demon.co.uk\u003e\nCC: Jan Kara \u003cjack@suse.cz\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a5989bdc981ec85e0734ac22519cc0b780813d7b", "tree": "74cc93bd420b7bd044e3fd5451c652b3742015e6", "parents": [ "7fa07729e439a6184bd824746d06a49cca553f15" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Wed Sep 16 19:22:48 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 25 18:08:24 2009 +0200" }, "message": "fs: Fix busyloop in wb_writeback()\n\nIf all inodes are under writeback (e.g. in case when there\u0027s only one inode\nwith dirty pages), wb_writeback() with WB_SYNC_NONE work basically degrades\nto busylooping until I_SYNC flags of the inode is cleared. Fix the problem by\nwaiting on I_SYNC flags of an inode on b_more_io list in case we failed to\nwrite anything.\n\nTested-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "1ef7d9aa32a8ee054c4d4fdcd2ea537c04d61b2f", "tree": "69c570a78f37760ead0c8cad2eda25991c3fcd4c", "parents": [ "77b9d059cb3ddb8b1246d5878e81d52926550b23" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Sep 15 21:37:55 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:53 2009 +0200" }, "message": "writeback: fix possible bdi writeback refcounting problem\n\nwb_clear_pending AFAIKS should not be called after the item has been\nput on the list, except by the worker threads. It could lead to the\nsituation where the refcount is decremented below 0 and cause lots of\nproblems.\n\nPresumably the !wb_has_dirty_io case is not a common one, so it can\nbe discovered when the thread wakes up to check?\n\nAlso add a comment in bdi_work_clear.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "77b9d059cb3ddb8b1246d5878e81d52926550b23", "tree": "6d6a894d91097aec9e589d22f48d7ec387e062d9", "parents": [ "77fad5e625e56eb31a343ae1d489979fdc61a2aa" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Sep 15 21:34:51 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: Fix bdi use after free in wb_work_complete()\n\nBy the time bdi_work_on_stack gets evaluated again in bdi_work_free, it\ncan already have been deallocated and used for something else in the\n!on stack case, giving a false positive in this test and causing\ncorruption.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "77fad5e625e56eb31a343ae1d489979fdc61a2aa", "tree": "e0b881a38be27d0c4d8523289f51b70ffb98c080", "parents": [ "deed62edffe600bc5b379c872d3004116e001b66" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Sep 15 21:34:12 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: improve scalability of bdi writeback work queues\n\nIf you\u0027re going to do an atomic RMW on each list entry, there\u0027s not much\npoint in all the RCU complexities of the list walking. This is only going\nto help the multi-thread case I guess, but it doesn\u0027t hurt to do now.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "deed62edffe600bc5b379c872d3004116e001b66", "tree": "2c1837366be7dac9986a250d8b5cebf6f54fdea0", "parents": [ "49db041430e8a856dbc3af15430bf068f1c74655" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Sep 15 21:32:58 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: remove smp_mb(), it\u0027s not needed with list_add_tail_rcu()\n\nlist_add_tail_rcu contains required barriers.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "49db041430e8a856dbc3af15430bf068f1c74655", "tree": "f6ea57fc200d6584bcaef88b0ac032da0ee5c459", "parents": [ "8010c3b6349b407f8f11b3f4d7e9f94cb00fe528" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Sep 15 21:27:40 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: use schedule_timeout_interruptible()\n\nGets rid of a manual set_current_state().\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "8010c3b6349b407f8f11b3f4d7e9f94cb00fe528", "tree": "eecf594bec286f582c0b9709a87a0edb82dc034b", "parents": [ "ce5f8e7795195edb6f84f74aa9d72e739df38486" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Sep 15 20:04:57 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: add comments to bdi_work structure\n\nAnd document its retriever, get_next_work_item().\n\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "b6e51316daede0633e9274e1e30391cfa4747877", "tree": "664476bb4e7c05dcce3ad908363b482134c68429", "parents": [ "bcddc3f01c9122882c8b9f12ab94a934e55aef97" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:13:54 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: separate starting of sync vs opportunistic writeback\n\nbdi_start_writeback() is currently split into two paths, one for\nWB_SYNC_NONE and one for WB_SYNC_ALL. Add bdi_sync_writeback()\nfor WB_SYNC_ALL writeback and let bdi_start_writeback() handle\nonly WB_SYNC_NONE.\n\nPush down the writeback_control allocation and only accept the\nparameters that make sense for each function. This cleans up\nthe API considerably.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "bcddc3f01c9122882c8b9f12ab94a934e55aef97", "tree": "db642f05ec083f49c4e32cf8d93c9f14028d8ec5", "parents": [ "cfc4ba5365449cb6b5c9f68d755a142f17da1e47" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sun Sep 13 20:07:36 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:52 2009 +0200" }, "message": "writeback: inline allocation failure handling in bdi_alloc_queue_work()\n\nThis gets rid of work \u003d\u003d NULL in bdi_queue_work() and puts the\nOOM handling where it belongs.\n\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "cfc4ba5365449cb6b5c9f68d755a142f17da1e47", "tree": "08770de9bb0e658f2e65abd4d10187b3e9f6bb1b", "parents": [ "f11fcae8401a3175f528e2f7917362645d570111" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon Sep 14 13:12:40 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:51 2009 +0200" }, "message": "writeback: use RCU to protect bdi_list\n\nNow that bdi_writeback_all() no longer handles integrity writeback,\nit doesn\u0027t have to block anymore. This means that we can switch\nbdi_list reader side protection to RCU.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "f11fcae8401a3175f528e2f7917362645d570111", "tree": "1d0cf5d256ab40405582f5b459856cff41938c56", "parents": [ "32a88aa1b6dfb901cec64e1898cac78d0f25028a" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Sep 15 09:53:35 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:51 2009 +0200" }, "message": "writeback: only use bdi_writeback_all() for WB_SYNC_NONE writeout\n\nData integrity writeback must use bdi_start_writeback() and ensure\nthat wbc-\u003esb and wbc-\u003ebdi are set.\n\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c4a77a6c7dcff04a2abc7fe4b6b2ae605be41c5b", "tree": "2e0a4097cab5b94249f69fae7ebbcb22d6c8f225", "parents": [ "f0fad8a530e7cbad5f686dbca3079d1a626a3882" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:25 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:18:25 2009 +0200" }, "message": "writeback: make wb_writeback() take an argument structure\n\nWe need to be able to pass in range_cyclic as well, so instead\nof growing yet another argument, split the arguments into a\nstruct wb_writeback_args structure that we can use internally.\nAlso makes it easier to just copy all members to an on-stack\nstruct, since we can\u0027t access work after clearing the pending\nbit.