UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/md/raid0.c

702 lines
19 KiB
C
Raw Normal View History

Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/*
raid0.c : Multiple Devices driver for Linux
Copyright (C) 1994-96 Marc ZYNGIER
<zyngier@ufr-info-p7.ibp.fr> or
<maz@gloups.fdn.fr>
Copyright (C) 1999, 2000 Ingo Molnar, Red Hat
RAID-0 management functions.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
You should have received a copy of the GNU General Public License
(for example /usr/src/linux/COPYING); if not, write to the Free
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
md: move lots of #include lines out of .h files and into .c This makes the includes more explicit, and is preparation for moving md_k.h to drivers/md/md.h Remove include/raid/md.h as its only remaining use was to #include other files. Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
#include <linux/blkdev.h>
#include <linux/seq_file.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
md: move md_k.h from include/linux/raid/ to drivers/md/ It really is nicer to keep related code together.. Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
#include "md.h"
md: move headers out of include/linux/raid/ Move the headers with the local structures for the disciplines and bitmap.h into drivers/md/ so that they are more easily grepable for hacking and not far away. md.h is left where it is for now as there are some uses from the outside. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:27:03 +08:00
#include "raid0.h"
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
#include "raid5.h"
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
[BLOCK] Get rid of request_queue_t typedef Some of the code has been gradually transitioned to using the proper struct request_queue, but there's lots left. So do a full sweet of the kernel and get rid of this typedef and replace its uses with the proper type. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-07-24 15:28:11 +08:00
static void raid0_unplug(struct request_queue *q)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
mddev_t *mddev = q->queuedata;
md: remove mddev_to_conf "helper" macro Having a macro just to cast a void* isn't really helpful. I would must rather see that we are simply de-referencing ->private, than have to know what the macro does. So open code the macro everywhere and remove the pointless cast. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:54:21 +08:00
raid0_conf_t *conf = mddev->private;
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
mdk_rdev_t **devlist = conf->devlist;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
int raid_disks = conf->strip_zone[0].nb_dev;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
int i;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
for (i=0; i < raid_disks; i++) {
[BLOCK] Get rid of request_queue_t typedef Some of the code has been gradually transitioned to using the proper struct request_queue, but there's lots left. So do a full sweet of the kernel and get rid of this typedef and replace its uses with the proper type. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-07-24 15:28:11 +08:00
struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
Add UNPLUG traces to all appropriate places Added blk_unplug interface, allowing all invocations of unplugs to result in a generated blktrace UNPLUG. Signed-off-by: Alan D. Brunelle <Alan.Brunelle@hp.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-11-08 03:26:56 +08:00
blk_unplug(r_queue);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
}
[PATCH] md: define backing_dev_info.congested_fn for raid0 and linear Each backing_dev needs to be able to report whether it is congested, either by modulating BDI_*_congested in ->state, or by defining a ->congested_fn. md/raid did neither of these. This patch add a congested_fn which simply checks all component devices to see if they are congested. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 16:15:53 +08:00
static int raid0_congested(void *data, int bits)
{
mddev_t *mddev = data;
md: remove mddev_to_conf "helper" macro Having a macro just to cast a void* isn't really helpful. I would must rather see that we are simply de-referencing ->private, than have to know what the macro does. So open code the macro everywhere and remove the pointless cast. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:54:21 +08:00
raid0_conf_t *conf = mddev->private;
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
mdk_rdev_t **devlist = conf->devlist;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
int raid_disks = conf->strip_zone[0].nb_dev;
[PATCH] md: define backing_dev_info.congested_fn for raid0 and linear Each backing_dev needs to be able to report whether it is congested, either by modulating BDI_*_congested in ->state, or by defining a ->congested_fn. md/raid did neither of these. This patch add a congested_fn which simply checks all component devices to see if they are congested. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 16:15:53 +08:00
int i, ret = 0;
md: report device as congested when suspended This should writeback from coming when the device is temporarily suspended. Signed-off-by: NeilBrown <neilb@suse.de>
2009-09-23 16:10:29 +08:00
if (mddev_congested(mddev, bits))
return 1;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
for (i = 0; i < raid_disks && !ret ; i++) {
[BLOCK] Get rid of request_queue_t typedef Some of the code has been gradually transitioned to using the proper struct request_queue, but there's lots left. So do a full sweet of the kernel and get rid of this typedef and replace its uses with the proper type. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-07-24 15:28:11 +08:00
struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
[PATCH] md: define backing_dev_info.congested_fn for raid0 and linear Each backing_dev needs to be able to report whether it is congested, either by modulating BDI_*_congested in ->state, or by defining a ->congested_fn. md/raid did neither of these. This patch add a congested_fn which simply checks all component devices to see if they are congested. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 16:15:53 +08:00
ret |= bdi_congested(&q->backing_dev_info, bits);
}
return ret;
}
md: have raid0 report its formation Report to the user what are the raid zones Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:54 +08:00
/*
* inform the user of the raid configuration
*/
static void dump_zones(mddev_t *mddev)
{
int j, k, h;
sector_t zone_size = 0;
sector_t zone_start = 0;
char b[BDEVNAME_SIZE];
raid0_conf_t *conf = mddev->private;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
int raid_disks = conf->strip_zone[0].nb_dev;
md: have raid0 report its formation Report to the user what are the raid zones Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:54 +08:00
printk(KERN_INFO "******* %s configuration *********\n",
mdname(mddev));
h = 0;
for (j = 0; j < conf->nr_strip_zones; j++) {
printk(KERN_INFO "zone%d=[", j);
for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_CONT "%s/",
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
bdevname(conf->devlist[j*raid_disks
md: have raid0 report its formation Report to the user what are the raid zones Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:54 +08:00
+ k]->bdev, b));
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_CONT "]\n");
md: have raid0 report its formation Report to the user what are the raid zones Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:54 +08:00
zone_size = conf->strip_zone[j].zone_end - zone_start;
printk(KERN_INFO " zone offset=%llukb "
"device offset=%llukb size=%llukb\n",
(unsigned long long)zone_start>>1,
(unsigned long long)conf->strip_zone[j].dev_start>>1,
(unsigned long long)zone_size>>1);
zone_start = conf->strip_zone[j].zone_end;
}
printk(KERN_INFO "**********************************\n\n");
}
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
md: remove sparse waring "symbol xxx shadows an earlier one" Rename some variable and remove some duplicate definitions to avoid there warnings. None of them are actual errors. Signed-off-by: NeilBrown <neilb@suse.de>
2009-09-23 16:06:41 +08:00
int i, c, err;
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
sector_t curr_zone_end, sectors;
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
struct strip_zone *zone;
int cnt;
char b[BDEVNAME_SIZE];
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
raid0_conf_t *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
if (!conf)
return -ENOMEM;
md: use list_for_each_entry macro directly The rdev_for_each macro defined in <linux/raid/md_k.h> is identical to list_for_each_entry_safe, from <linux/list.h>, it should be defined to use list_for_each_entry_safe, instead of reinventing the wheel. But some calls to each_entry_safe don't really need a safe version, just a direct list_for_each_entry is enough, this could save a temp variable (tmp) in every function that used rdev_for_each. In this patch, most rdev_for_each loops are replaced by list_for_each_entry, totally save many tmp vars; and only in the other situations that will call list_del to delete an entry, the safe version is used. Signed-off-by: Cheng Renquan <crquan@gmail.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-01-09 05:31:08 +08:00
list_for_each_entry(rdev1, &mddev->disks, same_set) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: looking at %s\n",
