← Back to team overview

kernel-packages team mailing list archive

[Bug 1469829] Re: ppc64el should use 'deadline' as default io scheduler

 

This bug was fixed in the package linux - 3.19.0-30.33

---------------
linux (3.19.0-30.33) vivid; urgency=low

  [ Brad Figg ]

  * Release Tracking Bug
    - LP: #1498065
  * Revert "[Config]
    MFD_INTEL_LPSS/MFD_INTEL_LPSS_ACPI/MFD_INTEL_LPSS_PCI=m"
    - LP: #1498137
  * [Config] Disable the MFD_INTEL_LPSS* driver

linux (3.19.0-30.32) vivid; urgency=low

  [ Brad Figg ]

  * Release Tracking Bug
    - LP: #1498065

  [ Upstream Kernel Changes ]

  * net: Fix skb_set_peeked use-after-free bug
    - LP: #1497184

linux (3.19.0-29.31) vivid; urgency=low

  [ Luis Henriques ]

  * Release Tracking Bug
    - LP: #1493902

  [ Ander Conselvan de Oliveira ]

  * SAUCE: i915_bpo: Set ddi_pll_sel in DP MST path
    - LP: #1483320

  [ Chris J Arges ]

  * [Config] DEFAULT_IOSCHED="deadline" for ppc64el
    - LP: #1469829

  [ Chris Wilson ]

  * SAUCE: i915_bpo: drm/i915: Flag the execlists context object as dirty
    after every use
    - LP: #1489501

  [ Daniel Vetter ]

  * SAUCE: i915_bpo: drm/i915: Only dither on 6bpc panels
    - LP: #1489501

  [ David Henningsson ]

  * SAUCE: drm/i915: Add audio pin sense / ELD callback
    - LP: #1490895
  * SAUCE: drm/i915: Call audio pin/ELD notify function
    - LP: #1490895
  * SAUCE: ubuntu/i915: Call audio pin/ELD notify function
    - LP: #1490895
  * SAUCE: ALSA: hda - Add "hdac_acomp" global variable
    - LP: #1490895
  * SAUCE: ALSA: hda - allow codecs to access the i915 pin/ELD callback
    - LP: #1490895
  * SAUCE: ALSA: hda - Wake the codec up on pin/ELD notify events
    - LP: #1490895

  [ Jani Nikula ]

  * SAUCE: i915_bpo: Revert "drm/i915: Allow parsing of variable size child
    device entries from VBT"
    - LP: #1489501

  [ Maarten Lankhorst ]

  * SAUCE: i915_bpo: drm/i915: calculate primary visibility changes instead
    of calling from set_config
    - LP: #1489501
  * SAUCE: i915_bpo: drm/i915: Commit planes on each crtc separately.
    - LP: #1489501

  [ Thulasimani,Sivakumar ]

  * SAUCE: i915_bpo: Revert "drm/i915: Add eDP intermediate frequencies for
    CHV"
    - LP: #1489501
  * SAUCE: i915_bpo: drm/i915: remove HBR2 from chv supported list
    - LP: #1489501
  * SAUCE: i915_bpo: drm/i915: Avoid TP3 on CHV
    - LP: #1489501

  [ Timo Aaltonen ]

  * Revert "SAUCE: i915_bpo: drm/i915: Allow parsing of variable size child
    device entries from VBT, addendum v2"
    - LP: #1489501
  * SAUCE: Migrate Broadwell to i915_bpo.
    - LP: #1483320

  [ Upstream Kernel Changes ]

