)]}' { "log": [ { "commit": "93d2341c750cda0df48a6cc67b35fe25f1ec47df", "tree": "f098a3bbfae65ce967591ee94d605c6e6bea21c6", "parents": [ "fec433aaaae32a02329ad7d71b0f3c91b7525077" ], "author": { "name": "Matthew Dobson", "email": "colpatch@us.ibm.com", "time": "Sun Mar 26 01:37:50 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Mar 26 08:57:00 2006 -0800" }, "message": "[PATCH] mempool: use mempool_create_slab_pool()\n\nModify well over a dozen mempool users to call mempool_create_slab_pool()\nrather than calling mempool_create() with extra arguments, saving about 30\nlines of code and increasing readability.\n\nSigned-off-by: Matthew Dobson \u003ccolpatch@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c42de9dd67250fe984e0e31c9b542d721af6454b", "tree": "a4079b25a044f7124837f572e5342dc7614ca75d", "parents": [ "7d46a49f512e8d10b23353781a8ba85edd4fa640" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:51 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:51 2006 -0500" }, "message": "NFS: Fix a race in nfs_sync_inode()\n\nKudos to Neil Brown for spotting the problem:\n\n\"in nfs_sync_inode, there is effectively the sequence:\n\n nfs_wait_on_requests\n nfs_flush_inode\n nfs_commit_inode\n\n This seems a bit racy to me as if the only requests are on the\n -\u003ecommit list, and nfs_commit_inode is called separately after\n nfs_wait_on_requests completes, and before nfs_commit_inode start\n (say: by nfs_write_inode) then none of these function will return\n \u003e0, yet there will be some pending request that aren\u0027t waited for.\"\n\nThe solution is to search for requests to wait upon, search for dirty\nrequests, and search for uncommitted requests while holding the\nnfsi-\u003ereq_lock\n\nThe patch also cleans up nfs_sync_inode(), getting rid of the redundant\nFLUSH_WAIT flag. It turns out that we were always setting it.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "7d46a49f512e8d10b23353781a8ba85edd4fa640", "tree": "8da455d9f2f80f6c8ee82ec85449d2eb0ea12aba", "parents": [ "deb7d638262019cbac5d15ab74ffd1c29242c7cb" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:50 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:50 2006 -0500" }, "message": "NFS: Clean up nfs_flush_list()\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "deb7d638262019cbac5d15ab74ffd1c29242c7cb", "tree": "88095acd2d455b594f4cec08702aa9691faff2a0", "parents": [ "1dd761e9070aa2e543df3db41bd75ed4b8f2fab9" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:50 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:50 2006 -0500" }, "message": "NFS: Fix a race with PG_private and nfs_release_page()\n\nWe don\u0027t need to set PG_private for readahead pages, since they never get\nunlocked while I/O is in progress. However there is a small race in\nnfs_readpage_release() whereby the page may be unlocked, and have\nPG_private set.\n\nFix is to have PG_private set only for the case of writes...\n\nAlso fix a bug in nfs_clear_page_writeback(): Don\u0027t attempt to clear the\nradix_tree tag if we\u0027ve already deleted the radix tree entry.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "3feb2d49394b7874348a6e43c076b780c1d222c5", "tree": "6d27d4170fd9435574bd804033793f9d0d69a355", "parents": [ "5db3a7b2cabe8f0957683f798c4f8fa8605f9ebb" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:37 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:37 2006 -0500" }, "message": "NFS: Uninline nfs_writedata_(alloc|free) and nfs_readdata_(alloc|free)\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "e17b1fc4b35399935f00a635206e183d9292fe4f", "tree": "950fd4a83d7b6ff89286fd89a9871b0da66a4435", "parents": [ "a37ec012d7fd352648c8455d3396ea24001efcd3" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:35 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:35 2006 -0500" }, "message": "NFS: Make nfs_commit_alloc() extern\n\nWe need to use nfs_commit_alloc() in fs/nfs/direct.c.