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "f0fad8a530e7cbad5f686dbca3079d1a626a3882", "tree": "8e2260cd493a9088c6523dcd0a9f00e34d34a328", "parents": [ "1fe06ad89255c211fe100d7f690d10b161398df8" ], "author": { "name": "Christoph Hellwig", "email": "hch@infradead.org", "time": "Fri Sep 11 09:47:56 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 16 15:16:18 2009 +0200" }, "message": "writeback: merely wakeup flusher thread if work allocation fails for WB_SYNC_NONE\n\nSince it\u0027s an opportunistic writeback and not a data integrity action,\ndon\u0027t punt to blocking writeback. Just wakeup the thread and it will\nflush old data.\n\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "18f2ee705d98034b0f229a3202d827468d4bffd9", "tree": "1da282e5eb90dc8e8a1e46214e0e7639138d3568", "parents": [ "2f3d675bcd4a84251d6e8eea8096ec8fc795e5d6" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Tue Aug 18 18:43:15 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:17 2009 +0200" }, "message": "vfs: Remove generic_osync_inode() and sync_page_range{_nolock}()\n\nRemove these three functions since nobody uses them anymore.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "500b067c5e6ceea49cf280a02597b1169320e08c", "tree": "5e2e9bfd66f825f845fdf395b6303b884769ff6d", "parents": [ "d993831fa7ffeb89e994f046f93eeb09ec91df08" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 09 09:10:25 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 11 09:20:26 2009 +0200" }, "message": "writeback: check for registered bdi in flusher add and inode dirty\n\nAlso a debugging aid. We want to catch dirty inodes being added to\nbacking devices that don\u0027t do writeback.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "d0bceac747b547c0b4769b91fec7d3c15600153f", "tree": "f8de99db3c0cdafb01a801d1c2e94b2f5ddac967", "parents": [ "03ba3782e8dcc5b0e1efe440d33084f066e38cae" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 18 08:20:32 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 11 09:20:25 2009 +0200" }, "message": "writeback: get rid of pdflush completely\n\nIt is now unused, so kill it off.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "03ba3782e8dcc5b0e1efe440d33084f066e38cae", "tree": "e5a6513b411de16a46199530ec98ef9b7f1efc50", "parents": [ "66f3b8e2e103a0b93b945764d98e9ba46cb926dd" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 09 09:08:54 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 11 09:20:25 2009 +0200" }, "message": "writeback: switch to per-bdi threads for flushing data\n\nThis gets rid of pdflush for bdi writeout and kupdated style cleaning.\npdflush writeout suffers from lack of locality and also requires more\nthreads to handle the same workload, since it has to work in a\nnon-blocking fashion against each queue. This also introduces lumpy\nbehaviour and potential request starvation, since pdflush can be starved\nfor queue access if others are accessing it. A sample ffsb workload that\ndoes random writes to files is about 8% faster here on a simple SATA drive\nduring the benchmark phase. File layout also seems a LOT more smooth in\nvmstat:\n\n r b swpd free buff cache si so bi bo in cs us sy id wa\n 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42\n 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44\n 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37\n 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58\n 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34\n 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37\n 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44\n 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38\n 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41\n 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45\n\nwhere vanilla tends to fluctuate a lot in the creation phase:\n\n r b swpd free buff cache si so bi bo in cs us sy id wa\n 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36\n 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51\n 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40\n 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37\n 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41\n 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49\n 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36\n 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43\n 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39\n 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45\n 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34\n 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54\n\nA 10 disk test with btrfs performs 26% faster with per-bdi flushing. A\nSSD based writeback test on XFS performs over 20% better as well, with\nthe throughput being very stable around 1GB/sec, where pdflush only\nmanages 750MB/sec and fluctuates wildly while doing so. Random buffered\nwrites to many files behave a lot better as well, as does random mmap\u0027ed\nwrites.\n\nA separate thread is added to sync the super blocks. In the long term,\nadding sync_supers_bdi() functionality could get rid of this thread again.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "66f3b8e2e103a0b93b945764d98e9ba46cb926dd", "tree": "442bf5664214f0a1448e4010b09868cc58fdd3d1", "parents": [ "d8a8559cd7a9ccac98d5f6f13297a2ff68a43627" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 02 09:19:46 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 11 09:20:25 2009 +0200" }, "message": "writeback: move dirty inodes from super_block to backing_dev_info\n\nThis is a first step at introducing per-bdi flusher threads. We should\nhave no change in behaviour, although sb_has_dirty_inodes() is now\nridiculously expensive, as there\u0027s no easy way to answer that question.\nNot a huge problem, since it\u0027ll be deleted in subsequent patches.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "d8a8559cd7a9ccac98d5f6f13297a2ff68a43627", "tree": "165e02117205e9790c21b2facc130b23addf3775", "parents": [ "0d03d59d9b31cd1e33b7e46a80b6fef66244b1f2" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Sep 02 12:34:32 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 11 09:20:25 2009 +0200" }, "message": "writeback: get rid of generic_sync_sb_inodes() export\n\nThis adds two new exported functions:\n\n- writeback_inodes_sb(), which only attempts to writeback dirty inodes on\n this super_block, for WB_SYNC_NONE writeout.\n- sync_inodes_sb(), which writes out all dirty inodes on this super_block\n and also waits for the IO to complete.\n\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "01c031945f2755c7afaaf456088543312f2b72ea", "tree": "90fd969d41a79fa007e94235b8215f3a960ada1f", "parents": [ "f21f62208a6f60e2e05440b2e438d9541822dc4d" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Mon Jun 08 13:35:40 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Jun 24 08:15:26 2009 -0400" }, "message": "cleanup __writeback_single_inode\n\nThere is no reason to for the split between __writeback_single_inode and\n__sync_single_inode, the former just does a couple of checks before\ntail-calling the latter. So merge the two, and while we\u0027re at it split\nout the I_SYNC waiting case for data integrity writers, as it\u0027s\nlogically separate function. Finally rename __writeback_single_inode to\nwriteback_single_inode.