Don't just do nothing: it'll cause busywaits all over writeback and page
reclaim.
For now, take a fixed-length nap. Will improve when NFS starts waking up
throttled processes.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can use this information for making more intelligent priority
decisions, and it will also be useful for blktrace.
Signed-off-by: Jens Axboe <axboe@suse.de>
CFQ implements this on its own now, but it's really block layer
knowledge. Tells a device queue to start dispatching requests to
the driver, taking care to unplug if needed. Also fixes the issue
where as/cfq will invoke a stopped queue, which we really don't
want.
Signed-off-by: Jens Axboe <axboe@suse.de>
cfq_exit_lock is protecting two things now:
- The per-ioc rbtree of cfq_io_contexts
- The per-cfqd linked list of cfq_io_contexts
The per-cfqd linked list can be protected by the queue lock, as it is (by
definition) per cfqd as the queue lock is.
The per-ioc rbtree is mainly used and updated by the process itself only.
The only outside use is the io priority changing. If we move the
priority changing to not browsing the rbtree, we can remove any locking
from the rbtree updates and lookup completely. Let the sys_ioprio syscall
just mark processes as having the iopriority changed and lazily update
the private cfq io contexts the next time io is queued, and we can
remove this locking as well.
Signed-off-by: Jens Axboe <axboe@suse.de>
Move some members around and unionize completion_data and rb_node since
they cannot ever be used at the same time.
Signed-off-by: Jens Axboe <axboe@suse.de>
After Christophs SCSI change, the only usage left is RQ_ACTIVE
and RQ_INACTIVE. The block layer sets RQ_INACTIVE right before freeing
the request, so any check for RQ_INACTIVE in a driver is a bug and
indicates use-after-free.
So kill/clean the remaining users, straight forward.
Signed-off-by: Jens Axboe <axboe@suse.de>
It is always identical to &q->rq, and we only use it for detecting
whether this request came out of our mempool or not. So replace it
with an additional ->flags bit flag.
Signed-off-by: Jens Axboe <axboe@suse.de>
As the comments indicates in blkdev.h, we can fold it into ->end_io_data
usage as that is really what ->waiting is. Fixup the users of
blk_end_sync_rq().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The rbtree sort/lookup/reposition logic is mostly duplicated in
cfq/deadline/as, so move it to the elevator core. The io schedulers
still provide the actual rb root, as we don't want to impose any sort
of specific handling on the schedulers.
Introduce the helpers and rb_node in struct request to help migrate the
IO schedulers.
Signed-off-by: Jens Axboe <axboe@suse.de>
Right now, every IO scheduler implements its own backmerging (except for
noop, which does no merging). That results in duplicated code for
essentially the same operation, which is never a good thing. This patch
moves the backmerging out of the io schedulers and into the elevator
core. We save 1.6kb of text and as a bonus get backmerging for noop as
well. Win-win!
Signed-off-by: Jens Axboe <axboe@suse.de>
Right now ->flags is a bit of a mess: some are request types, and
others are just modifiers. Clean this up by splitting it into
->cmd_type and ->cmd_flags. This allows introduction of generic
Linux block message types, useful for sending generic Linux commands
to block devices.
Signed-off-by: Jens Axboe <axboe@suse.de>
The current block queue implementation already contains most of the
machinery for shared tag maps. The only remaining pieces are a way to
allocate and destroy a tag map independently of the queues (so that
the maps can be managed on the life cycle of the overseeing entity)
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
A process flag to indicate whether we are doing sync io is incredibly
ugly. It also causes performance problems when one does a lot of async
io and then proceeds to sync it. Part of the io will go out as async,
and the other part as sync. This causes a disconnect between the
previously submitted io and the synced io. For io schedulers such as CFQ,
this will cause us lost merges and suboptimal behaviour in scheduling.
Remove PF_SYNCWRITE completely from the fsync/msync paths, and let
the O_DIRECT path just directly indicate that the writes are sync
by using WRITE_SYNC instead.
Signed-off-by: Jens Axboe <axboe@suse.de>
The RQ_SCSI_* flags are a vestiage of a long past history. The EH code
still sets them but we never make use of that information. The other
users is pluto.c which never had a chance to work but needs to be kept
compiling to keep Davem happy, so copy over the definition there.
We could probably get rid of RQ_ACTIVE/RQ_INACTIVE aswell with some
work, there's only two more or less bogus looking uses in ubd and scsi.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
We currently have two implementations of this obsolete ioctl, one in
the block layer and one in the scsi code. Both of them have drawbacks.
This patch kills the scsi layer version after updating the block version
with the missing bits:
- argument checking
- use scatterlist I/O
- set number of retries based on the submitted command
This is the last user of non-S/G I/O except for the gdth driver, so
getting this in ASAP and through the scsi tree would be nie to kill
the non-S/G I/O path. Jens, what do you think about adding a check
for non-S/G I/O in the midlayer?