mdname(mddev),
bdevname(rdev1->bdev, b));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
c = 0;
md: raid0/linear: ensure device sizes are rounded to chunk size. This is currently ensured by common code, but it is more reliable to ensure it where it is needed in personality code. All the other personalities that care already round the size to the chunk_size. raid0 and linear are the only hold-outs. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:48:55 +08:00
/* round size to chunk_size */
sectors = rdev1->sectors;
sector_div(sectors, mddev->chunk_sectors);
rdev1->sectors = sectors * mddev->chunk_sectors;
md: use list_for_each_entry macro directly The rdev_for_each macro defined in <linux/raid/md_k.h> is identical to list_for_each_entry_safe, from <linux/list.h>, it should be defined to use list_for_each_entry_safe, instead of reinventing the wheel. But some calls to each_entry_safe don't really need a safe version, just a direct list_for_each_entry is enough, this could save a temp variable (tmp) in every function that used rdev_for_each. In this patch, most rdev_for_each loops are replaced by list_for_each_entry, totally save many tmp vars; and only in the other situations that will call list_del to delete an entry, the safe version is used. Signed-off-by: Cheng Renquan <crquan@gmail.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-01-09 05:31:08 +08:00
list_for_each_entry(rdev2, &mddev->disks, same_set) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: comparing %s(%llu)",
mdname(mddev),
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
bdevname(rdev1->bdev,b),
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
(unsigned long long)rdev1->sectors);
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_CONT " with %s(%llu)\n",
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
bdevname(rdev2->bdev,b),
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
(unsigned long long)rdev2->sectors);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
if (rdev2 == rdev1) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: END\n",
mdname(mddev));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
break;
}
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
if (rdev2->sectors == rdev1->sectors) {
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/*
* Not unique, don't count it as a new
* group
*/
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: EQUAL\n",
mdname(mddev));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
c = 1;
break;
}
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: NOT EQUAL\n",
mdname(mddev));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
if (!c) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: ==> UNIQUE\n",
mdname(mddev));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
conf->nr_strip_zones++;
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: %d zones\n",
mdname(mddev), conf->nr_strip_zones);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
}
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: FINAL %d zones\n",
mdname(mddev), conf->nr_strip_zones);
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
err = -ENOMEM;
[PATCH] md: convert md to use kzalloc throughout Replace multiple kmalloc/memset pairs with kzalloc calls. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:32 +08:00
conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
conf->nr_strip_zones, GFP_KERNEL);
if (!conf->strip_zone)
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
goto abort;
[PATCH] md: convert md to use kzalloc throughout Replace multiple kmalloc/memset pairs with kzalloc calls. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:32 +08:00
conf->devlist = kzalloc(sizeof(mdk_rdev_t*)*
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
conf->nr_strip_zones*mddev->raid_disks,
GFP_KERNEL);
if (!conf->devlist)
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
goto abort;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/* The first zone must contain all devices, so here we check that
* there is a proper alignment of slots to devices and find them all
*/
zone = &conf->strip_zone[0];
cnt = 0;
smallest = NULL;
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
dev = conf->devlist;
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
err = -EINVAL;
md: use list_for_each_entry macro directly The rdev_for_each macro defined in <linux/raid/md_k.h> is identical to list_for_each_entry_safe, from <linux/list.h>, it should be defined to use list_for_each_entry_safe, instead of reinventing the wheel. But some calls to each_entry_safe don't really need a safe version, just a direct list_for_each_entry is enough, this could save a temp variable (tmp) in every function that used rdev_for_each. In this patch, most rdev_for_each loops are replaced by list_for_each_entry, totally save many tmp vars; and only in the other situations that will call list_del to delete an entry, the safe version is used. Signed-off-by: Cheng Renquan <crquan@gmail.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-01-09 05:31:08 +08:00
list_for_each_entry(rdev1, &mddev->disks, same_set) {
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
int j = rdev1->raid_disk;
md: fix handling of array level takeover that re-arranges devices. Most array level changes leave the list of devices largely unchanged, possibly causing one at the end to become redundant. However conversions between RAID0 and RAID10 need to renumber all devices (except 0). This renumbering is currently being done in the ->run method when the new personality takes over. However this is too late as the common code in md.c might already have invalidated some of the devices if they had a ->raid_disk number that appeared to high. Moving it into the ->takeover method is too early as the array is still active at that time and wrong ->raid_disk numbers could cause confusion. So add a ->new_raid_disk field to mdk_rdev_s and use it to communicate the new raid_disk number. Now the common code knows exactly which devices need to be renumbered, and which can be invalidated, and can do it all at a convenient time when the array is suspend. It can also update some symlinks in sysfs which previously were not be updated correctly. Reported-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-06-15 16:36:03 +08:00
if (mddev->level == 10) {
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
/* taking over a raid10-n2 array */
j /= 2;
md: fix handling of array level takeover that re-arranges devices. Most array level changes leave the list of devices largely unchanged, possibly causing one at the end to become redundant. However conversions between RAID0 and RAID10 need to renumber all devices (except 0). This renumbering is currently being done in the ->run method when the new personality takes over. However this is too late as the common code in md.c might already have invalidated some of the devices if they had a ->raid_disk number that appeared to high. Moving it into the ->takeover method is too early as the array is still active at that time and wrong ->raid_disk numbers could cause confusion. So add a ->new_raid_disk field to mdk_rdev_s and use it to communicate the new raid_disk number. Now the common code knows exactly which devices need to be renumbered, and which can be invalidated, and can do it all at a convenient time when the array is suspend. It can also update some symlinks in sysfs which previously were not be updated correctly. Reported-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-06-15 16:36:03 +08:00
rdev1->new_raid_disk = j;
}
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
if (j < 0 || j >= mddev->raid_disks) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
"aborting!\n", mdname(mddev), j);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
goto abort;
}
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
if (dev[j]) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: multiple devices for %d - "
"aborting!\n", mdname(mddev), j);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
goto abort;
}
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
dev[j] = rdev1;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: Use new topology calls to indicate alignment and I/O sizes Switch MD over to the new disk_stack_limits() function which checks for aligment and adjusts preferred I/O sizes when stacking. Also indicate preferred I/O sizes where applicable. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-07-01 09:13:45 +08:00
disk_stack_limits(mddev->gendisk, rdev1->bdev,
rdev1->data_offset << 9);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/* as we don't honour merge_bvec_fn, we must never risk
md: deal with merge_bvec_fn in component devices better. If a component device has a merge_bvec_fn then as we never call it we must ensure we never need to. Currently this is done by setting max_sector to 1 PAGE, however this does not stop a bio being created with several sub-page iovecs that would violate the merge_bvec_fn. So instead set max_segments to 1 and set the segment boundary to the same as a page boundary to ensure there is only ever one single-page segment of IO requested at a time. This can particularly be an issue when 'xen' is used as it is known to submit multiple small buffers in a single bio. Signed-off-by: NeilBrown <neilb@suse.de> Cc: stable@kernel.org
2010-03-08 13:44:38 +08:00
* violating it, so limit ->max_segments to 1, lying within
* a single page.