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "462d5b3296b56289efec426499a83faad4c08d9e", "tree": "eb4f9a0418e1190958603360cf9bcea0cbb67727", "parents": [ "63ab46abc70b01cb0711301f5ddb08c1c0bb9b1c" ], "author": { "name": "Chuck Lever", "email": "cel@netapp.com", "time": "Mon Mar 20 13:44:32 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:32 2006 -0500" }, "message": "NFS: make direct write path generate write requests concurrently\n\nDuplicate infrastructure from direct read path that will allow write\npath to generate multiple write requests concurrently. This will\nenable us to add support for aio in this path.\n\nTemporarily we will lose the ability to do UNSTABLE writes followed by\na COMMIT in the direct write path. However, all applications I am\naware of that use NFS O_DIRECT currently write in relatively small\nchunks, so this should not be inconvenient in any way.\n\nTest plan:\nMillions of fsx-odirect ops. OraSim.\n\nSigned-off-by: Chuck Lever \u003ccel@netapp.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "788e7a89a03e364855583c0ab4649b94925efbb9", "tree": "4434c93af133a92f550ba0ecc8d3254cb222e72d", "parents": [ "7117bf3dfb10b534a017260d9fc643bc1d0afd2a" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:27 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:27 2006 -0500" }, "message": "NFS: Cleanup of NFS write code in preparation for asynchronous o_direct\n\nThis patch inverts the callback hierarchy for NFS write calls.\n\nInstead of having the NFSv2/v3/v4-specific code set up the RPC callback\nops, we allow the original caller to do so. This allows for more\nflexibility w.r.t. how to set up and tear down the nfs_write_data\nstructure while still allowing the NFSv3/v4 code to perform error\nhandling.\n\nThe greater flexibility is needed by the asynchronous O_DIRECT code, which\nwants to be able to hold on to the original nfs_write_data structures after\nthe WRITE RPC call has completed in order to be able to replay them if the\nCOMMIT call determines that the server has rebooted.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "91d5b47023b608227d605d1e916b29dd0215bff7", "tree": "31dbb285639ea68db3abc0c4129988f02d50f11a", "parents": [ "d9ef5a8c26aab09762afce43df64736720b4860e" ], "author": { "name": "Chuck Lever", "email": "cel@netapp.com", "time": "Mon Mar 20 13:44:14 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:14 2006 -0500" }, "message": "NFS: add I/O performance counters\n\nInvoke the byte and event counter macros where we want to count bytes and\nevents.\n\nClean-up: fix a possible NULL dereference in nfs_lock, and simplify\nnfs_file_open.\n\nTest-plan:\nfsx and iozone on UP and SMP systems, with and without pre-emption. Watch\nfor memory overwrite bugs, and performance loss (significantly more CPU\nrequired per op).\n\nSigned-off-by: Chuck Lever \u003ccel@netapp.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "bd6475454c774bd9dbe6078d94bbf72b1d3b65f4", "tree": "641c38589e2aa02a22db229be7d77c9c342a81cb", "parents": [ "a162a6b804b48c605d1fd35e1861a5d32d00ad3f" ], "author": { "name": "Eric Sesterhenn", "email": "snakebyte@gmx.de", "time": "Mon Mar 20 13:44:10 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:10 2006 -0500" }, "message": "NFS: kzalloc conversion in fs/nfs\n\nthis converts fs/nfs to kzalloc() usage.\ncompile tested with make allyesconfig\n\nSigned-off-by: Eric Sesterhenn \u003csnakebyte@gmx.de\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "1dd594b21b2d98e56f2b1fe92bb222276b28de41", "tree": "c11a062713429112f162dc986a1b4002b0da1c83", "parents": [ "cd52ed35535ef443f08bf5cd3331d350272885b8" ], "author": { "name": "Neil Brown", "email": "neilb@suse.de", "time": "Mon Mar 20 13:44:04 2006 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Mon Mar 20 13:44:04 2006 -0500" }, "message": "NFS: Fix buglet in fs/nfs/write.c\n\nI\u0027ve been reading through fs/nfs/write.c trying to track down a bug\nthat seems to be related to pages loosing a refcount and getting\nfreed too early (you interested in detail??) and I spotted a little\nbug which the following patch should fix.