In D44961#1025280, @asomers wrote:What is an "OOA queue"?
- Queries
- All Stories
- Search
- Advanced Search
- Transactions
- Transaction Logs
Feed Advanced Search
Advanced Search
Advanced Search
Today
Today
I wonder what is your queue depth, so that one message per request per 90 seconds would cause a noticeable storm. Also per-system limiting makes output not very useful, since it does not say much useful about LUNs, ports, commands, etc due to selecting first message out of many, only that something is wrong. Thinking even wider, I find those messages printed on actual completion not very useful, since if there are not a delays, but something is really wrong, the commands many never complete and so the messages may never get printed. I wonder if instead removing all this and once per second checking OOA queues for stuck requests and printing some digests would be more useful.
Sat, Apr 20
Sat, Apr 20
libpmc: Import AMD Zen 4 PMU events
Looks good to me, but if you wish, couple cosmetic thoughts.
Looks good to me, though seems only cosmetic.
Wed, Apr 17
Wed, Apr 17
ahc/ahd: Fix target mode operation
ahc/ahd: Fix target mode operation
Wed, Apr 10
Wed, Apr 10
ahc/ahd: Fix target mode operation
Mar 25 2024
Mar 25 2024
Mar 21 2024
Mar 21 2024
mav added a comment to D44426: mpi3mr: Consider Diagnostic Fault Reset Success Beyond 0xF000 fault Code.
I don't have any chip documentation to know what is right here, so just wonder if unconditional printing a bunch of raw hex numbers is expected here. It feels mpi3mr_print_fault_info() is another candidate for mpi3mr_dprint().
mav added inline comments to D44425: mpi3mr: Update consumerindex of admin and op reply queues after every 100 replies.
mav added inline comments to D44423: mpi3mr: poll reply queue and add MPI3MR_DEV_REMOVE_HS_COMPLETED flag.
mav added inline comments to D44423: mpi3mr: poll reply queue and add MPI3MR_DEV_REMOVE_HS_COMPLETED flag.
I am not a big fan of kernel printing something in response to arbitrary user requests, it makes logs messy. Is the error reporting to user is not enough here?
Mar 18 2024
Mar 18 2024
Why not backport 506fe78c48 instead?
Mar 15 2024
Mar 15 2024
My only complaint is that it puts the queue into the same cache line as the main queue, that may be modified by writers. But if you really need it for debugging, it could be understood.
Mar 6 2024
Mar 6 2024
Mar 5 2024
Mar 5 2024
On failure we've already notified consumers that controller has failed. What will report it is back? And is there even a device to sent request IOCTL?
If you say it helps I have no objections, but I see nvme_sim_controller_fail() destroying SIM, so I am not sure you actually get here.
I wonder if there are any namespace-specific events? I remember NVMe specs allow per-namespace SMART, but I don't remember much details now.
In D39620#1008905, @sean_rogue-research.com wrote:stable/13 has this patch
releng/13.2 doesn't have this patch (yet).I'm not very familiar with FreeBSD's branching system... I see FreeBSD 13.3-RELEASE was released today, is this bug fix included?
Feb 27 2024
Feb 27 2024
mav committed rG7c667affb7b0: CTL: Drop Format Device and Rigid Disk Geometry mode pages (authored by mav).
CTL: Drop Format Device and Rigid Disk Geometry mode pages
Feb 5 2024
Feb 5 2024
mav committed rG7393d37b1224: ntb_hw_plx: Workaround read-only scratchpad registers (authored by mav).
ntb_hw_plx: Workaround read-only scratchpad registers
mav committed rG825b7c222a6b: ntb_hw_plx: Workaround read-only scratchpad registers (authored by mav).
ntb_hw_plx: Workaround read-only scratchpad registers
Jan 27 2024
Jan 27 2024
mav committed rG3883c6fbf232: ntb_hw_plx: Workaround read-only scratchpad registers (authored by mav).
ntb_hw_plx: Workaround read-only scratchpad registers
Jan 19 2024
Jan 19 2024
mpi3mr: Minor tweak to task queue pausing
mpi3mr: Assume dma_hiaddr is BUS_SPACE_MAXADDR
mav committed rGac7d9eaf066b: mpi3mr: Replace can't happen DataLength == 0 with an assert (authored by imp).
mpi3mr: Replace can't happen DataLength == 0 with an assert
mpi3mr: Add firmware version
mpi3mr: Trivial trailing white space reduction
mpi3mr: Honor the dma mask from IOCFacts
mpi3mr: Fix EINPROGRESS errors hanging the card
mav committed rGac4f33d2cd37: mpi3mr: Cleaup setting of status in processing scsiio requests (authored by imp).
mpi3mr: Cleaup setting of status in processing scsiio requests
mpi3mr: Use template for main busdma tag.
