![[BACK]](/icons/back.gif){kind=icon}
Up to [Development] / xfs-linux
Up to [Development] / xfs-linux
Request diff between arbitrary revisions
Default branch: MAIN
Revision 1.9 / (download) - annotate - [select for diffs], Wed Aug 6 16:19:11 2008 UTC (9 years, 2 months ago) by lachlan.longdrop.melbourne.sgi.com
Branch: MAIN
CVS Tags: HEAD
Changes since 1.8: +1 -1
lines
Diff to previous 1.8 (unified)
Use KM_NOFS for debug trace buffers Use KM_NOFS to prevent recursion back into the filesystem which can cause deadlocks. In the case of xfs_iread() we hold the lock on the inode cluster buffer while allocating memory for the trace buffers. If we recurse back into XFS to flush data that may require a transaction to allocate extents which needs log space. This can deadlock with the xfsaild thread which can't push the tail of the log because it is trying to get the inode cluster buffer lock. Merge of xfs-linux-melb:xfs-kern:31838a by kenmcd. Use KM_NOFS for debug trace buffers
Revision 1.8 / (download) - annotate - [select for diffs], Wed Jun 25 04:16:47 2008 UTC (9 years, 4 months ago) by xaiki.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.7: +3 -1
lines
Diff to previous 1.7 (unified)
streamline init/exit path Currently the xfs module init/exit code is a mess. It's farmed out over a lot of function with very little error checking. This patch makes sure we propagate all initialization failures properly and clean up after them. Various runtime initializations are replaced with compile-time initializations where possible to make this easier. The exit path is similarly consolidated. There's now split out function to create/destroy the kmem zones and alloc/free the trace buffers. I've also changed the ktrace allocations to KM_MAYFAIL and handled errors resulting from that. And yes, we really should replace the XFS_*_TRACE ifdefs with a single XFS_TRACE.. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Niv Sardi <xaiki@sgi.com> Merge of xfs-linux-melb:xfs-kern:31354a by kenmcd.
Revision 1.7 / (download) - annotate - [select for diffs], Wed Jun 25 04:15:46 2008 UTC (9 years, 4 months ago) by xaiki.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.6: +1 -3
lines
Diff to previous 1.6 (unified)
Undoes mod: xfs-linux-melb:xfs-kern:31210a streamline init/exit path Currently the xfs module init/exit code is a mess. It's farmed out over a lot of function with very little error checking. This patch makes sure we propagate all initialization failures properly and clean up after them. Various runtime initializations are replaced with compile-time initializations where possible to make this easier. The exit path is similarly consolidated. There's now split out function to create/destroy the kmem zones and alloc/free the trace buffers. I've also changed the ktrace allocations to KM_MAYFAIL and handled errors resulting from that. And yes, we really should replace the XFS_*_TRACE ifdefs with a single XFS_TRACE.. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Niv Sardi <xaiki@sgi.com> Merge of xfs-linux-melb:xfs-kern:31353a by kenmcd.
Revision 1.6 / (download) - annotate - [select for diffs], Mon May 26 03:28:21 2008 UTC (9 years, 5 months ago) by xaiki.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.5: +3 -1
lines
Diff to previous 1.5 (unified)
xiaki pmod2git xfs-linux-melb:xfs-kern:31210a Merge of xfs-linux-melb:xfs-kern:31210a by kenmcd.
Revision 1.5 / (download) - annotate - [select for diffs], Wed Apr 9 06:17:24 2008 UTC (9 years, 6 months ago) by dgc.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.4: +1 -1
lines
Diff to previous 1.4 (unified)
replace remaining __FUNCTION__ occurrences __FUNCTION__ is gcc-specific, use __func__ Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Merge of xfs-linux-melb:xfs-kern:30775a by kenmcd. __FUNCTION__ is gcc-specific, use __func__
Revision 1.4 / (download) - annotate - [select for diffs], Fri Nov 2 03:09:06 2007 UTC (9 years, 11 months ago) by dgc.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.3: +1 -1
lines
Diff to previous 1.3 (unified)
Fix up sparse warnings. These are mostly locking annotations, marking things static, casts where needed and declaring stuff in header files. Merge of xfs-linux-melb:xfs-kern:30002a by kenmcd. Fix up sparse warnings.