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "84a892456046921a40646114deed65e2df93a1bc", "tree": "2639b6031e55988b8780960c023618c381d61c55", "parents": [ "81236810226f71bd9ff77321c8e8276dae7efc61" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:33:17 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:45 2009 -0700" }, "message": "writeback: skip new or to-be-freed inodes\n\n1) I_FREEING tests should be coupled with I_CLEAR\n\nThe two I_FREEING tests are racy because clear_inode() can set i_state to\nI_CLEAR between the clear of I_SYNC and the test of I_FREEING.\n\n2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible\n races with generic_forget_inode()\n\ngeneric_forget_inode() sets I_WILL_FREE call writeback on its own, so\ngeneric_sync_sb_inodes() shall not try to step in and create possible races:\n\n generic_forget_inode\n inode-\u003ei_state |\u003d I_WILL_FREE;\n spin_unlock(\u0026inode_lock);\n generic_sync_sb_inodes()\n spin_lock(\u0026inode_lock);\n __iget(inode);\n __writeback_single_inode\n // see non zero i_count\n may WARN here \u003d\u003d\u003e WARN_ON(inode-\u003ei_state \u0026 I_WILL_FREE);\n spin_unlock(\u0026inode_lock);\n may call generic_forget_inode again \u003d\u003d\u003e iput(inode);\n\nThe above race and warning didn\u0027t turn up because writeback_inodes() holds\nthe s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns\nearly. But we are not sure the UBIFS calls and future callers will\nguarantee that. So skip I_WILL_FREE inodes for the sake of safety.\n\nCc: Eric Sandeen \u003csandeen@sandeen.net\u003e\nAcked-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nCc: Masayoshi MIZUMA \u003cm.mizuma@jp.fujitsu.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Artem Bityutskiy \u003cdedekind1@gmail.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4195f73d1329e49727bcceb028e58cb38376c2b0", "tree": "b4c729c164d6907e4186f6dc51e319a604dee416", "parents": [ "545b9fd3d737afc0bb5203b1e79194a471605acd" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu May 28 09:01:15 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Jun 11 21:36:10 2009 -0400" }, "message": "fs: block_dump missing dentry locking\n\nI think the block_dump output in __mark_inode_dirty is missing dentry locking.\nSurely the i_dentry list can change any time, so we may not even *get* a\ndentry there. If we do get one by chance, then it would appear to be able to\ngo away or get renamed at any time...\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "545b9fd3d737afc0bb5203b1e79194a471605acd", "tree": "9b9a39b55c3145a225c5256ff2be3b07a1ee43bb", "parents": [ "8688b8635266cf98f00c6b0350ea2dbe7c42c321" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jun 02 12:07:47 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Jun 11 21:36:10 2009 -0400" }, "message": "fs: remove incorrect I_NEW warnings\n\nSome filesystems can call in to sync an inode that is still in the\nI_NEW state (eg. ext family, when mounted with -osync). This is OK\nbecause the filesystem has sole access to the new inode, so it can\nmodify i_state without races (because no other thread should be\nmodifying it, by definition of I_NEW). Ie. a false positive, so\nremove the warnings.\n\nThe races are described here 7ef0d7377cb287e08f3ae94cebc919448e1f5dff,\nwhich is also where the warnings were introduced.\n\nReported-by: Stephen Hemminger \u003cshemminger@vyatta.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "5cee5815d1564bbbd505fea86f4550f1efdb5cd0", "tree": "ba99c38932dc534bf56f0d7dcfeeca153f50b007", "parents": [ "429479f031322a0cc5c921ffb2321a51718dc875" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Apr 27 16:43:51 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Jun 11 21:36:03 2009 -0400" }, "message": "vfs: Make sys_sync() use fsync_super() (version 4)\n\nIt is unnecessarily fragile to have two places (fsync_super() and do_sync())\ndoing data integrity sync of the filesystem. Alter __fsync_super() to\naccommodate needs of both callers and use it. So after this patch\n__fsync_super() is the only place where we gather all the calls needed to\nproperly send all data on a filesystem to disk.\n\nNice bonus is that we get a complete livelock avoidance and write_supers()\nis now only used for periodic writeback of superblocks.\n\nsync_blockdevs() introduced a couple of patches ago is gone now.\n\n[build fixes folded]\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "811158b147a503fbdf9773224004ffd32002d1fe", "tree": "0a11dcfefe721bfc38ea9f1f4a238822dbae0dda", "parents": [ "4e76c5ccd5ac9bd003467d3bb0f49b18572dd4cd", "b26e0ed4936b743b693a4cc1413561fa3e4eaf65" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Apr 03 15:24:35 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Apr 03 15:24:35 2009 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (28 commits)\n trivial: Update my email address\n trivial: NULL noise: drivers/mtd/tests/mtd_*test.c\n trivial: NULL noise: drivers/media/dvb/frontends/drx397xD_fw.h\n trivial: Fix misspelling of \"Celsius\".\n trivial: remove unused variable \u0027path\u0027 in alloc_file()\n trivial: fix a pdlfush -\u003e pdflush typo in comment\n trivial: jbd header comment typo fix for JBD_PARANOID_IOFAIL\n trivial: wusb: Storage class should be before const qualifier\n trivial: drivers/char/bsr.c: Storage class should be before const qualifier\n trivial: h8300: Storage class should be before const qualifier\n trivial: fix where cgroup documentation is not correctly referred to\n trivial: Give the right path in Documentation example\n trivial: MTD: remove EOL from MODULE_DESCRIPTION\n trivial: Fix typo in bio_split()\u0027s documentation\n trivial: PWM: fix of #endif comment\n trivial: fix typos/grammar errors in Kconfig texts\n trivial: Fix misspelling of firmware\n trivial: cgroups: documentation typo and spelling corrections\n trivial: Update contact info for Jochen Hein\n trivial: fix typo \"resgister\" -\u003e \"register\"\n ...\n" }, { "commit": "d2caa3c549c74d6476e2c29e13bd4d0e7d21c7fe", "tree": "8bdaf6ababcd789ced0f441fd9503ee8e033d242", "parents": [ "846c151a4de188bb8f7043097518dab2ff5b5c2c" ], "author": { "name": "Jeff Layton", "email": "jlayton@redhat.com", "time": "Thu Apr 02 16:56:37 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 02 19:04:48 2009 -0700" }, "message": "writeback: guard against jiffies wraparound on inode-\u003edirtied_when checks (try #3)\n\nThe dirtied_when value on an inode is supposed to represent the first time\nthat an inode has one of its pages dirtied. This value is in units of\njiffies. It\u0027s used in several places in the writeback code to determine\nwhen to write out an inode.\n\nThe problem is that these checks assume that dirtied_when is updated\nperiodically. If an inode is continuously being used for I/O it can be\npersistently marked as dirty and will continue to age. Once the time\ncompared to is greater than or equal to half the maximum of the jiffies\ntype, the logic of the time_*() macros inverts and the opposite of what is\nneeded is returned. On 32-bit architectures that\u0027s just under 25 days\n(assuming HZ \u003d\u003d 1000).