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
*/
md: deal with merge_bvec_fn in component devices better. If a component device has a merge_bvec_fn then as we never call it we must ensure we never need to. Currently this is done by setting max_sector to 1 PAGE, however this does not stop a bio being created with several sub-page iovecs that would violate the merge_bvec_fn. So instead set max_segments to 1 and set the segment boundary to the same as a page boundary to ensure there is only ever one single-page segment of IO requested at a time. This can particularly be an issue when 'xen' is used as it is known to submit multiple small buffers in a single bio. Signed-off-by: NeilBrown <neilb@suse.de> Cc: stable@kernel.org
2010-03-08 13:44:38 +08:00
if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
blk_queue_max_segments(mddev->queue, 1);
blk_queue_segment_boundary(mddev->queue,
PAGE_CACHE_SIZE - 1);
}
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
if (!smallest || (rdev1->sectors < smallest->sectors))
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
smallest = rdev1;
cnt++;
}
if (cnt != mddev->raid_disks) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
"aborting!\n", mdname(mddev), cnt, mddev->raid_disks);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
goto abort;
}
zone->nb_dev = cnt;
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
zone->zone_end = smallest->sectors * cnt;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
curr_zone_end = zone->zone_end;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/* now do the other zones */
for (i = 1; i < conf->nr_strip_zones; i++)
{
md: remove sparse waring "symbol xxx shadows an earlier one" Rename some variable and remove some duplicate definitions to avoid there warnings. None of them are actual errors. Signed-off-by: NeilBrown <neilb@suse.de>
2009-09-23 16:06:41 +08:00
int j;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
zone = conf->strip_zone + i;
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
dev = conf->devlist + i * mddev->raid_disks;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: zone %d\n",
mdname(mddev), i);
md/raid0: two cleanups in create_stripe_zones. 1/ remove current_start. The same value is available in zone->dev_start and storing it separately doesn't gain anything. 2/ rename curr_zone_start to curr_zone_end as we are now more focused on the 'end' of each zone. We end up storing the same number though - the old name was a little confusing (and what does 'current' mean in this context anyway). Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:46:46 +08:00
zone->dev_start = smallest->sectors;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
smallest = NULL;
c = 0;
for (j=0; j<cnt; j++) {
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
rdev = conf->devlist[j];
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: checking %s ...",
mdname(mddev),
bdevname(rdev->bdev, b));
md/raid0: two cleanups in create_stripe_zones. 1/ remove current_start. The same value is available in zone->dev_start and storing it separately doesn't gain anything. 2/ rename curr_zone_start to curr_zone_end as we are now more focused on the 'end' of each zone. We end up storing the same number though - the old name was a little confusing (and what does 'current' mean in this context anyway). Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:46:46 +08:00
if (rdev->sectors <= zone->dev_start) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_CONT " nope.\n");
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
continue;
}
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_CONT " contained as device %d\n", c);
md: raid0: remove ->dev pointer from strip_zone structure If we treat conf->devlist more like a 2 dimensional array, we can get the devlist for a particular zone simply by indexing that array, so we don't need to store the pointers to subarrays in strip_zone. This makes strip_zone smaller and so (hopefully) searches faster. Signed-of-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:52 +08:00
dev[c] = rdev;
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
c++;
if (!smallest || rdev->sectors < smallest->sectors) {
smallest = rdev;
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: (%llu) is smallest!.\n",
mdname(mddev),
(unsigned long long)rdev->sectors);
md: Represent raid device size in sectors. This patch renames the "size" field of struct mdk_rdev_s to "sectors" and changes this field to store sectors instead of blocks. All users of this field, linear.c, raid0.c and md.c, are fixed up accordingly which gets rid of many multiplications and divisions. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-03-31 11:33:13 +08:00
}
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
zone->nb_dev = c;
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
sectors = (smallest->sectors - zone->dev_start) * c;
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n",
mdname(mddev),
zone->nb_dev, (unsigned long long)sectors);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
curr_zone_end += sectors;
md/raid0: two cleanups in create_stripe_zones. 1/ remove current_start. The same value is available in zone->dev_start and storing it separately doesn't gain anything. 2/ rename curr_zone_start to curr_zone_end as we are now more focused on the 'end' of each zone. We end up storing the same number though - the old name was a little confusing (and what does 'current' mean in this context anyway). Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:46:46 +08:00
zone->zone_end = curr_zone_end;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: current zone start: %llu\n",
mdname(mddev),
(unsigned long long)smallest->sectors);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
mddev->queue->unplug_fn = raid0_unplug;
[PATCH] md: define backing_dev_info.congested_fn for raid0 and linear Each backing_dev needs to be able to report whether it is congested, either by modulating BDI_*_congested in ->state, or by defining a ->congested_fn. md/raid did neither of these. This patch add a congested_fn which simply checks all component devices to see if they are congested. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 16:15:53 +08:00
mddev->queue->backing_dev_info.congested_fn = raid0_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: raid0: chunk size check in raid0_run have raid0 check chunk size in run method instead of in md. This is part of a series moving the checks from common code to the personalities where they belong. hardsect is short and chunksize is an int, so it is safe to use %. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:57 +08:00
/*
* now since we have the hard sector sizes, we can make sure
* chunk size is a multiple of that sector size
*/
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
md: raid0: chunk size check in raid0_run have raid0 check chunk size in run method instead of in md. This is part of a series moving the checks from common code to the personalities where they belong. hardsect is short and chunksize is an int, so it is safe to use %. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:57 +08:00
mdname(mddev),
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
mddev->chunk_sectors << 9);
md: raid0: chunk size check in raid0_run have raid0 check chunk size in run method instead of in md. This is part of a series moving the checks from common code to the personalities where they belong. hardsect is short and chunksize is an int, so it is safe to use %. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:57 +08:00
goto abort;
}
md: Use new topology calls to indicate alignment and I/O sizes Switch MD over to the new disk_stack_limits() function which checks for aligment and adjusts preferred I/O sizes when stacking. Also indicate preferred I/O sizes where applicable. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-07-01 09:13:45 +08:00
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
blk_queue_io_opt(mddev->queue,
(mddev->chunk_sectors << 9) * mddev->raid_disks);
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: done.\n", mdname(mddev));
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
*private_conf = conf;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
return 0;
md: raid0: Make raid0_run() return a proper error code. Currently raid0_run() always returns -ENOMEM on errors. This is incorrect as running the array might fail for other reasons, for example because not all component devices were available. This patch changes create_strip_zones() so that it returns a proper error code (either -ENOMEM or -EINVAL) rather than 1 on errors and makes raid0_run(), its single caller, return that value instead of -ENOMEM. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:21 +08:00
abort:
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
*private_conf = NULL;
md: raid0: Allocate all buffers for the raid0 configuration in one function. Currently the raid0 configuration is allocated in raid0_run() while the buffers for the strip_zone and the dev_list arrays are allocated in create_strip_zones(). On errors, all three buffers are freed in raid0_run(). It's easier and more readable to do the allocation and cleanup within a single function. So move that code into create_strip_zones(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:36 +08:00
return err;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
/**
* raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
* @q: request queue
Add bvec_merge_data to handle stacked devices and ->merge_bvec() When devices are stacked, one device's merge_bvec_fn may need to perform the mapping and then call one or more functions for its underlying devices. The following bio fields are used: bio->bi_sector bio->bi_bdev bio->bi_size bio->bi_rw using bio_data_dir() This patch creates a new struct bvec_merge_data holding a copy of those fields to avoid having to change them directly in the struct bio when going down the stack only to have to change them back again on the way back up. (And then when the bio gets mapped for real, the whole exercise gets repeated, but that's a problem for another day...) Signed-off-by: Alasdair G Kergon <agk@redhat.com> Cc: Neil Brown <neilb@suse.de> Cc: Milan Broz <mbroz@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-07-03 15:53:43 +08:00
* @bvm: properties of new bio
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
* @biovec: the request that could be merged to it.