Thanks to Or Gerlitz for testing this patch.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Detect whether a given process is seeky and if so disable (mostly) the
idle window if it is. We still allow just a little idle time, just enough
to allow that process to submit a new request. That is needed to maintain
fairness across priority groups.
In some cases, we could setup several async queues. This is not optimal
from a performance POV, since we want all async io in one queue to perform
good sorting on it. It also impacted sync queues, as async io got too much
slice time.
Signed-off-by: Jens Axboe <axboe@suse.de>
On setups with many disks, we spend a considerable amount of time
looking up the process-disk mapping on each queue of io. Testing with
a NULL based block driver, this costs 40-50% reduction in throughput
for 1000 disks.
Signed-off-by: Jens Axboe <axboe@suse.de>
Request completion can be a quite heavy process, since it needs to
iterate through the entire request and complete the bio's it holds.
This patch adds blk_complete_request() which moves this processing
into a dedicated block softirq.
Signed-off-by: Jens Axboe <axboe@suse.de>
It's a broken interface, it's done way too late. And apparently it triggers
slab problems in recent kernels as well (most likely after the generic dispatch
code was merged). So kill it, ide-cd is the only user of it.
Signed-off-by: Jens Axboe <axboe@suse.de>
Reimplement handling of barrier requests.
* Flexible handling to deal with various capabilities of
target devices.
* Retry support for falling back.
* Tagged queues which don't support ordered tag can do ordered.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
add @uptodate argument to end_that_request_last() and @error
to rq_end_io_fn(). there's no generic way to pass error code
to request completion function, making generic error handling
of non-fs request difficult (rq->errors is driver-specific and
each driver uses it differently). this patch adds @uptodate
to end_that_request_last() and @error to rq_end_io_fn().
for fs requests, this doesn't really matter, so just using the
same uptodate argument used in the last call to
end_that_request_first() should suffice. imho, this can also
help the generic command-carrying request jens is working on.
Signed-off-by: tejun heo <htejun@gmail.com>
Signed-Off-By: Jens Axboe <axboe@suse.de>
- export __blk_put_request and blk_execute_rq_nowait
needed for async REQ_BLOCK_PC requests
- seperate max_hw_sectors and max_sectors for block/scsi_ioctl.c and
SG_IO bio.c helpers per Jens's last comments. Since block/scsi_ioctl.c SG_IO was
already testing against max_sectors and SCSI-ml was setting max_sectors and
max_hw_sectors to the same value this does not change any scsi SG_IO behavior. It only
prepares ll_rw_blk.c, scsi_ioctl.c and bio.c for when SCSI-ml begins to set
a valid max_hw_sectors for all LLDs. Today if a LLD does not set it
SCSI-ml sets it to a safe default and some LLDs set it to a artificial low
value to overcome memory and feedback issues.
Note: Since we now cap max_sectors to BLK_DEF_MAX_SECTORS, which is 1024,
drivers that used to call blk_queue_max_sectors with a large value of
max_sectors will now see the fs requests capped to BLK_DEF_MAX_SECTORS.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
For tape we need to control the retries. This patch adds a retries
counter on the request for REQ_BLOCK_PC commands originating from
scsi_execute* to use. REQ_BLOCK_PC commands comming from the block
layer SG_IO path continue to use the retires set in the ULD init_command.
(scsi_execute* does not set the gendisk so we do not execute
the init_command in that path).
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
To send async requests we need these two functions exported.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch adds request_queue->nr_sorted which keeps the number of
requests in the iosched and implement elv_drain_elevator which
performs forced dispatching. elv_drain_elevator checks whether
iosched actually dispatches all requests it has and prints error
message if it doesn't. As buggy forced dispatching can result in
wrong barrier operations, I think this extra check is worthwhile.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
- 100msec sleep is a little excessive, lots of requests can complete
in that timeframe. Use 10msec instead.
- Rename QUEUE_FLAG_BYPASS to QUEUE_FLAG_ELVSWITCH to indicate what
is going on.
Signed-off-by: Jens Axboe <axboe@suse.de>
This patch reimplements elevator switch. This patch assumes generic
dispatch queue patchset is applied.
* Each request is tagged with REQ_ELVPRIV flag if it has its elevator
private data set.
* Requests which doesn't have REQ_ELVPRIV flag set never enter
iosched. They are always directly back inserted to dispatch queue.
Of course, elevator_put_req_fn is called only for requests which
have its REQ_ELVPRIV set.
* Request queue maintains the current number of requests which have
its elevator data set (elevator_set_req_fn called) in
q->rq->elvpriv.
* If a request queue has QUEUE_FLAG_BYPASS set, elevator private data
is not allocated for new requests.