\n\nAs the least-recently dirtied inode, it\u0027ll end up being the first one that\npdflush will try to write out. sync_sb_inodes does this check:\n\n\t/* Was this inode dirtied after sync_sb_inodes was called? */\n \tif (time_after(inode-\u003edirtied_when, start))\n \t\tbreak;\n\n...but now dirtied_when appears to be in the future. sync_sb_inodes bails\nout without attempting to write any dirty inodes. When this occurs,\npdflush will stop writing out inodes for this superblock. Nothing can\nunwedge it until jiffies moves out of the problematic window.\n\nThis patch fixes this problem by changing the checks against dirtied_when\nto also check whether it appears to be in the future. If it does, then we\nconsider the value to be far in the past.\n\nThis should shrink the problematic window of time to such a small period\n(30s) as not to matter.\n\nSigned-off-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nAcked-by: Ian Kent \u003craven@themaw.net\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b6fac63cc1f52ec27f29fe6c6c8494a2ffac33fd", "tree": "78b4da8231fb80ea05fffc65c4647957b5a858fb", "parents": [ "33e5d76979cf01e3834814fe0aea569d1d602c1a" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Thu Apr 02 16:56:34 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 02 19:04:48 2009 -0700" }, "message": "vfs: skip I_CLEAR state inodes\n\nclear_inode() will switch inode state from I_FREEING to I_CLEAR, and do so\n_outside_ of inode_lock. So any I_FREEING testing is incomplete without a\ncoupled testing of I_CLEAR.\n\nSo add I_CLEAR tests to drop_pagecache_sb(), generic_sync_sb_inodes() and\nadd_dquot_ref().\n\nMasayoshi MIZUMA discovered the bug in drop_pagecache_sb() and Jan Kara\nreminds fixing the other two cases.\n\nMasayoshi MIZUMA has a nice panic flow:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n [process A] | [process B]\n | |\n | prune_icache() | drop_pagecache()\n | spin_lock(\u0026inode_lock) | drop_pagecache_sb()\n | inode-\u003ei_state |\u003d I_FREEING; | |\n | spin_unlock(\u0026inode_lock) | V\n | | | spin_lock(\u0026inode_lock)\n | V | |\n | dispose_list() | |\n | list_del() | |\n | clear_inode() | |\n | inode-\u003ei_state \u003d I_CLEAR | |\n | | | V\n | | | if (inode-\u003ei_state \u0026 (I_FREEING|I_WILL_FREE))\n | | | continue; \u003c\u003d\u003d\u003d\u003d NOT MATCH\n | | |\n | | | (DANGER from here on! Accessing disposing inode!)\n | | |\n | | | __iget()\n | | | list_move() \u003c\u003d\u003d\u003d\u003d\u003d PANIC on poisoned list !!\n V V |\n(time)\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nReported-by: Masayoshi MIZUMA \u003cm.mizuma@jp.fujitsu.com\u003e\nReviewed-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3e3cb64f6c306079dd8fa888c6c0a63e7e13f966", "tree": "2360e49a2fcadb919cdc8c9cb9fc1ace83ebcc8b", "parents": [ "0cbfdc8648115b2e8451ae9122311d01d2722005" ], "author": { "name": "Masatake YAMATO", "email": "yamato@redhat.com", "time": "Wed Feb 25 22:51:57 2009 +0900" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Mon Mar 30 15:22:03 2009 +0200" }, "message": "trivial: fix a pdlfush -\u003e pdflush typo in comment\n\nSigned-off-by: Masatake YAMATO \u003cyamato@redhat.com\u003e\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\n" }, { "commit": "7ef0d7377cb287e08f3ae94cebc919448e1f5dff", "tree": "3ab288db22eb17e76b5db1d9b8c6f7517570632f", "parents": [ "f272b7bc447553410dde691aa31fc531adf9c175" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu Mar 12 14:31:38 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Mar 12 16:20:24 2009 -0700" }, "message": "fs: new inode i_state corruption fix\n\nThere was a report of a data corruption\nhttp://lkml.org/lkml/2008/11/14/121. There is a script included to\nreproduce the problem.\n\nDuring testing, I encountered a number of strange things with ext3, so I\ntried ext2 to attempt to reduce complexity of the problem. I found that\nfsstress would quickly hang in wait_on_inode, waiting for I_LOCK to be\ncleared, even though instrumentation showed that unlock_new_inode had\nalready been called for that inode. This points to memory scribble, or\nsynchronisation problme.\n\ni_state of I_NEW inodes is not protected by inode_lock because other\nprocesses are not supposed to touch them until I_LOCK (and I_NEW) is\ncleared. Adding WARN_ON(inode-\u003ei_state \u0026 I_NEW) to sites where we modify\ni_state revealed that generic_sync_sb_inodes is picking up new inodes from\nthe inode lists and passing them to __writeback_single_inode without\nwaiting for I_NEW. Subsequently modifying i_state causes corruption. In\nmy case it would look like this:\n\nCPU0 CPU1\nunlock_new_inode() __sync_single_inode()\n reg \u003c- inode-\u003ei_state\n reg -\u003e reg \u0026 ~(I_LOCK|I_NEW) reg \u003c- inode-\u003ei_state\n reg -\u003e inode-\u003ei_state reg -\u003e reg | I_SYNC\n reg -\u003e inode-\u003ei_state\n\nNon-atomic RMW on CPU1 overwrites CPU0 store and sets I_LOCK|I_NEW again.\n\nFix for this is rather than wait for I_NEW inodes, just skip over them:\ninodes concurrently being created are not subject to data integrity\noperations, and should not significantly contribute to dirty memory\neither.\n\nAfter this change, I\u0027m unable to reproduce any of the added warnings or\nhangs after ~1hour of running. Previously, the new warnings would start\nimmediately and hang would happen in under 5 minutes.\n\nI\u0027m also testing on ext3 now, and so far no problems there either. I\ndon\u0027t know whether this fixes the problem reported above, but it fixes a\nreal problem for me.\n\nCc: \"Jorge Boncompte [DTI2]\" \u003cjorge@dti2.net\u003e\nReported-by: Adrian Hunter \u003cext-adrian.hunter@nokia.com\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "856bf4d717feb8c55d4e2f817b71ebb70cfbc67b", "tree": "f44790d9b8f42223955d1866645103ac5f9c68a3", "parents": [ "38f21977663126fef53f5585e7f1653d8ebe55c4" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:40:26 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "fs: sys_sync fix\n\ns_syncing livelock avoidance was breaking data integrity guarantee of\nsys_sync, by allowing sys_sync to skip writing or waiting for superblocks\nif there is a concurrent sys_sync happening.\n\nThis livelock avoidance is much less important now that we don\u0027t have the\nget_super_to_sync() call after every sb that we sync. This was replaced\nby __put_super_and_need_restart.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "38f21977663126fef53f5585e7f1653d8ebe55c4", "tree": "be5ee7a264fea0d9f4b2d109b7e08b7a1ec794c9", "parents": [ "4f5a99d64c17470a784a6c68064207d82e3e74a5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:40:25 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "fs: sync_sb_inodes fix\n\nFix data integrity semantics required by sys_sync, by iterating over all\ninodes and waiting for any writeback pages after the initial writeout.\nComments explain the exact problem.