Revision 1.3 / (download) - annotate - [select for diffs], Fri Aug 24 16:18:58 2007 UTC (10 years, 2 months ago) by dgc.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.2: +4 -3
lines
Diff to previous 1.2 (unified)
fix filestreams on 32-bit boxes
xfs_filestream_mount() sets up an mru cache with:
err = xfs_mru_cache_create(&mp->m_filestream, lifetime, grp_count,
(xfs_mru_cache_free_func_t)xfs_fstrm_free_func);
but that cast is causing problems...
typedef void (*xfs_mru_cache_free_func_t)(unsigned long, void*);
but:
void xfs_fstrm_free_func(
xfs_ino_t ino,
fstrm_item_t *item)
so on a 32-bit box, it's casting (32, 32) args into (64, 32) and I assume
it's getting garbage for *item, which subsequently causes an explosion.
With this change the filestreams xfsqa tests don't oops on my 32-bit box.
Signed-off-by: Eric Sandeen <sandeen@sandeen.net>
Merge of xfs-linux-melb:xfs-kern:29510a by kenmcd.
clean up item freeing callback to use correct interface. prevents
panics on 32 bit platforms.
Revision 1.2 / (download) - annotate - [select for diffs], Thu Aug 2 15:55:15 2007 UTC (10 years, 2 months ago) by dgc.longdrop.melbourne.sgi.com
Branch: MAIN
Changes since 1.1: +1 -2
lines
Diff to previous 1.1 (unified)
On-demand reaping of the MRU cache Instead of running the mru cache reaper all the time based on a timeout, we should only run it when the cache has active objects. This allows CPUs to sleep when there is no activity rather than be woken repeatedly just to check if there is anything to do. Merge of xfs-linux-melb:xfs-kern:29305a by kenmcd. No longer need to tell the MRU cache to restart the reaper when we flush the cache.
Revision 1.1 / (download) - annotate - [select for diffs], Mon Jul 9 06:12:03 2007 UTC (10 years, 3 months ago) by dgc.longdrop.melbourne.sgi.com
Branch: MAIN
Concurrent Multi-File Data Streams In media spaces, video is often stored in a frame-per-file format. When dealing with uncompressed realtime HD video streams in this format, it is crucial that files do not get fragmented and that multiple files a placed contiguously on disk. When multiple streams are being ingested and played out at the same time, it is critical that the filesystem does not cross the streams and interleave them together as this creates seek and readahead cache miss latency and prevents both ingest and playout from meeting frame rate targets. This patch set creates a "stream of files" concept into the allocator to place all the data from a single stream contiguously on disk so that RAID array readahead can be used effectively. Each additional stream gets placed in different allocation groups within the filesystem, thereby ensuring that we don't cross any streams. When an AG fills up, we select a new AG for the stream that is not in use. The core of the functionality is the stream tracking - each inode that we create in a directory needs to be associated with the directories' stream. Hence every time we create a file, we look up the directories' stream object and associate the new file with that object. Once we have a stream object for a file, we use the AG that the stream object point to for allocations. If we can't allocate in that AG (e.g. it is full) we move the entire stream to another AG. Other inodes in the same stream are moved to the new AG on their next allocation (i.e. lazy update). Stream objects are kept in a cache and hold a reference on the inode. Hence the inode cannot be reclaimed while there is an outstanding stream reference. This means that on unlink we need to remove the stream association and we also need to flush all the associations on certain events that want to reclaim all unreferenced inodes (e.g. filesystem freeze). Merge of xfs-linux-melb:xfs-kern:29096a by kenmcd. Concurrent Multi-File Data Streams feature check in.