#
265054 |
|
28-Apr-2014 |
mav |
Reduce number of opens by REOM RAID during provider taste.
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.
|
#
256880 |
|
22-Oct-2013 |
mav |
Merge GEOM direct dispatch changes from the projects/camlock branch.
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
|
#
242323 |
|
29-Oct-2012 |
mav |
Add basic BIO_DELETE support to GEOM RAID class for all RAID levels.
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
|
#
241329 |
|
07-Oct-2012 |
mav |
Make graid command line a bit more friendly by allowing volume name or 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
|
#
234848 |
|
30-Apr-2012 |
mav |
Add to GEOM RAID class module, supporting the DDF metadata format, as defined by the SNIA Common RAID Disk Data Format Specification v2.0.
Supports multiple volumes per array and multiple partitions per disk. Supports standard big-endian and Adaptec's little-endian byte ordering. Supports all single-layer RAID levels. Dual-layer RAID levels except RAID10 are not supported now because of GEOM RAID design limitations.
Some work is still to be done, but the present code already manages basic interoperation with RAID BIOS of the Adaptec 1430SA SATA RAID controller.
MFC after: 1 month Sponsored by: iXsystems, Inc.
|