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4f5a99d64c17470a784a6c68064207d82e3e74a5", "tree": "2a3e0f0c3990bb8dbda2cdaa506a64180e5cbff2", "parents": [ "e8ea1759138d4279869f52bfb7dca8f02f8ccfe5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:40:25 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "fs: remove WB_SYNC_HOLD\n\nRemove WB_SYNC_HOLD. The primary motiviation is the design of my\nanti-starvation code for fsync. It requires taking an inode lock over the\nsync operation, so we could run into lock ordering problems with multiple\ninodes. It is possible to take a single global lock to solve the ordering\nproblem, but then that would prevent a future nice implementation of \"sync\nmultiple inodes\" based on lock order via inode address.\n\nSeems like a backward step to remove this, but actually it is busted\nanyway: we can\u0027t use the inode lists for data integrity wait: an inode can\nbe taken off the dirty lists but still be under writeback. In order to\nsatisfy data integrity semantics, we should wait for it to finish\nwriteback, but if we only search the dirty lists, we\u0027ll miss it.\n\nIt would be possible to have a \"writeback\" list, for sys_sync, I suppose.\nBut why complicate things by prematurely optimise? For unmounting, we\ncould avoid the \"livelock avoidance\" code, which would be easier, but\nagain premature IMO.\n\nFixing the existing data integrity problem will come next.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e1f8e87449147ffe5ea3de64a46af7de450ce279", "tree": "304e90a6747f5a7586a67305b7225ed4b4dbb53a", "parents": [ "8033fe65a6d6c0e47ba9e3cb2e4e6902f9dfb8dd" ], "author": { "name": "Francois Cami", "email": "francois.cami@free.fr", "time": "Wed Oct 15 22:01:59 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 16 11:21:32 2008 -0700" }, "message": "Remove Andrew Morton\u0027s old email accounts\n\nPeople can use the real name an an index into MAINTAINERS to find the\ncurrent email address.\n\nSigned-off-by: Francois Cami \u003cfrancois.cami@free.fr\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4ee6afd34409d296782a5b667d7991b1050e910a", "tree": "2a9aa6e7361d923afc60a2a5ee8cb76542152ca8", "parents": [ "ae8547b0a9e5d718ce272ddc48f91703a0f52a0b" ], "author": { "name": "Artem Bityutskiy", "email": "Artem.Bityutskiy@nokia.com", "time": "Wed May 07 21:01:30 2008 +0300" }, "committer": { "name": "Artem Bityutskiy", "email": "Artem.Bityutskiy@nokia.com", "time": "Mon Jul 14 19:10:52 2008 +0300" }, "message": "VFS: export sync_sb_inodes\n\nThis patch exports the \u0027sync_sb_inodes()\u0027 which is needed for\nUBIFS because it has to force write-back from time to time.\nNamely, the UBIFS budgeting subsystem forces write-back when\nits pessimistic callculations show that there is no free\nspace on the media.\n\nSigned-off-by: Artem Bityutskiy \u003cArtem.Bityutskiy@nokia.com\u003e\n" }, { "commit": "ae8547b0a9e5d718ce272ddc48f91703a0f52a0b", "tree": "e7caceb5171ae64c71b575d7fc38bdc319379791", "parents": [ "bce7f793daec3e65ec5c5705d2457b81fe7b5725" ], "author": { "name": "Hans Reiser", "email": "reiser@namesys.com", "time": "Wed May 07 15:48:57 2008 +0300" }, "committer": { "name": "Artem Bityutskiy", "email": "Artem.Bityutskiy@nokia.com", "time": "Mon Jul 14 19:10:52 2008 +0300" }, "message": "VFS: move inode_lock into sync_sb_inodes\n\nThis patch makes \u0027sync_sb_inodes()\u0027 lock \u0027inode_lock\u0027, rather\nthan expect that the caller will do this.\n\nThis change was previously done by Hans Reiser \u003creiser@namesys.com\u003e\nand sat in the -mm tree.\n\nSigned-off-by: Artem Bityutskiy \u003cArtem.Bityutskiy@nokia.com\u003e\n" }, { "commit": "f11b00f3bd89c91c684d56b2082d1b0241ff20ae", "tree": "59f9be385f05d12d88d0ce70306687b64cbab3b8", "parents": [ "67cde595374dd0e4e4a537dbf9dff70fd3d7bd7b" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Tue Apr 29 00:58:56 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Apr 29 08:06:00 2008 -0700" }, "message": "fs/fs-writeback.c: make 2 functions static\n\nMake the following needlessly global functions static:\n\n- writeback_acquire()\n- writeback_release()\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a6b91919e0881a0d0a4ae5211d5c879a8c7ca92b", "tree": "148aabc0a92a297f9220174435e822f30c951215", "parents": [ "5366dc9fd1cb74023790a8edf29e4fe42c886dcf" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Wed Mar 19 17:01:00 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 19 18:53:36 2008 -0700" }, "message": "fs: fix kernel-doc notation warnings\n\nFix kernel-doc notation warnings in fs/.\n\nWarning(mmotm-2008-0314-1449//fs/super.c:560): missing initial short description on line:\n *\tmark_files_ro\nWarning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line:\n *\tlease_get_mtime\nWarning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line:\n *\tlease_get_mtime\nWarning(mmotm-2008-0314-1449//fs/namei.c:1368): missing initial short description on line:\n * lookup_one_len: filesystem helper to lookup single pathname component\nWarning(mmotm-2008-0314-1449//fs/buffer.c:3221): missing initial short description on line:\n * bh_uptodate_or_lock: Test whether the buffer is uptodate\nWarning(mmotm-2008-0314-1449//fs/buffer.c:3240): missing initial short description on line:\n * bh_submit_read: Submit a locked buffer for reading\nWarning(mmotm-2008-0314-1449//fs/fs-writeback.c:30): missing initial short description on line:\n * writeback_acquire: attempt to get exclusive writeback access to a device\nWarning(mmotm-2008-0314-1449//fs/fs-writeback.c:47): missing initial short description on line:\n * writeback_in_progress: determine whether there is writeback in progress\nWarning(mmotm-2008-0314-1449//fs/fs-writeback.c:58): missing initial short description on line:\n * writeback_release: relinquish exclusive writeback access against a device.\nWarning(mmotm-2008-0314-1449//include/linux/jbd.h:351): contents before sections\nWarning(mmotm-2008-0314-1449//include/linux/jbd.h:561): contents before sections\nWarning(mmotm-2008-0314-1449//fs/jbd/transaction.c:1935): missing initial short description on line:\n * void journal_invalidatepage()\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "18914b1884ebdbcd4d4454100502a23d1d2dba43", "tree": "e52412029b3c0d977e12454feb2a13f8415df6d9", "parents": [ "abe8be3abe4c2043bd766f32d7eba62c12dbb0b3" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Fri Feb 08 04:20:23 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 08 09:22:34 2008 -0800" }, "message": "write_inode_now(): avoid unnecessary synchronous write\n\nWe shouldn\u0027t use WB_SYNC_ALL if the caller is asking for asynchronous\ntreatment.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "797074e44d78835adbde2ca527718b0e50226b95", "tree": "7a54757b7201f4e0085ad1a654fa319eb7e07816", "parents": [ "e8462caa915d4d12846db7aae2557b6db7c054d5" ], "author": { "name": "Akinobu Mita", "email": "akinobu.mita@gmail.com", "time": "Wed Feb 06 01:37:08 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Feb 06 10:41:05 2008 -0800" }, "message": "fs: use list_for_each_entry_reverse and kill sb_entry\n\nUse list_for_each_entry_reverse for super_blocks list and remove\nunused sb_entry macro.