218675 |
14-Feb-2011 |
luigi |
Correct a subtle bug in the 'gsched_rr' disk scheduler. The algorithm is supposed to work as follows: in order to prevent starvation, when a new client starts being served we record the start time and reset the counter of bytes served. We then switch to a new client after a certain amount of time or bytes, even if the current one still has pending requests. To avoid charging a new client the time of the first seek, we start counting time when the first request is served.
Unfortunately a bug in the previous version of the code failed to set the start time in certain cases, resulting in some processes exceeding their timeslice.
The fix (in this patch) is trivial, though it took a while to find out and replicate the bug. Thanks to Tommaso Caprai for investigating and fixing the problem.
Submitted by: Tommaso Caprai MFC after: 1 week
|
212160 |
02-Sep-2010 |
gibbs |
Correct bioq_disksort so that bioq_insert_tail() offers barrier semantic. Add the BIO_ORDERED flag for struct bio and update bio clients to use it.
The barrier semantics of bioq_insert_tail() were broken in two ways:
o In bioq_disksort(), an added bio could be inserted at the head of the queue, even when a barrier was present, if the sort key for the new entry was less than that of the last queued barrier bio.
o The last_offset used to generate the sort key for newly queued bios did not stay at the position of the barrier until either the barrier was de-queued, or a new barrier (which updates last_offset) was queued. When a barrier is in effect, we know that the disk will pass through the barrier position just before the "blocked bios" are released, so using the barrier's offset for last_offset is the optimal choice.
sys/geom/sched/subr_disk.c: sys/kern/subr_disk.c: o Update last_offset in bioq_insert_tail().
o Only update last_offset in bioq_remove() if the removed bio is at the head of the queue (typically due to a call via bioq_takefirst()) and no barrier is active.
o In bioq_disksort(), if we have a barrier (insert_point is non-NULL), set prev to the barrier and cur to it's next element. Now that last_offset is kept at the barrier position, this change isn't strictly necessary, but since we have to take a decision branch anyway, it does avoid one, no-op, loop iteration in the while loop that immediately follows.
o In bioq_disksort(), bypass the normal sort for bios with the BIO_ORDERED attribute and instead insert them into the queue with bioq_insert_tail(). bioq_insert_tail() not only gives the desired command order during insertion, but also provides barrier semantics so that commands disksorted in the future cannot pass the just enqueued transaction.
sys/sys/bio.h: Add BIO_ORDERED as bit 4 of the bio_flags field in struct bio.
sys/cam/ata/ata_da.c: sys/cam/scsi/scsi_da.c Use an ordered command for SCSI/ATA-NCQ commands issued in response to bios with the BIO_ORDERED flag set.
sys/cam/scsi/scsi_da.c Use an ordered tag when issuing a synchronize cache command.
Wrap some lines to 80 columns.
sys/cddl/contrib/opensolaris/uts/common/fs/zfs/vdev_geom.c sys/geom/geom_io.c Mark bios with the BIO_FLUSH command as BIO_ORDERED.
Sponsored by: Spectra Logic Corporation MFC after: 1 month
|
206497 |
12-Apr-2010 |
luigi |
Bring in geom_sched, support for scheduling disk I/O requests in a device independent manner. Also include an example anticipatory scheduler, gsched_rr, which gives very nice performance improvements in presence of competing random access patterns.
This is joint work with Fabio Checconi, developed last year and presented at BSDCan 2009. You can find details in the README file or at
http://info.iet.unipi.it/~luigi/geom_sched/
|