  * tcp: fix recv with flags MSG_WAITALL | MSG_PEEK
    - LP: #1486146
  * powerpc/powernv: Fix the overflow of OPAL message notifiers head array
    - LP: #1487085
  * xhci: call BIOS workaround to enable runtime suspend on Intel Braswell
    - LP: #1489292
  * PM / QoS: Make it possible to expose device latency tolerance to
    userspace
    - LP: #1488395
  * ACPI / PM: Attach ACPI power domain only once
    - LP: #1488395
  * Driver core: wakeup the parent device before trying probe
    - LP: #1488395
  * klist: implement klist_prev()
    - LP: #1488395
  * driver core: implement device_for_each_child_reverse()
    - LP: #1488395
  * mfd: make mfd_remove_devices() iterate in reverse order
    - LP: #1488395
  * mfd: Add support for Intel Sunrisepoint LPSS devices
    - LP: #1488395
  * md: use kzalloc() when bitmap is disabled
    - LP: #1493319
  * regulator: s2mps11: Fix GPIO suspend enable shift wrapping bug
    - LP: #1493319
  * iwlwifi: mvm: fix antenna selection when BT is active
    - LP: #1493319
  * HID: cp2112: fix to force single data-report reply
    - LP: #1493319
  * ata: pmp: add quirk for Marvell 4140 SATA PMP
    - LP: #1493319
  * libata: add ATA_HORKAGE_BROKEN_FPDMA_AA quirk for HP 250GB SATA disk
    VB0250EAVER
    - LP: #1493319
  * efi: Handle memory error structures produced based on old versions of
    standard
    - LP: #1493319
  * phy: berlin-usb: fix divider for BG2CD
    - LP: #1493319
  * libata: add ATA_HORKAGE_NOTRIM
    - LP: #1493319
  * libata: force disable trim for SuperSSpeed S238
    - LP: #1493319
  * libata: add ATA_HORKAGE_MAX_SEC_1024 to revert back to previous
    max_sectors limit
    - LP: #1493319
  * libata: increase the timeout when setting transfer mode
    - LP: #1493319
  * can: mcp251x: fix resume when device is down
    - LP: #1493319
  * libata: Do not blacklist M510DC
    - LP: #1493319
  * mac80211: clear subdir_stations when removing debugfs
    - LP: #1493319
  * ALSA: pcm: Fix lockdep warning with nonatomic PCM ops
    - LP: #1493319
  * iio: adc: vf610: fix the adc register read fail issue
    - LP: #1493319
  * ALSA: hda - Add headset mic support for Acer Aspire V5-573G
    - LP: #1493319
  * Subject: pinctrl: imx1-core: Fix debug output in .pin_config_set
    callback
    - LP: #1493319
  * ALSA: hda: add new AMD PCI IDs with proper driver caps
    - LP: #1493319
  * x86/mm: Add parenthesis for TLB tracepoint size calculation
    - LP: #1493319
  * x86/mpx: Do not set ->vm_ops on MPX VMAs
    - LP: #1493319
  * net: mvneta: fix refilling for Rx DMA buffers
    - LP: #1493319
  * ALSA: hda - Add new GPU codec ID 0x10de007d to snd-hda
    - LP: #1493319
  * drm/i915: Use two 32bit reads for select 64bit REG_READ ioctls
    - LP: #1493319
  * md/raid10: always set reshape_safe when initializing reshape_position.
    - LP: #1493319
  * ALSA: hda - Add headset mic pin quirk for a Dell device
    - LP: #1476987, #1493319
  * drm: Stop resetting connector state to unknown
    - LP: #1493319
  * usb: dwc3: Reset the transfer resource index on SET_INTERFACE
    - LP: #1493319
  * usb: xhci: Bugfix for NULL pointer deference in xhci_endpoint_init()
    function
    - LP: #1493319
  * xhci: Calculate old endpoints correctly on device reset
    - LP: #1493319
  * xhci: report U3 when link is in resume state
    - LP: #1493319
  * xhci: prevent bus_suspend if SS port resuming in phase 1
    - LP: #1493319
  * xhci: do not report PLC when link is in internal resume state
    - LP: #1493319
  * usb: core: lpm: set lpm_capable for root hub device
    - LP: #1493319
  * USB: OHCI: Fix race between ED unlink and URB submission
    - LP: #1493319
  * usb-storage: ignore ZTE MF 823 card reader in mode 0x1225
    - LP: #1493319
  * blkcg: fix gendisk reference leak in blkg_conf_prep()
    - LP: #1493319
  * mei: prevent unloading mei hw modules while the device is opened.
    - LP: #1493319
  * iommu/vt-d: Fix VM domain ID leak
    - LP: #1493319
  * tile: use free_bootmem_late() for initrd
    - LP: #1493319
  * Input: usbtouchscreen - avoid unresponsive TSC-30 touch screen
    - LP: #1493319
  * block: Do a full clone when splitting discard bios
    - LP: #1493319
  * md/raid1: fix test for 'was read error from last working device'.
    - LP: #1493319
  * mmc: omap_hsmmc: Fix DTO and DCRC handling
    - LP: #1493319
  * spi: imx: Fix small DMA transfers
    - LP: #1493319
  * ftrace: Fix breakage of set_ftrace_pid
    - LP: #1493319
  * isdn/gigaset: reset tty->receive_room when attaching ser_gigaset
    - LP: #1493319
  * sched: cls_bpf: fix panic on filter replace
    - LP: #1493319
  * net_sched: fix a use-after-free in sfq
    - LP: #1493319
  * serial: core: Fix crashes while echoing when closing
    - LP: #1493319
  * mmc: sdhci-pxav3: fix platform_data is not initialized
    - LP: #1493319
  * mmc: block: Add missing mmc_blk_put() in power_ro_lock_show()
    - LP: #1493319
  * mmc: sdhci-esdhc: Make 8BIT bus work
    - LP: #1493319
  * bonding: correctly handle bonding type change on enslave failure
    - LP: #1493319
  * mmc: sdhci check parameters before call dma_free_coherent
    - LP: #1493319
  * net: Clone skb before setting peeked flag
    - LP: #1493319
  * mtd: nand: Fix NAND_USE_BOUNCE_BUFFER flag conflict
    - LP: #1493319
  * bridge: mdb: fix double add notification
    - LP: #1493319
  * usb: gadget: mv_udc_core: fix phy_regs I/O memory leak
    - LP: #1493319
  * net/xen-netback: off by one in BUG_ON() condition
    - LP: #1493319
  * sched: cls_flow: fix panic on filter replace
    - LP: #1493319
  * ipvlan: use rcu_deference_bh() in ipvlan_queue_xmit()
    - LP: #1493319
  * inet: frags: fix defragmented packet's IP header for af_packet
    - LP: #1493319
  * bonding: fix destruction of bond with devices different from
    arphrd_ether
    - LP: #1493319
  * fq_codel: fix a use-after-free
    - LP: #1493319
  * ASoC: dapm: Lock during userspace access
    - LP: #1493319
  * ASoC: dapm: Don't add prefix to widget stream name
    - LP: #1493319
  * ASoC: ssm4567: Keep TDM_BCLKS in ssm4567_set_dai_fmt
    - LP: #1493319
  * ARM: OMAP2+: hwmod: Fix _wait_target_ready() for hwmods without sysc
    - LP: #1493319
  * ASoC: pcm1681: Fix setting de-emphasis sampling rate selection
    - LP: #1493319
  * qla2xxx: Fix hardware lock/unlock issue causing kernel panic.
    - LP: #1493319
  * qla2xxx: release request queue reservation.
    - LP: #1493319
  * qla2xxx: Remove msleep in qlt_send_term_exchange
    - LP: #1493319
  * qla2xxx: fix command initialization in target mode.
    - LP: #1493319
  * qla2xxx: kill sessions/log out initiator on RSCN and port down events
    - LP: #1493319
  * qla2xxx: cleanup cmd in qla workqueue before processing TMR
    - LP: #1493319
  * qla2xxx: delay plogi/prli ack until existing sessions are deleted
    - LP: #1493319
  * qla2xxx: Abort stale cmds on qla_tgt_wq when plogi arrives
    - LP: #1493319
  * qla2xxx: added sess generations to detect RSCN update races
    - LP: #1493319
  * qla2xxx: disable scsi_transport_fc registration in target mode
    - LP: #1493319
  * qla2xxx: drop cmds/tmrs arrived while session is being deleted
    - LP: #1493319
  * qla2xxx: terminate exchange when command is aborted by LIO
    - LP: #1493319
  * iscsi-target: Fix use-after-free during TPG session shutdown
    - LP: #1493319
  * iscsi-target: Convert iscsi_thread_set usage to kthread.h
    - LP: #1493319
  * iscsi-target: Fix iscsit_start_kthreads failure OOPs
    - LP: #1493319
  * iscsi-target: Fix iser explicit logout TX kthread leak
    - LP: #1493319
  * ARM: dts: i.MX35: Fix can support.
    - LP: #1493319
  * ALSA: hda - Apply fixup for another Toshiba Satellite S50D
    - LP: #1493319
  * drm/nouveau/fbcon/nv11-: correctly account for ring space usage
    - LP: #1493319
  * vhost: actually track log eventfd file
    - LP: #1493319
  * arm64/efi: map the entire UEFI vendor string before reading it
    - LP: #1493319
  * xfs: remote attribute headers contain an invalid LSN
    - LP: #1493319
  * xfs: remote attributes need to be considered data
    - LP: #1493319
  * ALSA: hda - Apply a fixup to Dell Vostro 5480
    - LP: #1493319
  * ALSA: usb-audio: add dB range mapping for some devices
    - LP: #1493319
  * drm/i915: Replace WARN inside I915_READ64_2x32 with retry loop
    - LP: #1493319
  * drm/radeon/combios: add some validation of lvds values
    - LP: #1493319
  * drm/i915: Declare the swizzling unknown for L-shaped configurations
    - LP: #1493319
  * x86/efi: Use all 64 bit of efi_memmap in setup_e820()
    - LP: #1493319
  * efi: Check for NULL efi kernel parameters
    - LP: #1493319
  * ipr: Fix locking for unit attention handling
    - LP: #1493319
  * ipr: Fix incorrect trace indexing
    - LP: #1493319
  * ipr: Fix invalid array indexing for HRRQ
    - LP: #1493319
  * scsi: fix memory leak with scsi-mq
    - LP: #1493319
  * ALSA: hda - Fix MacBook Pro 5,2 quirk
    - LP: #1493319
  * x86/xen: Probe target addresses in set_aliased_prot() before the
    hypercall
    - LP: #1493319
  * packet: tpacket_snd(): fix signed/unsigned comparison
    - LP: #1493319
  * inet: frag: don't re-use chainlist for evictor
    - LP: #1493319
  * bridge: netlink: fix slave_changelink/br_setport race conditions
    - LP: #1493319
  * netfilter: ctnetlink: put back references to master ct and expect
    objects
    - LP: #1493319
  * NFS: Don't revalidate the mapping if both size and change attr are up
    to date
    - LP: #1493319
  * bridge: mdb: fix delmdb state in the notification
    - LP: #1493319
  * ipvs: skb_orphan in case of forwarding
    - LP: #1493319
  * avr32: handle NULL as a valid clock object
    - LP: #1493319
  * ipvs: fix crash with sync protocol v0 and FTP
    - LP: #1493319
  * act_pedit: check binding before calling tcf_hash_release()
    - LP: #1493319
  * netfilter: nf_conntrack: Support expectations in different zones
    - LP: #1493319
  * ipvs: do not use random local source address for tunnels
    - LP: #1493319
  * ALSA: hda - fix cs4210_spdif_automute()
    - LP: #1493319
  * niu: don't count tx error twice in case of headroom realloc fails
    - LP: #1493319
  * net: sched: fix refcount imbalance in actions
    - LP: #1493319
  * net/mlx4_core: Fix wrong index in propagating port change event to VFs
    - LP: #1493319
  * packet: missing dev_put() in packet_do_bind()
    - LP: #1493319
  * ipvs: fix crash if scheduler is changed
    - LP: #1493319
  * Linux 3.19.8-ckt6
    - LP: #1493319