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "70b9ecbdb9c5fdc731f8780bffd45d9519020c4a", "tree": "4678182bd417945cd424a652396510bc53eff8b7", "parents": [ "24174119c73983d5217da8f56a12c79a9b57e056" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Tue Jan 03 09:55:34 2006 +0100" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Jan 06 14:58:50 2006 -0500" }, "message": "NFS: Make stat() return updated mtimes after a write()\n\n The SuS states that a call to write() will cause mtime to be updated on\n the file. In order to satisfy that requirement, we need to flush out\n any cached writes in nfs_getattr().\n Speed things up slightly by not committing the writes.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "40859d7ee64ed6bfad8a4e93f9bb5c1074afadff", "tree": "ed4069423c3d6551035d5b6116f50452cdac4103", "parents": [ "325cfed9ae901320e9234b18c21434b783dbe342" ], "author": { "name": "Chuck Lever", "email": "cel@netapp.com", "time": "Wed Nov 30 18:09:02 2005 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Jan 06 14:58:49 2006 -0500" }, "message": "NFS: support large reads and writes on the wire\n\n Most NFS server implementations allow up to 64KB reads and writes on the\n wire. The Solaris NFS server allows up to a megabyte, for instance.\n\n Now the Linux NFS client supports transfer sizes up to 1MB, too. This will\n help reduce protocol and context switch overhead on read/write intensive NFS\n workloads, and support larger atomic read and write operations on servers\n that support them.\n\n Test-plan:\n Connectathon and iozone on mount point with wsize\u003drsize\u003e32768 over TCP.\n Tests with NFS over UDP to verify the maximum RPC payload size cap.\n\n Signed-off-by: Chuck Lever \u003ccel@netapp.com\u003e\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "963d8fe53339128ee46a7701f2e36305f0ccff8c", "tree": "426736c70a8e05cb1d945d5c7f44ea6475edd113", "parents": [ "abbcf28f23d53e8ec56a91f3528743913fa2694a" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Tue Jan 03 09:55:04 2006 +0100" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Jan 06 14:58:39 2006 -0500" }, "message": "RPC: Clean up RPC task structure\n\n Shrink the RPC task structure. Instead of storing separate pointers\n for task-\u003etk_exit and task-\u003etk_release, put them in a structure.\n\n Also pass the user data pointer as a parameter instead of passing it via\n task-\u003etk_calldata. This enables us to nest callbacks.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "abd3e641d5ef9f836ab2f2b04d80b8619b051531", "tree": "053c82b4c23a5fb419691154879acff3f487923b", "parents": [ "22905f775dd6a8b73be99826dcad07ceec00244b" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Tue Jan 03 09:55:02 2006 +0100" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Jan 06 14:58:39 2006 -0500" }, "message": "NFS: Work correctly with single-page -\u003ewritepage() calls\n\n Ensure that we always initiate flushing of data before we exit\n a single-page -\u003ewritepage() call.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "bb713d6d38f7be4f4e7d790cddb1b076e7da6699", "tree": "8b644138d771cf86599be4c1bd0f5bdcab09d39e", "parents": [ "bb184f3356adbbb1605df2f7c570b4c92231fa3a" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Sat Dec 03 15:20:14 2005 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Sat Dec 03 15:20:14 2005 -0500" }, "message": "NFS: use set_page_writeback() in the appropriate places\n\n Ensure that we use set_page_writeback() in the appropriate places\n to help the VM in keeping its page radix_tree in sync.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "0bbacc402e67abca8794a8401c1621dc0c0202e9", "tree": "a0969978295b806b35c943eb16af34b1eacfa47a", "parents": [ "c556b754967afd0878d65de2cfe0675577b0f62f" ], "author": { "name": "Chuck Lever", "email": "cel@netapp.com", "time": "Tue Nov 01 16:53:32 2005 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Nov 04 15:39:48 2005 -0500" }, "message": "NFS,SUNRPC,NLM: fix unused variable warnings when CONFIG_SYSCTL is disabled\n\n Fix some dprintk\u0027s so that NLM, NFS client, and RPC client compile\n cleanly if CONFIG_SYSCTL is disabled.