When CPU is not busy, those queues are typically empty. When CPU is busy,
then one more extra sorting is the last thing it needs. If specific device
(HDD) really needs sorting, then it will be done later by CAM.
This supposed to fix livelock reported for mirror of two SSDs, when UFS
fires zillion of BIO_DELETE requests, that totally blocks I/O subsystem by
pointless sorting of requests and responses under single mutex lock.
MFC after: 2 weeks
in userland rename in-kernel getenv()/setenv() to kern_setenv()/kern_getenv().
This fixes a namespace collision with libc symbols.
Submitted by: kmacy
Tested by: make universe
These changes prevent sysctl(8) from returning proper output,
such as:
1) no output from sysctl(8)
2) erroneously returning ENOMEM with tools like truss(1)
or uname(1)
truss: can not get etype: Cannot allocate memory
there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.
Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.
MFC after: 2 weeks
Sponsored by: Mellanox Technologies
Instead opening/closing provider by each of metadata classes, do it only
once in core code. Since for SCSI disks open/close means sending some
SCSI commands to the device, this change reduces taste time.
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
This caused incorrect behavior of arrays with big-endian DDF metadata.
Little-endian (like used by Adaptec controllers) should not be harmed.
Add workaround should be enough to manage compatibility.
MFC after: 2 weeks
shifts into the sign bit. Instead use (1U << 31) which gets the
expected result.
This fix is not ideal as it assumes a 32 bit int, but does fix the issue
for most cases.
A similar change was made in OpenBSD.
Discussed with: -arch, rdivacky
Reviewed by: cperciva
When safety requirements are met, it allows to avoid passing I/O requests
to GEOM g_up/g_down thread, executing them directly in the caller context.
That allows to avoid CPU bottlenecks in g_up/g_down threads, plus avoid
several context switches per I/O.
The defined now safety requirements are:
- caller should not hold any locks and should be reenterable;
- callee should not depend on GEOM dual-threaded concurency semantics;
- on the way down, if request is unmapped while callee doesn't support it,
the context should be sleepable;
- kernel thread stack usage should be below 50%.
To keep compatibility with GEOM classes not meeting above requirements
new provider and consumer flags added:
- G_CF_DIRECT_SEND -- consumer code meets caller requirements (request);
- G_CF_DIRECT_RECEIVE -- consumer code meets callee requirements (done);
- G_PF_DIRECT_SEND -- provider code meets caller requirements (done);
- G_PF_DIRECT_RECEIVE -- provider code meets callee requirements (request).
Capable GEOM class can set them, allowing direct dispatch in cases where
it is safe. If any of requirements are not met, request is queued to
g_up or g_down thread same as before.
Such GEOM classes were reviewed and updated to support direct dispatch:
CONCAT, DEV, DISK, GATE, MD, MIRROR, MULTIPATH, NOP, PART, RAID, STRIPE,
VFS, ZERO, ZFS::VDEV, ZFS::ZVOL, all classes based on g_slice KPI (LABEL,
MAP, FLASHMAP, etc).
To declare direct completion capability disk(9) KPI got new flag equivalent
to G_PF_DIRECT_SEND -- DISKFLAG_DIRECT_COMPLETION. da(4) and ada(4) disk
drivers got it set now thanks to earlier CAM locking work.
This change more then twice increases peak block storage performance on
systems with manu CPUs, together with earlier CAM locking changes reaching
more then 1 million IOPS (512 byte raw reads from 16 SATA SSDs on 4 HBAs to
256 user-level threads).
Sponsored by: iXsystems, Inc.
MFC after: 2 months
of upgrading older machines using ataraid(4) to newer releases.
This optional parameter is controlled via kern.geom.raid.legacy_aliases
and will create a /dev/ar0 device that will point at /dev/raid/r0 for
example.
Tested on Dell SC 1425 DDF-1 format software raid controllers installing from
stable/7 and upgrading to stable/9 without having to adjust /etc/fstab
Reviewed by: mav
Obtained from: Yahoo!
MFC after: 2 Weeks
unsupported metadata types like Intel Smart Response to not corrupt them.
- Improve setting of these things during metadata writing to protect from
incapable BIOS'es and other implementations.
disks should be rebuilt. Our rebuild code is same time disk-centric. To
handle this situation properly check all disks for RBLD flags, and if no
disk specified try rebuild/resync all of them except newly inserted.
Windows driver uses such migration when it creates new arrays. While GEOM
RAID has no mechanism to implement migration in general case, this specifc
case still can be handled easily via degraded RAID1 creation followed by
regular rebuild.
It is alike to RAID1, but with dedicating master and recovery disks and
providing manual control over synchronization. It allows to use recovery
disk as snapshot of the master disk from the time of the last sync.
This implementation is not functionaly complete comparing to Windows,
but it is better then silent conversion to RAID1 on first boot.
Alike to BIO_WRITE, report success if at least one subdisk succeeded with
BIO_DELETE. But unlike BIO_WRITE don't fail disk on BIO_DELETE error.
Sponsored by: iXsystems, Inc.
MFC after: 1 month
If at least one subdisk in the volume supports it, BIO_DELETE requests
will be propagated down. Unfortunatelly, for RAID levels with redundancy
unmapped blocks will be mapped back during first rebuild/resync process.
Sponsored by: iXsystems, Inc.
MFC after: 1 month
and move that action from shutdown_pre_sync to shutdown_post_sync stage
to avoid extra flapping.
ZFS tends to not close devices on shutdown, that doesn't allow GEOM RAID
to shutdown gracefully. To handle that, mark volume as clean just when
shutdown time comes and there are no active writes.
MFC after: 2 weeks
provider name to be specified instead of geom name (first argument in all
subcommands except label). In most cases there is only one array used
any way, so it is not really useful to make user type ugly geom names like
Intel-f0bdf223 or SiI-732c2b9448cf. Though they can be used in some cases.
Sponsored by: iXsystems, Inc.
MFC after: 1 month
failed while write to some other succeeded. Instead mark disk as failed.
- Make RAID1E less aggressive in failing disks to avoid volume breakage.
MFC after: 2 weeks