*
* Return amount of bytes we can accept at this offset
*/
Add bvec_merge_data to handle stacked devices and ->merge_bvec() When devices are stacked, one device's merge_bvec_fn may need to perform the mapping and then call one or more functions for its underlying devices. The following bio fields are used: bio->bi_sector bio->bi_bdev bio->bi_size bio->bi_rw using bio_data_dir() This patch creates a new struct bvec_merge_data holding a copy of those fields to avoid having to change them directly in the struct bio when going down the stack only to have to change them back again on the way back up. (And then when the bio gets mapped for real, the whole exercise gets repeated, but that's a problem for another day...) Signed-off-by: Alasdair G Kergon <agk@redhat.com> Cc: Neil Brown <neilb@suse.de> Cc: Milan Broz <mbroz@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-07-03 15:53:43 +08:00
static int raid0_mergeable_bvec(struct request_queue *q,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
mddev_t *mddev = q->queuedata;
Add bvec_merge_data to handle stacked devices and ->merge_bvec() When devices are stacked, one device's merge_bvec_fn may need to perform the mapping and then call one or more functions for its underlying devices. The following bio fields are used: bio->bi_sector bio->bi_bdev bio->bi_size bio->bi_rw using bio_data_dir() This patch creates a new struct bvec_merge_data holding a copy of those fields to avoid having to change them directly in the struct bio when going down the stack only to have to change them back again on the way back up. (And then when the bio gets mapped for real, the whole exercise gets repeated, but that's a problem for another day...) Signed-off-by: Alasdair G Kergon <agk@redhat.com> Cc: Neil Brown <neilb@suse.de> Cc: Milan Broz <mbroz@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-07-03 15:53:43 +08:00
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
int max;
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
unsigned int chunk_sectors = mddev->chunk_sectors;
Add bvec_merge_data to handle stacked devices and ->merge_bvec() When devices are stacked, one device's merge_bvec_fn may need to perform the mapping and then call one or more functions for its underlying devices. The following bio fields are used: bio->bi_sector bio->bi_bdev bio->bi_size bio->bi_rw using bio_data_dir() This patch creates a new struct bvec_merge_data holding a copy of those fields to avoid having to change them directly in the struct bio when going down the stack only to have to change them back again on the way back up. (And then when the bio gets mapped for real, the whole exercise gets repeated, but that's a problem for another day...) Signed-off-by: Alasdair G Kergon <agk@redhat.com> Cc: Neil Brown <neilb@suse.de> Cc: Milan Broz <mbroz@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-07-03 15:53:43 +08:00
unsigned int bio_sectors = bvm->bi_size >> 9;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: raid0: chunk_sectors cleanups. following the conversion to chunk_sectors, there is room for cleaning up a little. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:47:00 +08:00
if (is_power_of_2(chunk_sectors))
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
max = (chunk_sectors - ((sector & (chunk_sectors-1))
+ bio_sectors)) << 9;
else
max = (chunk_sectors - (sector_div(sector, chunk_sectors)
+ bio_sectors)) << 9;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
if (max < 0) max = 0; /* bio_add cannot handle a negative return */
if (max <= biovec->bv_len && bio_sectors == 0)
return biovec->bv_len;
else
return max;
}
md: add 'size' as a personality method In preparation for giving userspace control over ->array_sectors we need to be able to retrieve the 'default' size, and the 'anticipated' size when a reshape is requested. For personalities that do not reshape emit a warning if anything but the default size is requested. In the raid5 case we need to update ->previous_raid_disks to make the new 'default' size available. Reviewed-by: Andre Noll <maan@systemlinux.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-03-18 09:10:40 +08:00
static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
sector_t array_sectors = 0;
mdk_rdev_t *rdev;
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
list_for_each_entry(rdev, &mddev->disks, same_set)
array_sectors += rdev->sectors;
return array_sectors;
}
md: raid0: Remove hash spacing and sector shift. The "sector_shift" and "spacing" fields of struct raid0_private_data were only used for the hash table lookups. So the removal of the hash table allows get rid of these fields as well which simplifies create_strip_zones() and raid0_run() quite a bit. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:10 +08:00
static int raid0_run(mddev_t *mddev)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
raid0_conf_t *conf;
md: raid0: Make raid0_run() return a proper error code. Currently raid0_run() always returns -ENOMEM on errors. This is incorrect as running the array might fail for other reasons, for example because not all component devices were available. This patch changes create_strip_zones() so that it returns a proper error code (either -ENOMEM or -EINVAL) rather than 1 on errors and makes raid0_run(), its single caller, return that value instead of -ENOMEM. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:47:21 +08:00
int ret;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
if (mddev->chunk_sectors == 0) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: chunk size must be set.\n",
mdname(mddev));
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
return -EINVAL;
}
md: Move check for bitmap presence to personality code. If the superblock of a component device indicates the presence of a bitmap but the corresponding raid personality does not support bitmaps (raid0, linear, multipath, faulty), then something is seriously wrong and we'd better refuse to run such an array. Currently, this check is performed while the superblocks are examined, i.e. before entering personality code. Therefore the generic md layer must know which raid levels support bitmaps and which do not. This patch avoids this layer violation without adding identical code to various personalities. This is accomplished by introducing a new public function to md.c, md_check_no_bitmap(), which replaces the hard-coded checks in the superblock loading functions. A call to md_check_no_bitmap() is added to the ->run method of each personality which does not support bitmaps and assembly is aborted if at least one component device contains a bitmap. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:49:23 +08:00
if (md_check_no_bitmap(mddev))
return -EINVAL;
block: Rename blk_queue_max_sectors to blk_queue_max_hw_sectors The block layer calling convention is blk_queue_<limit name>. blk_queue_max_sectors predates this practice, leading to some confusion. Rename the function to appropriately reflect that its intended use is to set max_hw_sectors. Also introduce a temporary wrapper for backwards compability. This can be removed after the merge window is closed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-02-26 13:20:38 +08:00
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
Remove blkdev warning triggered by using md As setting and clearing queue flags now requires that we hold a spinlock on the queue, and as blk_queue_stack_limits is called without that lock, get the lock inside blk_queue_stack_limits. For blk_queue_stack_limits to be able to find the right lock, each md personality needs to set q->queue_lock to point to the appropriate lock. Those personalities which didn't previously use a spin_lock, us q->__queue_lock. So always initialise that lock when allocated. With this in place, setting/clearing of the QUEUE_FLAG_PLUGGED bit will no longer cause warnings as it will be clear that the proper lock is held. Thanks to Dan Williams for review and fixing the silly bugs. Signed-off-by: NeilBrown <neilb@suse.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Alistair John Strachan <alistair@devzero.co.uk> Cc: Nick Piggin <npiggin@suse.de> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Jacek Luczak <difrost.kernel@gmail.com> Cc: Prakash Punnoor <prakash@punnoor.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-15 07:05:54 +08:00
mddev->queue->queue_lock = &mddev->queue->__queue_lock;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
