We've noticed severe lasting performance degradation of our raid
arrays when we have drives that yield large amounts of media errors.
The raid10 module will queue each failed read for retry, and also
will attempt call fix_read_error() to perform the read recovery.
Read recovery is performed while the array is frozen, so repeated
recovery attempts can degrade the performance of the array for
extended periods of time.
With this patch I propose adding a per md device max number of
corrected read attempts. Each rdev will maintain a count of
read correction attempts in the rdev->read_errors field (not
used currently for raid10). When we enter fix_read_error()
we'll check to see when the last read error occurred, and
divide the read error count by 2 for every hour since the
last read error. If at that point our read error count
exceeds the read error threshold, we'll fail the raid device.
In addition in this patch I add sysfs nodes (get/set) for
the per md max_read_errors attribute, the rdev->read_errors
attribute, and added some printk's to indicate when
fix_read_error fails to repair an rdev.
For testing I used debugfs->fail_make_request to inject
IO errors to the rdev while doing IO to the raid array.
Signed-off-by: Robert Becker <Rob.Becker@riverbed.com>
Signed-off-by: NeilBrown <neilb@suse.de>
When we get a read error on a device in a RAID10, and attempting to
repair the error fails, print more useful messages about why it
failed.
Signed-off-by: Robert Becker <Rob.Becker@riverbed.com>
Signed-off-by: NeilBrown <neilb@suse.de>
There is a sysfs file which allows bits in the write-intent
bitmap to be explicit set - indicating that the block is thought
to be 'dirty'.
When this happens we should really set recovery_cp backwards
to include the block to reflect this dirtiness.
In particular, a 'resync' process will refuse to start if
recovery_cp is beyond the end of the array, so this is needed
to allow a resync to be triggered.
Signed-off-by: NeilBrown <neilb@suse.de>
In this case, the metadata needs to not be in the same
sector as the bitmap.
md will not read/write any bitmap metadata. Config must be
done via sysfs and when a recovery makes the array non-degraded
again, writing 'true' to 'bitmap/can_clear' will allow bits in
the bitmap to be cleared again.
Signed-off-by: NeilBrown <neilb@suse.de>
Setting daemon_lastrun really has nothing to do with reading
the bitmap superblock, it just happens to be needed at the same time.
bitmap_read_sb is about to become options, so move that code out
to after the call to bitmap_read_sb.
Signed-off-by: NeilBrown <neilb@suse.de>
A new attribute directory 'bitmap' in 'md' is created which
contains files for configuring the bitmap.
'location' identifies where the bitmap is, either 'none',
or 'file' or 'sector offset from metadata'.
Writing 'location' can create or remove a bitmap.
Adding a 'file' bitmap this way is not yet supported.
'chunksize' and 'time_base' must be set before 'location'
can be set.
'chunksize' can be set before creating a bitmap, but is
currently always over-ridden by the bitmap superblock.
'time_base' and 'backlog' can be updated at any time.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Andre Noll <maan@systemlinux.org>
safe_delay_store can parse fixed point numbers (for fractions
of a second). We will want to do that for another sysfs
file soon, so factor out the code.
Signed-off-by: NeilBrown <neilb@suse.de>
For md arrays were metadata is managed externally, the kernel does not
know about a superblock so the superblock offset is 0.
If we want to have a write-intent-bitmap near the end of the
devices of such an array, we should support sector_t sized offset.
We need offset be possibly negative for when the bitmap is before
the metadata, so use loff_t instead.
Also add sanity check that bitmap does not overlap with data.
Signed-off-by: NeilBrown <neilb@suse.de>
As bitmap_create and bitmap_destroy already set thread->timeout
as appropriate, there is no need to do it in raid10_quiesce.
There is a possible need to wake the thread after the timeout
has been set low, but it is better to do that where the timeout
is actually set low, in bitmap_create.
Signed-off-by: NeilBrown <neilb@suse.de>
... and into bitmap_info. These are all configuration parameters
that need to be set before the bitmap is created.
Signed-off-by: NeilBrown <neilb@suse.de>
In preparation for making bitmap fields configurable via sysfs,
start tidying up by making a single structure to contain the
configuration fields.
Signed-off-by: NeilBrown <neilb@suse.de>
This will allow us to stop writeout to portions of the array
while they are resynced by someone else - e.g. another node in
a cluster.
Signed-off-by: NeilBrown <neilb@suse.de>
The post-barrier-flush is sent by md as soon as make_request on the
barrier write completes. For raid5, the data might not be in the
per-device queues yet. So for barrier requests, wait for any
pre-reading to be done so that the request will be in the per-device
queues.