  [ Ville Syrjälä ]

  * SAUCE: i915_bpo: drm/i915: Don't use link_bw for PLL setup
    - LP: #1483320
  * SAUCE: i915_bpo: drm/i915: Split atomic wm update to pre and post
    variants
    - LP: #1493746

  [ Wen Xiong ]

  * SAUCE: ipr: Byte swapping for device_id attribute in sysfs
    - LP: #1453892

  [ Wen-chien Jesse Sung ]

  * [Config] MFD_INTEL_LPSS/MFD_INTEL_LPSS_ACPI/MFD_INTEL_LPSS_PCI=m
    - LP: #1488395

 -- Brad Figg <brad.figg@xxxxxxxxxxxxx>  Mon, 21 Sep 2015 11:57:20 -0700

-- 
You received this bug notification because you are a member of Kernel
Packages, which is subscribed to linux in Ubuntu.
https://bugs.launchpad.net/bugs/1469829

Title:
  ppc64el should use 'deadline' as default io scheduler

Status in linux package in Ubuntu:
  Fix Released
Status in linux source package in Trusty:
  Fix Released
Status in linux-lts-utopic source package in Trusty:
  Fix Released
Status in linux source package in Utopic:
  Won't Fix
Status in linux source package in Vivid:
  Fix Released

Bug description:
  [Impact]
  Using cfq instead of deadline as the default io scheduler starves certain workloads and causes performance issues. In addition every other arch we build uses deadline as the default scheduler.