/* if private is not null, we are here after takeover */
if (mddev->private == NULL) {
ret = create_strip_zones(mddev, &conf);
if (ret < 0)
return ret;
mddev->private = conf;
}
conf = mddev->private;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/* calculate array device size */
md: centralize ->array_sectors modifications Get personalities out of the business of directly modifying ->array_sectors. Lays groundwork to introduce policy on when ->array_sectors can be modified. Reviewed-by: Andre Noll <maan@systemlinux.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-03-31 11:59:03 +08:00
md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n",
mdname(mddev),
(unsigned long long)mddev->array_sectors);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/* calculate the max read-ahead size.
* For read-ahead of large files to be effective, we need to
* readahead at least twice a whole stripe. i.e. number of devices
* multiplied by chunk size times 2.
* If an individual device has an ra_pages greater than the
* chunk size, then we will not drive that device as hard as it
* wants. We consider this a configuration error: a larger
* chunksize should be used in that case.
*/
{
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
int stripe = mddev->raid_disks *
(mddev->chunk_sectors << 9) / PAGE_SIZE;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
}
blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
md: have raid0 report its formation Report to the user what are the raid zones Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:00:54 +08:00
dump_zones(mddev);
md: Push down data integrity code to personalities. This patch replaces md_integrity_check() by two new public functions: md_integrity_register() and md_integrity_add_rdev() which are both personality-independent. md_integrity_register() is called from the ->run and ->hot_remove methods of all personalities that support data integrity. The function iterates over the component devices of the array and determines if all active devices are integrity capable and if their profiles match. If this is the case, the common profile is registered for the mddev via blk_integrity_register(). The second new function, md_integrity_add_rdev() is called from the ->hot_add_disk methods, i.e. whenever a new device is being added to a raid array. If the new device does not support data integrity, or has a profile different from the one already registered, data integrity for the mddev is disabled. For raid0 and linear, only the call to md_integrity_register() from the ->run method is necessary. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-08-03 08:59:47 +08:00
md_integrity_register(mddev);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
return 0;
}
md: raid0: Fix a memory leak when stopping a raid0 array. raid0_stop() removes all references to the raid0 configuration but misses to free the ->devlist buffer. This patch closes this leak, removes a pointless initialization and fixes a coding style issue in raid0_stop(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:48:19 +08:00
static int raid0_stop(mddev_t *mddev)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
md: remove mddev_to_conf "helper" macro Having a macro just to cast a void* isn't really helpful. I would must rather see that we are simply de-referencing ->private, than have to know what the macro does. So open code the macro everywhere and remove the pointless cast. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:54:21 +08:00
raid0_conf_t *conf = mddev->private;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
[PATCH] md: remove unneeded NULL checks before kfree This patch removes some unneeded checks of pointers being NULL before calling kfree() on them. kfree() handles NULL pointers just fine, checking first is pointless. Signed-off-by: Jesper Juhl <juhl-lkml@dif.dk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 08:17:30 +08:00
kfree(conf->strip_zone);
md: raid0: Fix a memory leak when stopping a raid0 array. raid0_stop() removes all references to the raid0 configuration but misses to free the ->devlist buffer. This patch closes this leak, removes a pointless initialization and fixes a coding style issue in raid0_stop(). Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:48:19 +08:00
kfree(conf->devlist);
[PATCH] md: remove unneeded NULL checks before kfree This patch removes some unneeded checks of pointers being NULL before calling kfree() on them. kfree() handles NULL pointers just fine, checking first is pointless. Signed-off-by: Jesper Juhl <juhl-lkml@dif.dk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 08:17:30 +08:00
kfree(conf);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
mddev->private = NULL;
return 0;
}
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
/* Find the zone which holds a particular offset
* Update *sectorp to be an offset in that zone
*/
md: raid0: Replace hash table lookup by looping over all strip_zones. The number of strip_zones of a raid0 array is bounded by the number of drives in the array and is in fact much smaller for typical setups. For example, any raid0 array containing identical disks will have only a single strip_zone. Therefore, the hash tables which are used for quickly finding the strip_zone that holds a particular sector are of questionable value and add quite a bit of unnecessary complexity. This patch replaces the hash table lookup by equivalent code which simply loops over all strip zones to find the zone that holds the given sector. In order to make this loop as fast as possible, the zone->start field of struct strip_zone has been renamed to zone_end, and it now stores the beginning of the next zone in sectors. This allows to save one addition in the loop. Subsequent cleanup patches will remove the hash table structure. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:18:43 +08:00
static struct strip_zone *find_zone(struct raid0_private_data *conf,
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
sector_t *sectorp)
md: raid0: Replace hash table lookup by looping over all strip_zones. The number of strip_zones of a raid0 array is bounded by the number of drives in the array and is in fact much smaller for typical setups. For example, any raid0 array containing identical disks will have only a single strip_zone. Therefore, the hash tables which are used for quickly finding the strip_zone that holds a particular sector are of questionable value and add quite a bit of unnecessary complexity. This patch replaces the hash table lookup by equivalent code which simply loops over all strip zones to find the zone that holds the given sector. In order to make this loop as fast as possible, the zone->start field of struct strip_zone has been renamed to zone_end, and it now stores the beginning of the next zone in sectors. This allows to save one addition in the loop. Subsequent cleanup patches will remove the hash table structure. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:18:43 +08:00
{
int i;
struct strip_zone *z = conf->strip_zone;
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
sector_t sector = *sectorp;
md: raid0: Replace hash table lookup by looping over all strip_zones. The number of strip_zones of a raid0 array is bounded by the number of drives in the array and is in fact much smaller for typical setups. For example, any raid0 array containing identical disks will have only a single strip_zone. Therefore, the hash tables which are used for quickly finding the strip_zone that holds a particular sector are of questionable value and add quite a bit of unnecessary complexity. This patch replaces the hash table lookup by equivalent code which simply loops over all strip zones to find the zone that holds the given sector. In order to make this loop as fast as possible, the zone->start field of struct strip_zone has been renamed to zone_end, and it now stores the beginning of the next zone in sectors. This allows to save one addition in the loop. Subsequent cleanup patches will remove the hash table structure. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:18:43 +08:00
for (i = 0; i < conf->nr_strip_zones; i++)
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
if (sector < z[i].zone_end) {
if (i)
*sectorp = sector - z[i-1].zone_end;