We use the 'preread_active' count to check that nothing is still in
the preread phase, and delay the decrement of this count until after
write requests have been submitted to the underlying devices.
Signed-off-by: NeilBrown <neilb@suse.de>
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>
If a resync/recovery/check/repair is interrupted for some reason, it
can be useful to know exactly where it got up to.
So in that case, do not clear curr_resync_completed.
Initialise it when starting a resync/recovery/... instead.
Signed-off-by: NeilBrown <neilb@suse.de>
When a 'check' or 'repair' finished we should clear resync_min
so that a future check/repair will cover the whole array (by default).
However if it is interrupted, we should update resync_min to
where we got up to, so that when the check/repair continues it
just does the remainder of the array.
Signed-off-by: NeilBrown <neilb@suse.de>
A write intent bitmap can be removed from an array while the
array is active.
When this happens, all IO is suspended and flushed before the
bitmap is removed.
However it is possible that bitmap_daemon_work is still running to
clear old bits from the bitmap. If it is, it can dereference the
bitmap after it has been freed.
So introduce a new mutex to protect bitmap_daemon_work and get it
before destroying a bitmap.
This is suitable for any current -stable kernel.
Signed-off-by: NeilBrown <neilb@suse.de>
Cc: stable@kernel.org
* 'ixp4xx' of git://git.kernel.org/pub/scm/linux/kernel/git/chris/linux-2.6:
IXP4xx: GTWX5715 platform only has two PCI IRQ lines, not four.
IXP4xx: Introduce IXP4XX_GPIO_IRQ(n) macro and convert IXP4xx platform files.
IXP4xx: move Gemtek GTWX5715 platform macros to the platform code.
IXP4xx: Remove unused Motorola PrPMC1100 platform macros.
IXP4xx: move FSG platform macros to the platform code.
IXP4xx: move DSM G600 platform macros to the platform code.
IXP4xx: move NAS100D platform macros to the platform code.
IXP4xx: move NSLU2 platform macros to the platform code.
IXP4xx: move Coyote platform macros to the platform code.
IXP4xx: move AVILA platform macros to the platform code.
IXP4xx: move IXDP425 platform macros to the platform code.
IXP4xx: Extend PCI MMIO indirect address space to 1 GB.
IXP4xx: Fix compilation failure with CONFIG_IXP4XX_INDIRECT_PCI.
IXP4xx: Drop "__ixp4xx_" prefix from in/out/ioread/iowrite functions for clarity.
IXP4xx: Rename indirect MMIO primitives from __ixp4xx_* to __indirect_*.
IXP4xx: Ensure index is positive in irq_to_gpio() and npe_request().
ARM: fix insl() and outsl() endianness on IXP4xx architecture.
IXP4xx: Fix normally-disabled debugging text in drivers/net/arm/ixp4xx_eth.c.
IXP4xx: change the timer base frequency to 66.666000 MHz.
As shown by the previous patch (6698e3472: "tty: Fix BKL taken under a
spinlock bug introduced in the BKL split") the BKL removal is prone to
some subtle issues, where removing the BKL in one place may in fact make
a previously nested BKL call the new outer call, and then prone to nasty
deadlocks with other spinlocks.
In general, we should never take the BKL while we're holding a spinlock,
so let's just add a "might_sleep()" to it (even though the BKL doesn't
technically sleep - at least not yet), and we'll get nice warnings the
next time this kind of problem happens during BKL removal.
Acked-and-Tested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The fasync path takes the BKL (it probably doesn't need to in fact)
while holding the file_list spinlock. You can't do that with the kernel
lock: it causes lock inversions and deadlocks.
Leave the BKL over that bit for the moment.
Identified by AKPM.
Signed-off-by: Alan Cox <alan@linux.intel.com>
Acked-and-Tested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (151 commits)
powerpc: Fix usage of 64-bit instruction in 32-bit altivec code
MAINTAINERS: Add PowerPC patterns
powerpc/pseries: Track previous CPPR values to correctly EOI interrupts
powerpc/pseries: Correct pseries/dlpar.c build break without CONFIG_SMP
powerpc: Make "intspec" pointers in irq_host->xlate() const
powerpc/8xx: DTLB Miss cleanup
powerpc/8xx: Remove DIRTY pte handling in DTLB Error.
powerpc/8xx: Start using dcbX instructions in various copy routines
powerpc/8xx: Restore _PAGE_WRITETHRU
powerpc/8xx: Add missing Guarded setting in DTLB Error.
