Jan@work escribió:Con tune2fs quiza...
Data Mode
363 =========
364 There are 3 different data modes:
365
366 * writeback mode
367 In data=writeback mode, ext4 does not journal data at all. This mode provides
368 a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
369 mode - metadata journaling. A crash+recovery can cause incorrect data to
370 appear in files which were written shortly before the crash. This mode will
371 typically provide the best ext4 performance.
372
373 * ordered mode
374 In data=ordered mode, ext4 only officially journals metadata, but it logically
375 groups metadata information related to data changes with the data blocks into a
376 single unit called a transaction. When it's time to write the new metadata
377 out to disk, the associated data blocks are written first. In general,
378 this mode performs slightly slower than writeback but significantly faster than journal mode.
379
380 * journal mode
381 data=journal mode provides full data and metadata journaling. All new data is
382 written to the journal first, and then to its final location.
383 In the event of a crash, the journal can be replayed, bringing both data and
384 metadata into a consistent state. This mode is the slowest except when data
385 needs to be read from and written to disk at the same time where it
386 outperforms all others modes. Currently ext4 does not have delayed
387 allocation support if this data journalling mode is selected.
nu_kru escribió:buscando por la documentacion de ext4...
http://www.mjmwired.net/kernel/Document ... t4.txt#362
Se puede leer lo siguienteData Mode
363 =========
364 There are 3 different data modes:
365
366 * writeback mode
367 In data=writeback mode, ext4 does not journal data at all. This mode provides
368 a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
369 mode - metadata journaling. A crash+recovery can cause incorrect data to
370 appear in files which were written shortly before the crash. This mode will
371 typically provide the best ext4 performance.
372
373 * ordered mode
374 In data=ordered mode, ext4 only officially journals metadata, but it logically
375 groups metadata information related to data changes with the data blocks into a
376 single unit called a transaction. When it's time to write the new metadata
377 out to disk, the associated data blocks are written first. In general,
378 this mode performs slightly slower than writeback but significantly faster than journal mode.
379
380 * journal mode
381 data=journal mode provides full data and metadata journaling. All new data is
382 written to the journal first, and then to its final location.
383 In the event of a crash, the journal can be replayed, bringing both data and
384 metadata into a consistent state. This mode is the slowest except when data
385 needs to be read from and written to disk at the same time where it
386 outperforms all others modes. Currently ext4 does not have delayed
387 allocation support if this data journalling mode is selected.
asi que tienes la opción de writeback.. por lo que seria ejecutar..
tune2fs -o journal_data_writeback /dev/sdax