  [Fix]
  Change the configuration to the following for ppc64el:
  CONFIG_DEFAULT_DEADLINE=y
  CONFIG_DEFAULT_IOSCHED="deadline"

  [Test Case]
  Boot and cat /sys/block/*/queue/scheduler to see if deadline is being used.

  --

  -- Problem Description --

  Firestone system given to DASD group failed HTX overnight test with miscompare error.
  HTX mdt.hdbuster was running on secondary drive and failed about 12 hours into test

  HTX miscompare analysis:
  ====================-==

  Device under test: /dev/sdb
  Stanza running: rule_3
  miscompare offset: 0x40
  Transfer size: Random Size
  LBA number: 0x70fc
  miscompare length: all the blocks in the transfer size

  *- STANZA 3: Creates number of threads twice the queue depth. Each thread  -*
  *- doing 20000 num_oper with RC operation with xfer size between 1 block   -*
  *- to 256K.                                                                -*

  This miscompare shows read operation is unable to get the expected
  data from the disk. The re-read buffer also shows the same data as the
  first read operation. Since the first read and next re-read shows same
  data, there could be a write operation (of previous rule stanza to
  initialize disk with pattern 007 ) failure on the disk. The same
  miscompare behavior shows for all the blocks in the transfer size.

  /dev/sdb          Jun  2 02:29:43 2015 err=000003b6 sev=2 hxestorage      <<===  device name (/dev/sdb)
  rule_3_13  numopers=     20000  loop=       767  blk=0x70fc len=89088
   min_blkno=0 max_blkno=0x74706daf, RANDOM access
  Seed Values= 37303, 290, 23235
  Data Pattern Seed Values = 37303, 291, 23235
  BWRC LBA fencepost Detail:
  th_num                min_lba                  max_lba      status
       0                 0            1c9be3ff    R
       1          1d1c1b6c            3a3836d7    F
       2          3a3836d8            57545243    F
       3          57545244            74706daf    F
  Miscompare at buffer offset 64 (0x40)                             <<===   miscompare offset (0x40)
  (Flags: badsig=0; cksum=0x60000)  Maximum LBA = 0x74706daf
  wbuf (baseaddr 0x3ffe1c0e6600) b0ffffffffffffffffffffffffffffffffffffff
  rbuf (baseaddr 0x3ffe1c0fc400) 850100fc700200fd700300fe700400ff70050000
  Write buffer saved in /tmp/htxsdb.wbuf1
  Read buffer saved in /tmp/htxsdb.rbuf1
  Re-read fails compare at offset64; buffer saved in /tmp/htxsdb.rerd1
  errno: 950(Unknown error 950)

  Asghar reproduced that HTX hang he is seeing. Looking in the kernel
  logs I see some messages from the kernel that there are user threads
  blocked on getting reads serviced. So likely HTX is seeing the same
  thing. I've asked Asghar to try using the deadline I/O scheduler
  rather than CFQ to see if that makes any difference. If that does not
  make any difference, the next thing to try is reducing the queue depth
  of the device. Right now its 31, which I think is pretty high.

  Step 1:

  echo deadline > /sys/block/sda/queue/scheduler
  echo deadline > /sys/block/sdb/queue/scheduler

  If that reproduces the issue, go to step 2:

  echo cfq > /sys/block/sda/queue/scheduler
  echo cfq > /sys/block/sdb/queue/scheduler
  echo 8 > /sys/block/sda/device/queue_depth
  echo 8 > /sys/block/sdb/device/queue_depth

  Breno - it looks like the default I/O scheduler + default queue depth
  for the SATA disks in Firestone is not optimal, in that when running a
  heavy I/O workload, we see read starvation occurring, which is making
  the system nearly unusable.

  Once we changed the I/O scheduler from cfq to deadline, all the issues
  went away and the system is able to run the same workload yet still be
  responsive. Suggest we either encourage Canonical to change the
  default I/O scheduler to deadline or at the very least provide
  documentation to encourage our customers to make this change
  themselves.

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1469829/+subscriptions