powerpc/8xx: Fixup DAR from buggy dcbX instructions.
powerpc/8xx: Tag DAR with 0x00f0 to catch buggy instructions.
powerpc/8xx: Update TLB asm so it behaves as linux mm expects.
powerpc/8xx: Invalidate non present TLBs
powerpc/pseries: Serialize cpu hotplug operations during deactivate Vs deallocate
pseries/pseries: Add code to online/offline CPUs of a DLPAR node
powerpc: stop_this_cpu: remove the cpu from the online map.
powerpc/pseries: Add kernel based CPU DLPAR handling
sysfs/cpu: Add probe/release files
powerpc/pseries: Kernel DLPAR Infrastructure
...
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:
ALSA: hda - Overwrite pin config on intel DG45ID board.
intelhdmi - dont power off HDA link
ALSA: hrtimer - Fix lock-up
ALSA: intelhdmi - add channel mapping for typical configurations
ALSA: intelhdmi - channel mapping applies to Pin
ALSA: intelhdmi - accept DisplayPort pin
ALSA: hda - show HBR(High Bit Rate) pin cap in procfs
ALSA: hda - Fix LED GPIO setup for HP laptops with IDT codecs
ASoC: Fix build of OMAP sound drivers
ALSA: opti93x: fix irq releasing if the irq cannot be allocated
* 'omap-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6: (75 commits)
omap3: Fix OMAP35XX_REV macros
omap: serial: fix non-empty uart fifo read abort
omap3: Zoom2/3: Update hsmmc board config params
omap3 : Enable TWL4030 Keypad for Zoom2 and Zoom3 boards
omap3: id code detection 3525 vs 3515
omap3: rx51: Use wl1251 in SPI mode 3
omap3: zoom2/3: make MMC slot work again
omap1: htcherald: Update defconfig to include mux support
omap1: LCD_DMA: Use some define rather than a hexadecimal
omap: header: remove unused data-type
omap: arch/arm/plat-omap/devices.c - sort alphabetically
omap: Correcting GPMC_CONFIG1_DEVICETYPE_NAND
OMAP3: serial - allow platforms specify which UARTs to initialize
omap3: cm-t35: add mux initialization
OMAP4: Sync up omap4430 defconfig
OMAP4: Remove the secondary wait loop
OMAP4: AuxCoreBoot registers only accessible in secure mode
OMAP4: Fix SRAM base and size
OMAP4: Fix cpu detection
omap3: pandora: board file updates for .33
...
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
be2net: fix error in rx completion processing.
igbvf: avoid reset storms due to mailbox issues
igb: fix handling of mailbox collisions between PF/VF
usb: remove rare pm primitive for conversion to new API
The pin config provided by BIOS have some problems:
0x0221401f: [Jack] HP Out at Ext Front <-- other association and sequence
0x02a19020: [Jack] Mic at Ext Front <-- other association
0x01113014: [Jack] Speaker at Ext Rear <-- line out (not speaker)
0x01114010: [Jack] Speaker at Ext Rear <-- line out
0x01a19030: [Jack] Mic at Ext Rear <-- other association
0x01111012: [Jack] Speaker at Ext Rear <-- line out
0x01116011: [Jack] Speaker at Ext Rear <-- line out
0x40f000f0: [N/A] Other at Ext N/A
0x40f000f0: [N/A] Other at Ext N/A
0x40f000f0: [N/A] Other at Ext N/A
0x40f000f0: [N/A] Other at Ext N/A
0x40f000f0: [N/A] Other at Ext N/A
0x01451140: [Jack] SPDIF Out at Ext Rear
0x40f000f0: [N/A] Other at Ext N/A
just overwrite it.
Signed-off-by: Alexey Fisher <bug-track@fisher-privat.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
There are certain skews of the NIC which have multiple bits set in
adapter->cap. Use & instead of == to process rx completions.
Signed-off-by: Ajit Khaparde <ajitk@serverengines.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change makes it so that reset/interrupt storms can be avoided when
there are mailbox issues. The new behavior is to only allow the device to
trigger mailbox related resets only once every 10 seconds.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch changes the handling of collisions between the use of the
PF/VF sides of the mailbox.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes a rare use of the USB power management API which
won't be supported after the conversion to the new generic runtime power
management framework. Functionality is not altered.