\n\n Test plan:\n Compile kernel with CONFIG_NFS enabled and CONFIG_SYSCTL disabled.\n\n Signed-off-by: Chuck Lever \u003ccel@netapp.com\u003e\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "d530838bfa507d67b40d13b00d9cbd7a46a47e78", "tree": "f4b2be26c0a7b9ed3233a2be016b7e97427f8705", "parents": [ "4cecb76ff86db46d2823550256c828b6597f418e" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Nov 04 15:33:38 2005 -0500" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Fri Nov 04 15:33:38 2005 -0500" }, "message": "NFSv4: Fix problem with OPEN_DOWNGRADE\n\n RFC 3530 states that for OPEN_DOWNGRADE \"The share_access and share_deny\n bits specified must be exactly equal to the union of the share_access and\n share_deny bits specified for some subset of the OPENs in effect for\n current openowner on the current file.\n\n Setattr is currently violating the NFSv4 rules for OPEN_DOWNGRADE in that\n it may cause a downgrade from OPEN4_SHARE_ACCESS_BOTH to\n OPEN4_SHARE_ACCESS_WRITE despite the fact that there exists no open file\n with O_WRONLY access mode.\n\n Fix the problem by replacing nfs4_find_state() with a modified version of\n nfs_find_open_context().\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "0e574af1be5f569a5d7f2800333b0bfb358a5e34", "tree": "bb5b62dece21b8906222dfee022020ed6f81e34c", "parents": [ "4c2cb58c552a34744979a99ccf01762d5eb7e288" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Thu Oct 27 22:12:38 2005 -0400" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Thu Oct 27 22:12:38 2005 -0400" }, "message": "NFS: Cleanup initialisation of struct nfs_fattr\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "3da28eb1c6545fe73263a24eba0996217490e1eb", "tree": "944ccf9418c75a5c0b121f2c554c92dc93de1efa", "parents": [ "c6a556b88adfacd2af90be84357c8165d716c27d" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 17:16:31 2005 +0000" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 16:07:39 2005 -0400" }, "message": "[PATCH] NFS: Replace nfs_page insertion sort with a radix sort\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "c6a556b88adfacd2af90be84357c8165d716c27d", "tree": "b63d477180052d3d1edabffb51f3fdfe4f699866", "parents": [ "ab0a3dbedc51037f3d2e22ef67717a987b3d15e2" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 17:16:30 2005 +0000" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 16:07:39 2005 -0400" }, "message": "[PATCH] NFS: Make searching and waiting on busy writeback requests more efficient.\n\n Basically copies the VFS\u0027s method for tracking writebacks and applies\n it to the struct nfs_page.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "ab0a3dbedc51037f3d2e22ef67717a987b3d15e2", "tree": "bda40d85d59a729fb7a9c2573a43d1820df9de3c", "parents": [ "fe51beecc55d0b0dce289e4758e7c529a642f63e" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 17:16:30 2005 +0000" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 16:07:38 2005 -0400" }, "message": "[PATCH] NFS: Write optimization for short files and small O_SYNC writes.\n\n Use stable writes if we can see that we are only going to put a single\n write on the wire.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "951a143b3fcf15cfa9d38250b7462f821db241db", "tree": "6e4ea13c5f48cc3e1ac1c8649dd0f9f20c502e20", "parents": [ "08e9eac42edab63bce14b5c8419771f3c92aa3f4" ], "author": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 17:16:30 2005 +0000" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Wed Jun 22 16:07:36 2005 -0400" }, "message": "[PATCH] NFS: Fix the file size revalidation\n\n Instead of looking at whether or not the file is open for writes before\n we accept to update the length using the server value, we should rather\n be looking at whether or not we are currently caching any writes.\n\n Failure to do so means in particular that we\u0027re not updating the file\n length correctly after obtaining a POSIX or BSD lock.\n\n Signed-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }