Lines Matching refs:this
51 * 'use_far_sets' is true. In this case, the array's devices are grouped into
53 * are still shifted by 'near_copies' devices, but this shifting stays confined
387 * this branch is our 'one mirror IO has finished' event handler:
403 /* If all other devices that store this block have
476 * this branch is our 'one mirror IO has finished' event handler:
529 * check this here.
578 * With this layout, and block is never stored twice on the one device.
668 /* Never use conf->prev as this is only called during resync
713 * number - if this matches on the next IO then we use the last disk.
716 * completion handlers update this position correctly. If there is no
804 /* Cannot read here. If this is the
900 * As this is called in a wait_event() loop (see freeze_array),
903 * rare that this path is taken, it is perfectly safe to force
929 * To do this we raise a 'barrier'.
1002 * blocked until this io is done.
1074 * Thus the number queued (nr_queued) plus this request (extra)
1397 /* Have to wait for this device to get unblocked, then retry */
1516 * know to recover this chunk.
1517 * In this case the device is here, and the
1518 * fact that this chunk is not in-sync is
1919 * If this request crosses a chunk boundary, we need to split
1987 int this = first;
1990 if (this != ignore &&
1991 (rdev = rcu_dereference(conf->mirrors[this].rdev)) &&
1994 this = (this+1) % disks;
2467 /* Just give up on this device */
2471 /* Ok, we need to write this bio, either to correct an
2685 * just set read errors to 0. We do this to avoid
2734 /* still own a reference to this rdev, so it cannot
2838 /* Well, this device is dead */
2872 /* Well, this device is dead */
2915 * blocks. We must handle this.
3280 * given address, one for each out-of-sync device. We model this by allocating
3423 * though before starting on this new sync request.
3434 * In this case, the subordinate r10bios link back through a
3474 /* want to reconstruct this device */
3479 * try to recover this sector.
3674 /* Only want this if there is elsewhere to
3701 /* resync. Schedule a read for every block at this virt offset */
3719 /* We can skip this block */
3910 * no important difference in this case
4020 * actually using this, but leave code here just in case.*/
4351 * For 'offset', this is far_copies*chunksize.
4356 * multiply by chunk_size. Then round to this number.
4524 * an array, this might not contribute to
4540 * this section has already been recovered, so
4788 * down yet. We divide this by previous stripe size and multiply
4792 * From this we use last_device_address() to find where we might
4794 * If this 'next' write position is after the 'safe' position,
4801 * In all this the minimum difference in data offsets
4848 * write to for this chunk in the new layout
4869 * might write to for this chunk in the new layout
5191 /* couldn't read this block, must give up */