\n\nSigned-off-by: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8bc3be2751b4f74ab90a446da1912fd8204d53f7", "tree": "2bc514025a906203244d98de70fb6bd87f3ac9ac", "parents": [ "a322f8ab66f50b6c0dcdb59abae84fede7a5fded" ], "author": { "name": "Fengguang Wu", "email": "wfg@mail.ustc.edu.cn", "time": "Mon Feb 04 22:29:36 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 05 09:44:19 2008 -0800" }, "message": "writeback: speed up writeback of big dirty files\n\nAfter making dirty a 100M file, the normal behavior is to start the\nwriteback for all data after 30s delays. But sometimes the following\nhappens instead:\n\n\t- after 30s: ~4M\n\t- after 5s: ~4M\n\t- after 5s: all remaining 92M\n\nSome analyze shows that the internal io dispatch queues goes like this:\n\n\t\ts_io s_more_io\n\t\t-------------------------\n\t1)\t100M,1K 0\n\t2)\t1K 96M\n\t3)\t0 96M\n1) initial state with a 100M file and a 1K file\n\n2) 4M written, nr_to_write \u003c\u003d 0, so write more\n\n3) 1K written, nr_to_write \u003e 0, no more writes(BUG)\n\nnr_to_write \u003e 0 in (3) fools the upper layer to think that data have all\nbeen written out. The big dirty file is actually still sitting in\ns_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io\nbecomes empty, and let the loop in generic_sync_sb_inodes() continue: this\nmay starve newly expired inodes in s_dirty. It is also not an option to\ndraw inodes from both s_more_io and s_dirty, an let the loop go on: this\nmight lead to live locks, and might also starve other superblocks in sync\ntime(well kupdate may still starve some superblocks, that\u0027s another bug).\n\nWe have to return when a full scan of s_io completes. So nr_to_write \u003e 0\ndoes not necessarily mean that \"all data are written\". This patch\nintroduces a flag writeback_control.more_io to indicate that more io should\nbe done. With it the big dirty file no longer has to wait for the next\nkupdate invokation 5s later.\n\nIn sync_sb_inodes() we only set more_io on super_blocks we actually\nvisited. This avoids the interaction between two pdflush deamons.\n\nAlso in __sync_single_inode() we don\u0027t blindly keep requeuing the io if the\nfilesystem cannot progress. Failing to do so may lead to 100% iowait.\n\nTested-by: Mike Snitzer \u003csnitzer@gmail.com\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nCc: Michael Rubin \u003cmrubin@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2d544564f9954860235db97df2e549a66c61f557", "tree": "b539ab01562ae5b92ce365afd32e8fbab74a7e11", "parents": [ "5a9bbdcd29adbb786c53eba1dfc3c2d256020d6b" ], "author": { "name": "Qi Yong", "email": "qiyong@fc-cn.com", "time": "Mon Feb 04 22:29:23 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 05 09:44:18 2008 -0800" }, "message": "skip writing data pages when inode is under I_SYNC\n\nSince I_SYNC was split out from I_LOCK, the concern in commit\n4b89eed93e0fa40a63e3d7b1796ec1337ea7a3aa (\"Write back inode data pages\neven when the inode itself is locked\") is not longer valid.\n\nWe should revert to the original behavior: in __writeback_single_inode(),\nwhen we find an I_SYNC-ed inode and we\u0027re not doing a data-integrity sync,\nskip writing entirely. Otherwise, we are double calling do_writepages()\n\nSigned-off-by: Qi Yong \u003cqiyong@fc-cn.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Joern Engel \u003cjoern@wohnheim.fh-wedel.de\u003e\nCc: WU Fengguang \u003cwfg@mail.ustc.edu.cn\u003e\nCc: Michael Rubin \u003cmrubin@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c23f72cae9523d29ff94eec8f30ccbdaf234b20e", "tree": "1e5f46971510cd36a3deebfa8f160933212f4df0", "parents": [ "031f2dcd7075e218e74dd7f942ad015cf82dffab" ], "author": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Jan 14 21:21:29 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Jan 14 21:21:29 2008 -0800" }, "message": "Revert \"writeback: introduce writeback_control.more_io to indicate more io\"\n\nThis reverts commit 2e6883bdf49abd0e7f0d9b6297fc3be7ebb2250b, as\nrequested by Fengguang Wu. It\u0027s not quite fully baked yet, and while\nthere are patches around to fix the problems it caused, they should get\nmore testing. Says Fengguang: \"I\u0027ll resend them both for -mm later on,\nin a more complete patchset\".\n\nSee\n\n\thttp://bugzilla.kernel.org/show_bug.cgi?id\u003d9738\n\nfor some of this discussion.\n\nRequested-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ba25f9dcc4ea6e30839fcab5a5516f2176d5bfed", "tree": "3123c03b25dd5c0cd24b6ab4fc16731217838157", "parents": [ "9a2e70572e94e21e7ec4186702d045415422bda0" ], "author": { "name": "Pavel Emelyanov", "email": "xemul@openvz.org", "time": "Thu Oct 18 23:40:40 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:43 2007 -0700" }, "message": "Use helpers to obtain task pid in printks\n\nThe task_struct-\u003epid member is going to be deprecated, so start\nusing the helpers (task_pid_nr/task_pid_vnr/task_pid_nr_ns) in\nthe kernel.\n\nThe first thing to start with is the pid, printed to dmesg - in\nthis case we may safely use task_pid_nr(). Besides, printks produce\nmore (much more) than a half of all the explicit pid usage.\n\n[akpm@linux-foundation.org: git-drm went and changed lots of stuff]\nSigned-off-by: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nCc: Dave Airlie \u003cairlied@linux.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1c0eeaf5698597146ed9b873e2f9e0961edcf0f9", "tree": "5265eac8437e8ce517a62db8fe2bd99db5b7019b", "parents": [ "2e6883bdf49abd0e7f0d9b6297fc3be7ebb2250b" ], "author": { "name": "Joern Engel", "email": "joern@wohnheim.fh-wedel.de", "time": "Tue Oct 16 23:30:44 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "introduce I_SYNC\n\nI_LOCK was used for several unrelated purposes, which caused deadlock\nsituations in certain filesystems as a side effect. One of the purposes\nnow uses the new I_SYNC bit.\n\nAlso document the various bits and change their order from historical to\nlogical.\n\n[bunk@stusta.de: make fs/inode.c:wake_up_inode() static]\nSigned-off-by: Joern Engel \u003cjoern@wohnheim.fh-wedel.de\u003e\nCc: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nCc: David Chinner \u003cdgc@sgi.com\u003e\nCc: Anton Altaparmakov \u003caia21@cam.ac.uk\u003e\nCc: Al Viro \u003cviro@ftp.linux.org.uk\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2e6883bdf49abd0e7f0d9b6297fc3be7ebb2250b", "tree": "aec0418150413c7e9f43fb2ec68bfd24738b0623", "parents": [ "1f7decf6d9f06dac008b8d66935c0c3b18e564f9" ], "author": { "name": "Fengguang Wu", "email": "wfg@mail.ustc.edu.cn", "time": "Tue Oct 16 23:30:43 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: introduce writeback_control.more_io to indicate more io\n\nAfter making dirty a 100M file, the normal behavior is to start the writeback\nfor all data after 30s delays. But sometimes the following happens instead:\n\n\t- after 30s: ~4M\n\t- after 5s: ~4M\n\t- after 5s: all remaining 92M\n\nSome analyze shows that the internal io dispatch queues goes like this:\n\n\t\ts_io s_more_io\n\t\t-------------------------\n\t1)\t100M,1K 0\n\t2)\t1K 96M\n\t3)\t0 96M\n\n1) initial state with a 100M file and a 1K file\n2) 4M written, nr_to_write \u003c\u003d 0, so write more\n3) 1K written, nr_to_write \u003e 0, no more writes(BUG)\n\nnr_to_write \u003e 0 in (3) fools the upper layer to think that data have all been\nwritten out. The big dirty file is actually still sitting in s_more_io. We\ncannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and\nlet the loop in generic_sync_sb_inodes() continue: this may starve newly\nexpired inodes in s_dirty. It is also not an option to draw inodes from both\ns_more_io and s_dirty, an let the loop go on: this might lead to live locks,\nand might also starve other superblocks in sync time(well kupdate may still\nstarve some superblocks, that\u0027s another bug).