md: raid0: Replace hash table lookup by looping over all strip_zones. The number of strip_zones of a raid0 array is bounded by the number of drives in the array and is in fact much smaller for typical setups. For example, any raid0 array containing identical disks will have only a single strip_zone. Therefore, the hash tables which are used for quickly finding the strip_zone that holds a particular sector are of questionable value and add quite a bit of unnecessary complexity. This patch replaces the hash table lookup by equivalent code which simply loops over all strip zones to find the zone that holds the given sector. In order to make this loop as fast as possible, the zone->start field of struct strip_zone has been renamed to zone_end, and it now stores the beginning of the next zone in sectors. This allows to save one addition in the loop. Subsequent cleanup patches will remove the hash table structure. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:18:43 +08:00
return z + i;
md: raid0: remove ->sectors from the strip_zone structure. storing ->sectors is redundant as is can be computed from the difference z->zone_end - (z-1)->zone_end The one place where it is used, it is just as efficient to use a zone_end value instead. And removing it makes strip_zone smaller, so they array of these that is searched on every request has a better chance to say in cache. So discard the field and get the value from elsewhere. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:50:35 +08:00
}
md: raid0: Replace hash table lookup by looping over all strip_zones. The number of strip_zones of a raid0 array is bounded by the number of drives in the array and is in fact much smaller for typical setups. For example, any raid0 array containing identical disks will have only a single strip_zone. Therefore, the hash tables which are used for quickly finding the strip_zone that holds a particular sector are of questionable value and add quite a bit of unnecessary complexity. This patch replaces the hash table lookup by equivalent code which simply loops over all strip zones to find the zone that holds the given sector. In order to make this loop as fast as possible, the zone->start field of struct strip_zone has been renamed to zone_end, and it now stores the beginning of the next zone in sectors. This allows to save one addition in the loop. Subsequent cleanup patches will remove the hash table structure. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:18:43 +08:00
BUG();
}
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
/*
* remaps the bio to the target device. we separate two flows.
* power 2 flow and a general flow for the sake of perfromance
*/
static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone,
sector_t sector, sector_t *sector_offset)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
unsigned int sect_in_chunk;
sector_t chunk;
md: remove mddev_to_conf "helper" macro Having a macro just to cast a void* isn't really helpful. I would must rather see that we are simply de-referencing ->private, than have to know what the macro does. So open code the macro everywhere and remove the pointless cast. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:54:21 +08:00
raid0_conf_t *conf = mddev->private;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
int raid_disks = conf->strip_zone[0].nb_dev;
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
unsigned int chunk_sects = mddev->chunk_sectors;
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
md: raid0: chunk_sectors cleanups. following the conversion to chunk_sectors, there is room for cleaning up a little. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:47:00 +08:00
if (is_power_of_2(chunk_sects)) {
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
int chunksect_bits = ffz(~chunk_sects);
/* find the sector offset inside the chunk */
sect_in_chunk = sector & (chunk_sects - 1);
sector >>= chunksect_bits;
/* chunk in zone */
chunk = *sector_offset;
/* quotient is the chunk in real device*/
sector_div(chunk, zone->nb_dev << chunksect_bits);
} else{
sect_in_chunk = sector_div(sector, chunk_sects);
chunk = *sector_offset;
sector_div(chunk, chunk_sects * zone->nb_dev);
}
/*
* position the bio over the real device
* real sector = chunk in device + starting of zone
* + the position in the chunk
*/
*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
return conf->devlist[(zone - conf->strip_zone)*raid_disks
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
+ sector_div(sector, zone->nb_dev)];
}
/*
* Is io distribute over 1 or more chunks ?
*/
static inline int is_io_in_chunk_boundary(mddev_t *mddev,
unsigned int chunk_sects, struct bio *bio)
{
md: raid0: chunk_sectors cleanups. following the conversion to chunk_sectors, there is room for cleaning up a little. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:47:00 +08:00
if (likely(is_power_of_2(chunk_sects))) {
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
+ (bio->bi_size >> 9));
} else{
sector_t sector = bio->bi_sector;
return chunk_sects >= (sector_div(sector, chunk_sects)
+ (bio->bi_size >> 9));
}
}
md: pass mddev to make_request functions rather than request_queue We used to pass the personality make_request function direct to the block layer so the first argument had to be a queue. But now we have the intermediary md_make_request so it makes at lot more sense to pass a struct mddev_s. It makes it possible to have an mddev without its own queue too. Signed-off-by: NeilBrown <neilb@suse.de>
2010-04-01 12:02:13 +08:00
static int raid0_make_request(mddev_t *mddev, struct bio *bio)
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
{
unsigned int chunk_sects;
sector_t sector_offset;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
struct strip_zone *zone;
mdk_rdev_t *tmp_dev;
bio: first step in sanitizing the bio->bi_rw flag testing Get rid of any functions that test for these bits and make callers use bio_rw_flagged() directly. Then it is at least directly apparent what variable and flag they check. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-11 20:32:04 +08:00
if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
md: support barrier requests on all personalities. Previously barriers were only supported on RAID1. This is because other levels requires synchronisation across all devices and so needed a different approach. Here is that approach. When a barrier arrives, we send a zero-length barrier to every active device. When that completes - and if the original request was not empty - we submit the barrier request itself (with the barrier flag cleared) and then submit a fresh load of zero length barriers. The barrier request itself is asynchronous, but any subsequent request will block until the barrier completes. The reason for clearing the barrier flag is that a barrier request is allowed to fail. If we pass a non-empty barrier through a striping raid level it is conceivable that part of it could succeed and part could fail. That would be way too hard to deal with. So if the first run of zero length barriers succeed, we assume all is sufficiently well that we send the request and ignore errors in the second run of barriers. RAID5 needs extra care as write requests may not have been submitted to the underlying devices yet. So we flush the stripe cache before proceeding with the barrier. Note that the second set of zero-length barriers are submitted immediately after the original request is submitted. Thus when a personality finds mddev->barrier to be set during make_request, it should not return from make_request until the corresponding per-device request(s) have been queued. That will be done in later patches. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Andre Noll <maan@systemlinux.org>
2009-12-14 09:49:49 +08:00
md_barrier_request(mddev, bio);
[PATCH] md: fail IO request to md that require a barrier. md does not yet support BIO_RW_BARRIER, so be honest about it and fail (-EOPNOTSUPP) any such requests. Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-10 07:23:41 +08:00
return 0;
}
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
chunk_sects = mddev->chunk_sectors;
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
sector_t sector = bio->bi_sector;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
struct bio_pair *bp;
/* Sanity check -- queue functions should prevent this happening */
if (bio->bi_vcnt != 1 ||
bio->bi_idx != 0)
goto bad_map;
/* This is a one page bio that upper layers
* refuse to split for us, so we need to split it.
