aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/filesystems/ext4.txt
diff options
context:
space:
mode:
authorMingming Cao <cmm@us.ibm.com>2008-07-11 19:27:31 -0400
committerTheodore Ts'o <tytso@mit.edu>2008-07-11 19:27:31 -0400
commit49f1487b2e41bd8439ea39a4f15b4064e823cc54 (patch)
tree03f6b923b8d1a2134b7049b199cce0244ce66fcf /Documentation/filesystems/ext4.txt
parente4079a11f5ed966b7d972cc69e8d337a0f095e32 (diff)
ext4: Documention update for new ordered mode and delayed allocation
Adding some documentations for delayed allocation and new ordered mode. Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'Documentation/filesystems/ext4.txt')
-rw-r--r--Documentation/filesystems/ext4.txt21
1 files changed, 14 insertions, 7 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 7e940c64be47..80e193d82e2e 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -66,7 +66,7 @@ Mailing list: linux-ext4@vger.kernel.org
66* extent format reduces metadata overhead (RAM, IO for access, transactions) 66* extent format reduces metadata overhead (RAM, IO for access, transactions)
67* extent format more robust in face of on-disk corruption due to magics, 67* extent format more robust in face of on-disk corruption due to magics,
68* internal redunancy in tree 68* internal redunancy in tree
69* improved file allocation (multi-block alloc, delayed alloc) 69* improved file allocation (multi-block alloc)
70* fix 32000 subdirectory limit 70* fix 32000 subdirectory limit
71* nsec timestamps for mtime, atime, ctime, create time 71* nsec timestamps for mtime, atime, ctime, create time
72* inode version field on disk (NFSv4, Lustre) 72* inode version field on disk (NFSv4, Lustre)
@@ -77,6 +77,10 @@ Mailing list: linux-ext4@vger.kernel.org
77 flex_bg feature 77 flex_bg feature
78* large file support 78* large file support
79* Inode allocation using large virtual block groups via flex_bg 79* Inode allocation using large virtual block groups via flex_bg
80* delayed allocation
81* large block (up to pagesize) support
82* efficent new ordered mode in JBD2 and ext4(avoid using buffer head to force
83 the ordering)
80 84
812.2 Candidate features for future inclusion 852.2 Candidate features for future inclusion
82 86
@@ -239,7 +243,9 @@ stripe=n Number of filesystem blocks that mballoc will try
239 to use for allocation size and alignment. For RAID5/6 243 to use for allocation size and alignment. For RAID5/6
240 systems this should be the number of data 244 systems this should be the number of data
241 disks * RAID chunk size in file system blocks. 245 disks * RAID chunk size in file system blocks.
242 246delalloc (*) Deferring block allocation until write-out time.
247nodelalloc Disable delayed allocation. Blocks are allocation
248 when data is copied from user to page cache.
243Data Mode 249Data Mode
244========= 250=========
245There are 3 different data modes: 251There are 3 different data modes:
@@ -253,10 +259,10 @@ typically provide the best ext4 performance.
253 259
254* ordered mode 260* ordered mode
255In data=ordered mode, ext4 only officially journals metadata, but it logically 261In data=ordered mode, ext4 only officially journals metadata, but it logically
256groups metadata and data blocks into a single unit called a transaction. When 262groups metadata information related to data changes with the data blocks into a
257it's time to write the new metadata out to disk, the associated data blocks 263single unit called a transaction. When it's time to write the new metadata
258are written first. In general, this mode performs slightly slower than 264out to disk, the associated data blocks are written first. In general,
259writeback but significantly faster than journal mode. 265this mode performs slightly slower than writeback but significantly faster than journal mode.
260 266
261* journal mode 267* journal mode
262data=journal mode provides full data and metadata journaling. All new data is 268data=journal mode provides full data and metadata journaling. All new data is
@@ -264,7 +270,8 @@ written to the journal first, and then to its final location.
264In the event of a crash, the journal can be replayed, bringing both data and 270In the event of a crash, the journal can be replayed, bringing both data and
265metadata into a consistent state. This mode is the slowest except when data 271metadata into a consistent state. This mode is the slowest except when data
266needs to be read from and written to disk at the same time where it 272needs to be read from and written to disk at the same time where it
267outperforms all others modes. 273outperforms all others modes. Curently ext4 does not have delayed
274allocation support if this data journalling mode is selected.
268 275
269References 276References
270========== 277==========