\n\nWe have to return when a full scan of s_io completes. So nr_to_write \u003e 0 does\nnot necessarily mean that \"all data are written\". This patch introduces a\nflag writeback_control.more_io to indicate this situation. With it the big\ndirty file no longer has to wait for the next kupdate invocation 5s later.\n\nCc: David Chinner \u003cdgc@sgi.com\u003e\nCc: Ken Chen \u003ckenchen@google.com\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "08d8e9749e7f0435ba4683b620e8d30d59276b4c", "tree": "a973ab68d1f10f02e13f8d536ba0bf2cb8f2ffba", "parents": [ "2c1365791048e8aff42138ed5f6040b3c7824a69" ], "author": { "name": "Fengguang Wu", "email": "wfg@mail.ustc.edu.cn", "time": "Tue Oct 16 23:30:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix ntfs with sb_has_dirty_inodes()\n\nNTFS\u0027s if-condition on dirty inodes is not complete. Fix it with\nsb_has_dirty_inodes().\n\nCc: Anton Altaparmakov \u003caia21@cantab.net\u003e\nCc: Ken Chen \u003ckenchen@google.com\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2c1365791048e8aff42138ed5f6040b3c7824a69", "tree": "3c8de64f6b4995125f3f6171fdf175232a412783", "parents": [ "0e0f4fc22ece8e593167eccbb1a4154565c11faa" ], "author": { "name": "Fengguang Wu", "email": "wfg@mail.ustc.edu.cn", "time": "Tue Oct 16 23:30:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock inode lists 8\n\nStreamline the management of dirty inode lists and fix time ordering bugs.\n\nThe writeback logic used to move not-yet-expired dirty inodes from s_dirty to\ns_io, *only to* move them back. The move-inodes-back-and-forth thing is a\nmess, which is eliminated by this patch.\n\nThe new scheme is:\n- s_dirty acts as a time ordered io delaying queue;\n- s_io/s_more_io together acts as an io dispatching queue.\n\nOn kupdate writeback, we pull some inodes from s_dirty to s_io at the start of\nevery full scan of s_io. Otherwise (i.e. for sync/throttle/background\nwriteback), we always pull from s_dirty on each run (a partial scan).\n\nNote that the line\n\tlist_splice_init(\u0026sb-\u003es_more_io, \u0026sb-\u003es_io);\nis moved to queue_io() to leave s_io empty. Otherwise a big dirtied file will\nsit in s_io for a long time, preventing new expired inodes to get in.\n\nCc: Ken Chen \u003ckenchen@google.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0e0f4fc22ece8e593167eccbb1a4154565c11faa", "tree": "564ab2eabb31ab945c334706662854bb227f45e9", "parents": [ "670e4def6ef5f44315d62748134e535b479c784f" ], "author": { "name": "Ken Chen", "email": "kenchen@google.com", "time": "Tue Oct 16 23:30:38 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix periodic superblock dirty inode flushing\n\nCurrent -mm tree has bucketful of bug fixes in periodic writeback path.\nHowever, we still hit a glitch where dirty pages on a given inode aren\u0027t\ncompletely flushed to the disk, and system will accumulate large amount of\ndirty pages beyond what dirty_expire_interval is designed for.\n\nThe problem is __sync_single_inode() will move an inode to sb-\u003es_dirty list\neven when there are more pending dirty pages on that inode. If there is\nanother inode with a small number of dirty pages, we hit a case where the loop\niteration in wb_kupdate() terminates prematurely because wbc.nr_to_write \u003e 0.\nThus leaving the inode that has large amount of dirty pages behind and it has\nto wait for another dirty_writeback_interval before we flush it again. We\neffectively only write out MAX_WRITEBACK_PAGES every dirty_writeback_interval.\nIf the rate of dirtying is sufficiently high, the system will start\naccumulate a large number of dirty pages.\n\nSo fix it by having another sb-\u003es_more_io list on which to park the inode\nwhile we iterate through sb-\u003es_io and to allow each dirty inode which resides\non that sb to have an equal chance of flushing some amount of dirty pages.\n\nSigned-off-by: Ken Chen \u003ckenchen@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "670e4def6ef5f44315d62748134e535b479c784f", "tree": "808b850c2f08c3d546f6ca06850815324cb770a3", "parents": [ "65cb9b47e0ea568a7a38cce7773052a6ea093629" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:37 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists 7\n\nThis one fixes four bugs.\n\nThere are a few situation in there where writeback decides it is going to skip\nover a blockdev inode on the kernel-internal blockdev superblock. It\npresently does this by moving the blockdev inode onto the tail of the blockdev\nsuperblock\u0027s s_dirty. But\n\na) this screws up s_dirty\u0027s reverse-time-orderedness and\n\nb) refiling the blockdev for writeback in another 30 second is rude. We\n should try again sooner than that.\n\nFix all this up by using redirty_head(): move the blockdev inode onto the head\nof the blockdev superblock\u0027s s_dirty list for prompt writeback.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "65cb9b47e0ea568a7a38cce7773052a6ea093629", "tree": "9a53747f37c772cb882a7cbcd65879c36c5297fd", "parents": [ "c6945e77e477103057b4a639b4b01596f5257861" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:37 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists 6\n\nRecycling the previous changelog:\n\n When the writeback function is operating in writeback-for-flushing mode\n (as opposed to writeback-for-integrity) and it encounters an I_LOCKed inode,\n it will skip writing that inode. This is done for throughput and latency:\n move on to another inode rather than blocking for this one.\n\n Writeback skips this inode by moving it off s_io and onto s_dirty, so that\n writeback can proceed with the other inodes on s_io.\n\n However that inode movement can corrupt s_dirty\u0027s\n reverse-time-orderedness. Fix that by using the new redirty_tail(), which\n will update the refiled inode\u0027s dirtied_when field.\n\n Note: the behaviour in here is a bit rude: if kupdate happens to come\n across a locked inode then it will defer writeback of that inode for another\n 30 seconds. We\u0027ll address that in the next patch.\n\nAddress that here. What we do is to move the skipped inode to the _head_ of\ns_dirty, immediately eligible for writeout again. Instead of deferring that\nwriteout for another 30 seconds.\n\nOne would think that this might cause a livelock: we keep on trying to write\nthe same locked inode. But it won\u0027t because:\n\na) if that was the case, it would _already_ be happening on the\n balance_dirty_pages codepath. Because balance_dirty_pages() doesn\u0027t care\n about inode timestamps.\n\nb) if we skipped this inode then we won\u0027t have done any writeback. The\n higher-level writeback paths will see that wbc.nr_to_write didn\u0027t change\n and they\u0027ll then back off and take a nap.