*/
md: raid0: chunk_sectors cleanups. following the conversion to chunk_sectors, there is room for cleaning up a little. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:47:00 +08:00
if (likely(is_power_of_2(chunk_sects)))
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
bp = bio_split(bio, chunk_sects - (sector &
(chunk_sects-1)));
else
bp = bio_split(bio, chunk_sects -
sector_div(sector, chunk_sects));
md: pass mddev to make_request functions rather than request_queue We used to pass the personality make_request function direct to the block layer so the first argument had to be a queue. But now we have the intermediary md_make_request so it makes at lot more sense to pass a struct mddev_s. It makes it possible to have an mddev without its own queue too. Signed-off-by: NeilBrown <neilb@suse.de>
2010-04-01 12:02:13 +08:00
if (raid0_make_request(mddev, &bp->bio1))
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
generic_make_request(&bp->bio1);
md: pass mddev to make_request functions rather than request_queue We used to pass the personality make_request function direct to the block layer so the first argument had to be a queue. But now we have the intermediary md_make_request so it makes at lot more sense to pass a struct mddev_s. It makes it possible to have an mddev without its own queue too. Signed-off-by: NeilBrown <neilb@suse.de>
2010-04-01 12:02:13 +08:00
if (raid0_make_request(mddev, &bp->bio2))
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
generic_make_request(&bp->bio2);
bio_pair_release(bp);
return 0;
}
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
sector_offset = bio->bi_sector;
zone = find_zone(mddev->private, &sector_offset);
tmp_dev = map_sector(mddev, zone, bio->bi_sector,
&sector_offset);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
bio->bi_bdev = tmp_dev->bdev;
md: raid0 :Enables chunk size other than powers of 2. Maintain two flows, one for pow2 chunk sizes (which uses masks and shift), and a flow for the general case (which uses sector_div). This is for the sake of performance. - introduce map_sector and is_io_in_chunk_boundary to encapsulate those two flows better for raid0_make_request - fix blk_mergeable to support the two flows. Signed-off-by: raziebe@gmail.com Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 15:02:05 +08:00
bio->bi_sector = sector_offset + zone->dev_start +
tmp_dev->data_offset;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
/*
* Let the main block layer submit the IO and resolve recursion:
*/
return 1;
bad_map:
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk("md/raid0:%s: make_request bug: can't convert block across chunks"
" or bigger than %dk %llu %d\n",
mdname(mddev), chunk_sects / 2,
(unsigned long long)bio->bi_sector, bio->bi_size >> 10);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
Drop 'size' argument from bio_endio and bi_end_io As bi_end_io is only called once when the reqeust is complete, the 'size' argument is now redundant. Remove it. Now there is no need for bio_endio to subtract the size completed from bi_size. So don't do that either. While we are at it, change bi_end_io to return void. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-09-27 18:47:43 +08:00
bio_io_error(bio);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
return 0;
}
md: fix a bug in some never-used code. http://bugzilla.kernel.org/show_bug.cgi?id=3277 There is a seq_printf here that isn't being passed a 'seq'. Howeve as the code is inside #ifdef MD_DEBUG, nobody noticed. Also remove some extra spaces. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:30:53 +08:00
md: have raid0 compile with MD_DEBUG on Because of the removal of the device list from the strips raid0 did not compile with MD_DEBUG flag on Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:57:40 +08:00
static void raid0_status(struct seq_file *seq, mddev_t *mddev)
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
#undef MD_DEBUG
#ifdef MD_DEBUG
int j, k, h;
char b[BDEVNAME_SIZE];
md: remove mddev_to_conf "helper" macro Having a macro just to cast a void* isn't really helpful. I would must rather see that we are simply de-referencing ->private, than have to know what the macro does. So open code the macro everywhere and remove the pointless cast. Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:54:21 +08:00
raid0_conf_t *conf = mddev->private;
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
int raid_disks = conf->strip_zone[0].nb_dev;
md: fix a bug in some never-used code. http://bugzilla.kernel.org/show_bug.cgi?id=3277 There is a seq_printf here that isn't being passed a 'seq'. Howeve as the code is inside #ifdef MD_DEBUG, nobody noticed. Also remove some extra spaces. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:30:53 +08:00
md: have raid0 compile with MD_DEBUG on Because of the removal of the device list from the strips raid0 did not compile with MD_DEBUG flag on Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:57:40 +08:00
sector_t zone_size;
sector_t zone_start = 0;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
h = 0;
md: have raid0 compile with MD_DEBUG on Because of the removal of the device list from the strips raid0 did not compile with MD_DEBUG flag on Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:57:40 +08:00
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
for (j = 0; j < conf->nr_strip_zones; j++) {
seq_printf(seq, " z%d", j);
seq_printf(seq, "=[");
for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
md: fix a bug in some never-used code. http://bugzilla.kernel.org/show_bug.cgi?id=3277 There is a seq_printf here that isn't being passed a 'seq'. Howeve as the code is inside #ifdef MD_DEBUG, nobody noticed. Also remove some extra spaces. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:30:53 +08:00
seq_printf(seq, "%s/", bdevname(
md: don't use mddev->raid_disks in raid0 or raid10 while array is active. In a subsequent patch we will make it possible to change mddev->raid_disks while a RAID0 or RAID10 array is active. This is part of the process of reshaping such an array. This means that we cannot use this value while processes requests (it is OK to use it during initialisation as we are locked against changes then). Both RAID0 and RAID10 have the same value stored in the private data structure, so use that value instead. Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-16 14:23:35 +08:00
conf->devlist[j*raid_disks + k]
md: have raid0 compile with MD_DEBUG on Because of the removal of the device list from the strips raid0 did not compile with MD_DEBUG flag on Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-16 14:57:40 +08:00
->bdev, b));
zone_size = conf->strip_zone[j].zone_end - zone_start;
seq_printf(seq, "] ze=%lld ds=%lld s=%lld\n",
(unsigned long long)zone_start>>1,
(unsigned long long)conf->strip_zone[j].dev_start>>1,
(unsigned long long)zone_size>>1);
zone_start = conf->strip_zone[j].zone_end;
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
#endif
md: Make mddev->chunk_size sector-based. This patch renames the chunk_size field to chunk_sectors with the implied change of semantics. Since is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9) = is_power_of_2(chunk_sectors) these bits don't need an adjustment for the shift. Signed-off-by: Andre Noll <maan@systemlinux.org> Signed-off-by: NeilBrown <neilb@suse.de>