To switch to another iosched, we set QUEUE_FLAG_BYPASS and wait until
elvpriv goes to zero; then, we attach the new iosched and clears
QUEUE_FLAG_BYPASS. New implementation is much simpler and main code
paths are less cluttered, IMHO.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
This patch kills max_back_kb handling from elv_dispatch_sort() and
kills max_back_kb field from struct request_queue.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
Currently, both generic elevator code and specific ioscheds
participate in the management and usage of last_merge. This
and the following patches move last_merge handling into
generic elevator code.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
Implements generic dispatch queue which can replace all
dispatch queues implemented by each iosched. This reduces
code duplication, eases enforcing semantics over dispatch
queue, and simplifies specific ioscheds.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jens Axboe <axboe@suse.de>
"extern inline" doesn't make much sense.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
My patch in commit fa72b903f7 incorrectly
removed blk_queue_tag->real_max_depth.
The original resize implementation was incorrect in the following
points.
* actual allocation size of tag_index was shorter than real_max_size,
but assumed to be of the same size, possibly causing memory access
beyond the allocated area.
* bits in tag_map between max_deptn and real_max_depth were
initialized to 1's, making the tags permanently reserved.
In an attempt to fix above two bugs, I had removed allocation optimization
in init_tag_map and real_max_size. Tag map/index were allocated and freed
immediately during resize.
Unfortunately, I wasn't considering that tag map/index can be resized
dynamically with tags beyond new_depth active. This led to accessing
freed area after shrinking tags and led to the following bug reporting
thread on linux-scsi.
http://marc.theaimsgroup.com/?l=linux-scsi&m=112319898111885&w=2
To fix the problem, I've revived real_max_depth without allocation
optimization in init_tag_map, and Andrew Vasquez confirmed that the
problem was fixed. As Jens is not going to be available for a week, he
asked me to make sure that this patch reaches you.
http://marc.theaimsgroup.com/?l=linux-scsi&m=112325778530886&w=2
Also, a comment was added to make sure that real_max_size is needed for
dynamic shrinking.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
get_io_context needlessly turned off interrupts and checked for racing io
context creations. Both of which aren't needed, because the io context can
only be created while in process context of the current process.
Also, split the function in 2. A light version, current_io_context does not
elevate the reference count specifically, but can be used when in process
context, because the process holds a reference itself.
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This updates the CFQ io scheduler to the new time sliced design (cfq
v3). It provides full process fairness, while giving excellent
aggregate system throughput even for many competing processes. It
supports io priorities, either inherited from the cpu nice value or set
directly with the ioprio_get/set syscalls. The latter closely mimic
set/getpriority.
This import is based on my latest from -mm.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch contains the following cleanups:
- make needlessly global code static
- remove the following unused global functions:
- blkdev_scsi_issue_flush_fn
- __blk_attempt_remerge
- remove the following unused EXPORT_SYMBOL's:
- blk_phys_contig_segment
- blk_hw_contig_segment
- blkdev_scsi_issue_flush_fn
- __blk_attempt_remerge
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Acked-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
blk_queue_tag->real_max_depth was used to optimize out unnecessary
allocations/frees on tag resize. However, the whole thing was very broken -
tag_map was never allocated to real_max_depth resulting in access beyond the
end of the map, bits in [max_depth..real_max_depth] were set when initializing
a map and copied when resizing resulting in pre-occupied tags.
As the gain of the optimization is very small, well, almost nill, remove the
whole thing.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Acked-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Patch to allocate the control structures for for ide devices on the node of
the device itself (for NUMA systems). The patch depends on the Slab API
change patch by Manfred and me (in mm) and the pcidev_to_node patch that I
posted today.
Does some realignment too.
Signed-off-by: Justin M. Forbes <jmforbes@linuxtx.org>
Signed-off-by: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Pravin Shelar <pravin@calsoftinc.com>
Signed-off-by: Shobhit Dayal <shobhit@calsoftinc.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Original From: Mike Christie <michaelc@cs.wisc.edu>
Modified to split out block changes (this patch) and SCSI pieces.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Change the blk_rq_map_user() and blk_rq_map_kern() interface to require
a previously allocated request to be passed in. This is both more efficient
for multiple iterations of mapping data to the same request, and it is also
a much nicer API.
Signed-off-by: Jens Axboe <axboe@suse.de>
Add blk_rq_map_kern which takes a kernel buffer and maps it into
a request and bio. This can be used by the dm hw_handlers, old
sg_scsi_ioctl, and one day scsi special requests so all requests
comming into scsi will have bios. All requests having bios
should allow scsi to use scatter lists for all IO and allow it
to use block layer functions.
Signed-off-by: Jens Axboe <axboe@suse.de>
blk_insert_request() has a unobivous feature of requeuing a
request setting REQ_SPECIAL|REQ_SOFTBARRIER. SCSI midlayer
was the only user and as previous patches removed the usage,
remove the feature from blk_insert_request(). Only special
requests should be queued with blk_insert_request(). All
requeueing should go through blk_requeue_request().
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
The current problem seen is that the queue lock is actually in the
SCSI device structure, so when that structure is freed on device
release, we go boom if the queue tries to access the lock again.
The fix here is to move the lock from the scsi_device to the queue.
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Andrew Morton