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c6945e77e477103057b4a639b4b01596f5257861", "tree": "02e6b473143060cdec08f3d8447512d56ea699bd", "parents": [ "1b43ef91d40190b16ba10218e66d5c2c4ba11de3" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:36 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists 5\n\nWhen the writeback function is operating in writeback-for-flushing mode (as\nopposed to writeback-for-integrity) and it encounters an I_LOCKed inode, it\nwill skip writing that inode. This is done for throughput and latency: move\non to another inode rather than blocking for this one.\n\nWriteback skips this inode by moving it off s_io and onto s_dirty, so that\nwriteback can proceed with the other inodes on s_io.\n\nHowever that inode movement can corrupt s_dirty\u0027s reverse-time-orderedness.\nFix that by using the new redirty_tail(), which will update the refiled\ninode\u0027s dirtied_when field.\n\nNote: the behaviour in here is a bit rude: if kupdate happens to come across a\nlocked inode then it will defer writeback of that inode for another 30\nseconds. We\u0027ll address that in the next patch.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1b43ef91d40190b16ba10218e66d5c2c4ba11de3", "tree": "21d46e09ae07ae8a7ea0b0d9927b1dafb8787155", "parents": [ "c986d1e2a460cbce79d631c51519ae82c778c6c5" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:35 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix comment, use helper function\n\nThere\u0027s a comment in there which claims that the inode is left on s_io\nif nfs chickened out of writing some data.\n\nBut that\u0027s not been true for three years.\n9290280ced13c85689adeffa587e9a53bd3a5873 fixed a livelock by moving these\ninodes back onto s_dirty. Fix the comment.\n\nIn the second leg of the `if\u0027, use redirty_tail() rather than open-coding it.\n\nAdd weaselly comment indicating lack of confidence in the code and lack of the\nfortitude which would be needed to fiddle with it.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c986d1e2a460cbce79d631c51519ae82c778c6c5", "tree": "d7303b22dfea805dba8db7d147294d1aa53ba7ce", "parents": [ "f57b9b7b4f68e1723ca99381dc10c8bc07d6df14" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:34 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists 4\n\nWhen the kupdate function has tried to write back an expired inode it will\nthen check to see whether some of the inode\u0027s pages are still dirty.\n\nThis can happen when the filesystem decided to not write a page for some\nreason. But it does _not_ occur due to redirtyings: a redirtying will set\nI_DIRTY_PAGES.\n\nWhat we need to do here is to set I_DIRTY_PAGES to reflect reality and to then\nput the inode onto the _head_ of s_dirty for consideration on the next kupdate\npass, in five seconds time.\n\nProblem is, the code failed to modify the inode\u0027s timestamp when pushing the\ninode onto thehead of s_dirty.\n\nThe patch:\n\nIf there are no other inodes on s_dirty then we leave the inode\u0027s timestamp\nalone: it is already expired.\n\nIf there _are_ other inodes on s_dirty then we arrange for this inode to get\nthe same timestamp as the inode which is at the head of s_dirty, thus\npreserving the s_dirty ordering. But we only need to do this if this inode\npurports to have been dirtied before the one at head-of-list.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f57b9b7b4f68e1723ca99381dc10c8bc07d6df14", "tree": "2d622e2878b86d74a9c2d0cff3d1261c55864abf", "parents": [ "9852a0e76cd9c89e71f84e784212fdd7a97ae93a" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:34 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists 3\n\nWhile writeback is working against a dirty inode it does a check after trying\nto write some of the inode\u0027s pages:\n\n\"did the lower layers skip some of the inode\u0027s dirty pages because they were\nlocked (or under writeback, or whatever)\"\n\nIf this turns out to be true, we must move the inode back onto s_dirty and\nredirty it. The reason for doing this is that fsync() and friends only check\nthe s_dirty list, and those functions want to know about those pages which\nwere locked, so they can be waited upon and, if necessary, rewritten.\n\nProblem is, that redirtying was putting the inode onto the tail of s_dirty\nwithout updating its timestamp. This causes a violation of s_dirty ordering.\n\nFix this by updating inode-\u003edirtied_when when moving the inode onto s_dirty.\n\nBut the code is still a bit buggy? If the inode was _already_ dirty then we\ndon\u0027t need to move it at all. Oh well, hopefully it doesn\u0027t matter too much,\nas that was a redirtying, which was very recent anwyay.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9852a0e76cd9c89e71f84e784212fdd7a97ae93a", "tree": "e655477605be55176a99a01e14e3b60454bd2012", "parents": [ "6610a0bc8dcc120daa1d93807d470d5cbf777c39" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:33 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:02 2007 -0700" }, "message": "writeback: fix time ordering of the per superblock dirty inode lists: memory-backed inodes\n\nFor reasons which escape me, inodes which are dirty against a ram-backed\nfilesystem are managed in the same way as inodes which are backed by real\ndevices.\n\nProbably we could optimise things here. But given that we skip the entire\nsupeblock as son as we hit the first dirty inode, there\u0027s not a lot to be\ngained.\n\nAnd the code does need to handle one particular non-backed superblock: the\nkernel\u0027s fake internal superblock which holds all the blockdevs.\n\nStill. At present when the code encounters an inode which is dirty against a\nmemory-backed filesystem it will skip that inode by refiling it back onto\ns_dirty. But it fails to update the inode\u0027s timestamp when doing so which at\nleast makes the debugging code upset.\n\nFix.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6610a0bc8dcc120daa1d93807d470d5cbf777c39", "tree": "e98afd34fa859877286c9f67d2b99fc7022c94af", "parents": [ "2b0172e1c6e6aea0a4efcfaaab38d4a02046f45a" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 23:30:32 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:01 2007 -0700" }, "message": "writeback: fix time-ordering of the per-superblock dirty-inode lists\n\nWhen writeback has finished writing back an inode it looks to see if that\ninode is still dirty. If it is, that means that a process redirtied the inode\nwhile its writeback was in progress.\n\nWhat we need to do here is to refile the redirtied inode onto the s_dirty\nlist.\n\nBut we\u0027re doing that wrongly: it could be that this inode was redirtied\n_before_ the last inode on s_dirty. We\u0027re blindly appending this inode to the\nlist, after an inode which might be less-recently-dirtied, thus violating the\nlist\u0027s ordering.\n\nSo we must either insertion-sort this inode into the correct place, or we must\nupdate this inode\u0027s dirtied_when field when appending it to the reverse-sorted\ns_dirty list, to preserve the reverse-time-ordering.\n\nThis patch does the latter: if this inode was dirtied less recently than the\ntail inode then copy the tail inode\u0027s timestamp into this inode.\n\nThis means that in rare circumstances, some inodes will be writen back later\nthan they should have been. But the time slip will be small.\n\nCc: Mike Waychison \u003cmikew@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" } ], "next": "f5ff8422bbdd59f8c1f699df248e1b7a11073027" }