2009-06-18 06:45:01 +08:00
seq_printf(seq, " %dk chunks", mddev->chunk_sectors / 2);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
return;
}
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
static void *raid0_takeover_raid5(mddev_t *mddev)
{
mdk_rdev_t *rdev;
raid0_conf_t *priv_conf;
if (mddev->degraded != 1) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: raid5 must be degraded! Degraded disks: %d\n",
mdname(mddev),
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
mddev->degraded);
return ERR_PTR(-EINVAL);
}
list_for_each_entry(rdev, &mddev->disks, same_set) {
/* check slot number for a disk */
if (rdev->raid_disk == mddev->raid_disks-1) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n",
mdname(mddev));
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
return ERR_PTR(-EINVAL);
}
}
/* Set new parameters */
mddev->new_level = 0;
md: clear layout after ->raid0 takeover After takeover from raid5/10 -> raid0 mddev->layout is not cleared. Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-06-16 18:55:14 +08:00
mddev->new_layout = 0;
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->raid_disks--;
mddev->delta_disks = -1;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
create_strip_zones(mddev, &priv_conf);
return priv_conf;
}
static void *raid0_takeover_raid10(mddev_t *mddev)
{
raid0_conf_t *priv_conf;
/* Check layout:
* - far_copies must be 1
* - near_copies must be 2
* - disks number must be even
* - all mirrors must be already degraded
*/
if (mddev->layout != ((1 << 8) + 2)) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takover layout: 0x%x\n",
mdname(mddev),
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
mddev->layout);
return ERR_PTR(-EINVAL);
}
if (mddev->raid_disks & 1) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: Raid0 cannot takover Raid10 with odd disk number.\n",
mdname(mddev));
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
return ERR_PTR(-EINVAL);
}
if (mddev->degraded != (mddev->raid_disks>>1)) {
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: All mirrors must be already degraded!\n",
mdname(mddev));
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
return ERR_PTR(-EINVAL);
}
/* Set new parameters */
mddev->new_level = 0;
md: clear layout after ->raid0 takeover After takeover from raid5/10 -> raid0 mddev->layout is not cleared. Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-06-16 18:55:14 +08:00
mddev->new_layout = 0;
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->delta_disks = - mddev->raid_disks / 2;
mddev->raid_disks += mddev->delta_disks;
mddev->degraded = 0;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
create_strip_zones(mddev, &priv_conf);
return priv_conf;
}
static void *raid0_takeover(mddev_t *mddev)
{
/* raid0 can take over:
* raid5 - providing it is Raid4 layout and one disk is faulty
* raid10 - assuming we have all necessary active disks
*/
if (mddev->level == 5) {
if (mddev->layout == ALGORITHM_PARITY_N)
return raid0_takeover_raid5(mddev);
md/raid0: tidy up printk messages. All messages now start md/raid0:md-device-name: Signed-off-by: NeilBrown <neilb@suse.de>
2010-05-03 13:06:27 +08:00
printk(KERN_ERR "md/raid0:%s: Raid can only takeover Raid5 with layout: %d\n",
mdname(mddev), ALGORITHM_PARITY_N);
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
}
if (mddev->level == 10)
return raid0_takeover_raid10(mddev);
return ERR_PTR(-EINVAL);
}
static void raid0_quiesce(mddev_t *mddev, int state)
{
}
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
static struct mdk_personality raid0_personality=
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
{
.name = "raid0",
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
.level = 0,
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
.owner = THIS_MODULE,
.make_request = raid0_make_request,
.run = raid0_run,
.stop = raid0_stop,
.status = raid0_status,
md: add 'size' as a personality method In preparation for giving userspace control over ->array_sectors we need to be able to retrieve the 'default' size, and the 'anticipated' size when a reshape is requested. For personalities that do not reshape emit a warning if anything but the default size is requested. In the raid5 case we need to update ->previous_raid_disks to make the new 'default' size available. Reviewed-by: Andre Noll <maan@systemlinux.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-03-18 09:10:40 +08:00
.size = raid0_size,
md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover Signed-off-by: Maciej Trela <maciej.trela@intel.com> Signed-off-by: NeilBrown <neilb@suse.de>
2010-03-08 13:02:44 +08:00
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
};
static int __init raid0_init (void)
{
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
return register_md_personality (&raid0_personality);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
static void raid0_exit (void)
{
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
unregister_md_personality (&raid0_personality);
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
}
module_init(raid0_init);
module_exit(raid0_exit);
MODULE_LICENSE("GPL");
md: add MODULE_DESCRIPTION for all md related modules. Suggested by Oren Held <orenhe@il.ibm.com> Signed-off-by: NeilBrown <neilb@suse.de>
2009-12-14 09:49:58 +08:00
MODULE_DESCRIPTION("RAID0 (striping) personality for MD");
Linux-2.6.12-rc2 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!
2005-04-17 06:20:36 +08:00
MODULE_ALIAS("md-personality-2"); /* RAID0 */
[PATCH] md: allow array level to be set textually via sysfs Signed-off-by: Neil Brown <neilb@suse.de> Acked-by: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:51 +08:00
MODULE_ALIAS("md-raid0");
[PATCH] md: remove personality numbering from md md supports multiple different RAID level, each being implemented by a 'personality' (which is often in a separate module). These personalities have fairly artificial 'numbers'. The numbers are use to: 1- provide an index into an array where the various personalities are recorded 2- identify the module (via an alias) which implements are particular personality. Neither of these uses really justify the existence of personality numbers. The array can be replaced by a linked list which is searched (array lookup only happens very rarely). Module identification can be done using an alias based on level rather than 'personality' number. The current 'raid5' modules support two level (4 and 5) but only one personality. This slight awkwardness (which was handled in the mapping from level to personality) can be better handled by allowing raid5 to register 2 personalities. With this change in place, the core md module does not need to have an exhaustive list of all possible personalities, so other personalities can be added independently. This patch also moves the check for chunksize being non-zero into the ->run routines for the personalities that need it, rather than having it in core-md. This has a side effect of allowing 'faulty' and 'linear' not to have a chunk-size set. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 16:20:36 +08:00
MODULE_ALIAS("md-level-0");