Signed-off-by: Oliver Neukum <oliver@neukum.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (75 commits)
net: Handle NETREG_UNINITIALIZED devices correctly
can: add the driver for Analog Devices Blackfin on-chip CAN controllers
xfrm: Fix truncation length of authentication algorithms installed via PF_KEY
net: use compat helper functions in compat_sys_recvmmsg
net: fix compat_sys_recvmmsg parameter type
cxgb3: Fixing EEH handlers
cnic: Zero out status block and Event Queue indices.
cnic: Send delete command when shutting down iSCSI ring.
net: smc91x: Fix up type mismatch in smc_drv_resume().
smc91x: fix unused flags warnings on UP systems
MAINTAINERS: Transfering maintainership of cdc-ether
net: Add missing TST_CFG_WRITE bits around sky2_pci_write
net: Fix Yukon-2 Optima TCP offload setup
net: niu uses crc32, so select CRC32
wireless: update old static regulatory domain rules
mac80211: Revert 'Use correct sign for mesh active path refresh'
mac80211: Fixed bug in mesh portal paths
net/mac80211: Correct size given to memset
b43: Remove reset after fatal DMA error
rtl8187: add radio led and fix warnings on suspend
...
* git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic:
asm-generic: add sys_recvmmsg to unistd.h
asm-generic: add sys_accept4 to unistd.h
asm-generic/gpio.h: add some forward decls of the device struct
asm-generic: Fix typo in asm-generic/unistd.h.
lib/checksum: fix one more thinko
lib/checksum.c: make do_csum optional
lib/checksum.c: use 32-bit arithmetic consistently
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
itimer: Fix the itimer trace print format
hrtimer: move timer stats helper functions to hrtimer.c
hrtimer: Tune hrtimer_interrupt hang logic
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
lockdep: Avoid out of bounds array reference in save_trace()
futex: Take mmap_sem for get_user_pages in fault_in_user_writeable
lockstat: Add usage info to Documentation/lockstat.txt
lockstat: Fix min, max times in /proc/lock_stats
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86/amd-iommu: Fix PCI hotplug with passthrough mode
x86/amd-iommu: Fix passthrough mode
x86: mmio-mod.c: Use pr_fmt
x86: kmmio.c: Add and use pr_fmt(fmt)
x86: i8254.c: Add pr_fmt(fmt)
x86: setup_percpu.c: Use pr_<level> and add pr_fmt(fmt)
x86: es7000_32.c: Use pr_<level> and add pr_fmt(fmt)
x86: Print DMI_BOARD_NAME as well as DMI_PRODUCT_NAME from __show_regs()
x86: Factor duplicated code out of __show_regs() into show_regs_common()
arch/x86/kernel/microcode*: Use pr_fmt() and remove duplicated KERN_ERR prefix
x86, mce: fix confusion between bank attributes and mce attributes
x86/mce: Set up timer unconditionally
x86: Fix bogus warning in apic_noop.apic_write()
x86: Fix typo in arch/x86/mm/kmmio.c
x86: ASUS P4S800 reboot=bios quirk
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: Remove comparing of NULL to va_list in trace_array_vprintk()
tracing: Fix function graph trace_pipe to properly display failed entries
tracing: Add full state to trace_seq
tracing: Buffer the output of seq_file in case of filled buffer
tracing: Only call pipe_close if pipe_close is defined
tracing: Add pipe_close interface
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (57 commits)
x86, perf events: Check if we have APIC enabled
perf_event: Fix variable initialization in other codepaths
perf kmem: Fix unused argument build warning
perf symbols: perf_header__read_build_ids() offset'n'size should be u64
perf symbols: dsos__read_build_ids() should read both user and kernel buildids
perf tools: Align long options which have no short forms
perf kmem: Show usage if no option is specified
sched: Mark sched_clock() as notrace
perf sched: Add max delay time snapshot
perf tools: Correct size given to memset
perf_event: Fix perf_swevent_hrtimer() variable initialization
perf sched: Fix for getting task's execution time
tracing/kprobes: Fix field creation's bad error handling
perf_event: Cleanup for cpu_clock_perf_event_update()
perf_event: Allocate children's perf_event_ctxp at the right time
perf_event: Clean up __perf_event_init_context()
hw-breakpoints: Modify breakpoints without unregistering them
perf probe: Update perf-probe document
perf probe: Support --del option
trace-kprobe: Support delete probe syntax
...
In original implementation, the revision passed to
these macros contained revision number in lower nibble.
But, later the revision bits (OMAP_REVBITS_XX) were
defined to use omap_revision[15:08] where revision
number is containied in higher nibble.
This patch updates the macros; else incorrect revision
is detected for OMAP35xx devices.
Signed-off-by: Sanjeev Premi <premi@ti.com>
Robert Becker