mav committed rG2d84c6e89435: mpi3mr: Make these bus_dmamap_load calls synchronous (authored by mav).
mpi3mr: Make these bus_dmamap_load calls synchronous
mpi3mr: Fix MAXPHYS usage
mav committed rGc351a6ec918e: mpi3mr: Only set callout_owned when we create a timeout (authored by imp).
mpi3mr: Only set callout_owned when we create a timeout
mpi3mr: Minor style fix
mpi3mr: Reduce the scope of the reset_mutext
mpi3mr: Remove unused fields in struct mpi3mr_cmd
mav committed rG0d2cce768cbc: mpi3mr: Don't hold fwevt_lock over call to taskqueue_drain (authored by imp).
mpi3mr: Don't hold fwevt_lock over call to taskqueue_drain
iichid(4): Switch taskqueue to "fast"
iichid(4): Unify two taskqueue tasks
iichid(4): Restore/increase sampling rate
iicbb: Fix pause_sbt() arguments order
iichid(4): Improve idle sampling hysteresis
ig4: Actively use FIFO thresholds
ig4: Fix FIFO depths detection
mav committed rG44fac9c0be90: ispfw(4): Update and add firmware (authored by Joerg.Pulz_frm2.tum.de).
ispfw(4): Update and add firmware
mav committed rG4f30677080c3: ispfw(4): Update and add firmware (authored by Joerg.Pulz_frm2.tum.de).
ispfw(4): Update and add firmware
mav committed rGbdc2003fc517: isp: Fix endianness conversion in isp_read_flash_data() (authored by markj).
isp: Fix endianness conversion in isp_read_flash_data()
mav committed rG84f8cfcbe493: isp(4): Rework firmware handling/loading (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Rework firmware handling/loading
isp(4): Style changes
mav committed rG0a38059e24d4: isp(4): Remove redundant functions for reading data from FLT and flash (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Remove redundant functions for reading data from FLT and flash
mav committed rGde4c073977c9: isp(4): Use the FLT on all supported controllers (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Use the FLT on all supported controllers
mav committed rGa922b89834ef: isp(4): Add support to read contents of the FLT (flash layout table) (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Add support to read contents of the FLT (flash layout table)
mav committed rGf0275240dc3d: isp(4): Fix reading NVRAM contents for 28xx based devices (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Fix reading NVRAM contents for 28xx based devices
mav committed rG6fdabe9b8df4: isp(4): Add support for QLogic 28xx devices (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Add support for QLogic 28xx devices
isp: Remove unused variable.
mav committed rG16f4d8fc14b6: isp: Fix endianness conversion in isp_read_flash_data() (authored by markj).
isp: Fix endianness conversion in isp_read_flash_data()
mav committed rGd095e86f0517: isp(4): Rework firmware handling/loading (authored by Joerg.Pulz_frm2.tum.de).
isp(4): Rework firmware handling/loading
acpi_lid: Remove duplicate events
iichid(4): Switch taskqueue to "fast"
iichid(4): Unify two taskqueue tasks
iichid(4): Restore/increase sampling rate
iicbb: Fix pause_sbt() arguments order
iichid(4): Improve idle sampling hysteresis
acpi_cpu: Reduce BUS_MASTER_RLD manipulations
Schedule fast taskqueue callouts on right CPU.
ig4: Actively use FIFO thresholds
ig4: Fix FIFO depths detection
acpi_cpu: Reduce BUS_MASTER_RLD manipulations
Schedule fast taskqueue callouts on right CPU.
Jan 10 2024
Jan 10 2024
In D43385#989072, @gallatin wrote:Is it possible that the firmware could set ACPI_HEST_GEN_ERROR_FATAL in ged->ErrorSeverity but not ges->ErrorSeverity ?
There is already a panic in apei_ge_handler(), based on total status severity. Do you see it not enough?
Jan 3 2024
Jan 3 2024
nvme: Add some bits from NVMe 2.0c spec.
stand/zfs: Remove one more read-compatible feature
stand/zfs: Remove read-compatible features
Dec 30 2023
Dec 30 2023
Not very my area, but seems to have sense.
Dec 28 2023
Dec 28 2023
Dec 27 2023
Dec 27 2023
nvme: Add some bits from NVMe 2.0c spec.
Schedule fast taskqueue callouts on right CPU.
iichid(4): Switch taskqueue to "fast"
iichid(4): Unify two taskqueue tasks
Dec 26 2023
Dec 26 2023
This is already merged.
acpi_cpu: Reduce BUS_MASTER_RLD manipulations
Dec 24 2023
Dec 24 2023
ig4: Actively use FIFO thresholds
acpi_lid: Remove duplicate events
iichid(4): Restore/increase sampling rate
ig4: Fix FIFO depths detection