[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
** Changed in: linux-gke (Ubuntu) Status: Fix Committed => Fix Released -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1703742 Title: Transparent hugepages should default to enabled=madvise Status in linux package in Ubuntu: Fix Released Status in linux-gke package in Ubuntu: Fix Released Status in linux source package in Xenial: Fix Released Status in linux-gke source package in Xenial: Fix Released Status in linux source package in Yakkety: Won't Fix Status in linux source package in Zesty: Won't Fix Status in linux source package in Artful: Fix Released Bug description: SRU Justification, Zesty, Xenial [Impact] Ubuntu kernels should default transparent_hugepages to enabled=madvise, not enabled=always (this corresponds to TRANSPARENT_HUGEPAGE_MADVISE=y in .config). I've blogged about this at some length here: https://blog.nelhage.com/post/transparent-hugepages/ but here is a summary: Transparent Hugepages are a feature that allows the kernel to attempt to automatically back any anonymous maps with "huge" 2MiB page tables, instead of the normal 4k entries. It can produce small net performance gains in certain benchmarks, but also has numerous downsides, in the form of apparent memory leaks and 30% slowdowns or worse for some applications. Many popular pieces of software now refuse to run with hugepages enabled because of known performance issues. Examples of problem reports: MongoDB: https://docs.mongodb.com/manual/tutorial/transparent-huge-pages/ Oracle: https://blogs.oracle.com/linux/entry/performance_issues_with_transparent_huge Splunk: https://docs.splunk.com/Documentation/Splunk/6.5.2/ReleaseNotes/SplunkandTHP Go runtime: https://github.com/golang/go/issues/8832 jemalloc: https://blog.digitalocean.com/transparent-huge-pages-and-alternative-memory-allocators/ node.js: https://github.com/nodejs/node/issues/11077 Setting `enabled=madvise` enables applications that know they benefit from transparent huge pages to opt-in to this feature, while eliminating all the problematic behavior for other applications. Note also that transparent hugepage settings don't affect the use of explicit hugepages via hugetlbfs or mmap(…, MAP_HUGETLB, …) [Fix] Enable CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y [Regression Potential] May marginally impact performance, but the benefits of madvise'd huge transparent hugepage over-weigh this considerably. This has been enabled in Artful since July (and in Bionic) and we've not seen any regression reports, so we are confident this has minimal impact. [Testcase] Kernel ADT tests and stress-ng memory tests should not show any regressions. To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1703742/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
This bug was fixed in the package linux - 4.4.0-119.143 --- linux (4.4.0-119.143) xenial; urgency=medium * linux: 4.4.0-119.143 -proposed tracker (LP: #1760327) * Dell XPS 13 9360 bluetooth scan can not detect any device (LP: #1759821) - Revert "Bluetooth: btusb: fix QCA Rome suspend/resume" linux (4.4.0-118.142) xenial; urgency=medium * linux: 4.4.0-118.142 -proposed tracker (LP: #1759607) * Kernel panic with AWS 4.4.0-1053 / 4.4.0-1015 (Trusty) (LP: #1758869) - x86/microcode/AMD: Do not load when running on a hypervisor * CVE-2018-8043 - net: phy: mdio-bcm-unimac: fix potential NULL dereference in unimac_mdio_probe() linux (4.4.0-117.141) xenial; urgency=medium * linux: 4.4.0-117.141 -proposed tracker (LP: #1755208) * Xenial update to 4.4.114 stable release (LP: #1754592) - x86/asm/32: Make sync_core() handle missing CPUID on all 32-bit kernels - usbip: prevent vhci_hcd driver from leaking a socket pointer address - usbip: Fix implicit fallthrough warning - usbip: Fix potential format overflow in userspace tools - x86/microcode/intel: Fix BDW late-loading revision check - x86/retpoline: Fill RSB on context switch for affected CPUs - sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks - can: af_can: can_rcv(): replace WARN_ONCE by pr_warn_once - can: af_can: canfd_rcv(): replace WARN_ONCE by pr_warn_once - PM / sleep: declare __tracedata symbols as char[] rather than char - time: Avoid undefined behaviour in ktime_add_safe() - timers: Plug locking race vs. timer migration - Prevent timer value 0 for MWAITX - drivers: base: cacheinfo: fix x86 with CONFIG_OF enabled - drivers: base: cacheinfo: fix boot error message when acpi is enabled - PCI: layerscape: Add "fsl,ls2085a-pcie" compatible ID - PCI: layerscape: Fix MSG TLP drop setting - mmc: sdhci-of-esdhc: add/remove some quirks according to vendor version - fs/select: add vmalloc fallback for select(2) - hwpoison, memcg: forcibly uncharge LRU pages - cma: fix calculation of aligned offset - mm, page_alloc: fix potential false positive in __zone_watermark_ok - ipc: msg, make msgrcv work with LONG_MIN - x86/ioapic: Fix incorrect pointers in ioapic_setup_resources() - ACPI / processor: Avoid reserving IO regions too early - ACPI / scan: Prefer devices without _HID/_CID for _ADR matching - ACPICA: Namespace: fix operand cache leak - netfilter: x_tables: speed up jump target validation - netfilter: arp_tables: fix invoking 32bit "iptable -P INPUT ACCEPT" failed in 64bit kernel - netfilter: nf_dup_ipv6: set again FLOWI_FLAG_KNOWN_NH at flowi6_flags - netfilter: nf_ct_expect: remove the redundant slash when policy name is empty - netfilter: nfnetlink_queue: reject verdict request from different portid - netfilter: restart search if moved to other chain - netfilter: nf_conntrack_sip: extend request line validation - netfilter: use fwmark_reflect in nf_send_reset - ext2: Don't clear SGID when inheriting ACLs - reiserfs: fix race in prealloc discard - reiserfs: don't preallocate blocks for extended attributes - reiserfs: Don't clear SGID when inheriting ACLs - fs/fcntl: f_setown, avoid undefined behaviour - scsi: libiscsi: fix shifting of DID_REQUEUE host byte - Input: trackpoint - force 3 buttons if 0 button is reported - usb: usbip: Fix possible deadlocks reported by lockdep - usbip: fix stub_rx: get_pipe() to validate endpoint number - usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input - usbip: prevent leaking socket pointer address in messages - um: link vmlinux with -no-pie - vsyscall: Fix permissions for emulate mode with KAISER/PTI - eventpoll.h: add missing epoll event masks - x86/microcode/intel: Extend BDW late-loading further with LLC size check - hrtimer: Reset hrtimer cpu base proper on CPU hotplug - dccp: don't restart ccid2_hc_tx_rto_expire() if sk in closed state - ipv6: Fix getsockopt() for sockets with default IPV6_AUTOFLOWLABEL - ipv6: fix udpv6 sendmsg crash caused by too small MTU - ipv6: ip6_make_skb() needs to clear cork.base.dst - lan78xx: Fix failure in USB Full Speed - net: igmp: fix source address check for IGMPv3 reports - tcp: __tcp_hdrlen() helper - net: qdisc_pkt_len_init() should be more robust - pppoe: take ->needed_headroom of lower device into account on xmit - r8169: fix memory corruption on retrieval of hardware statistics. - sctp: do not allow the v4 socket to bind a v4mapped v6 address - sctp: return error if the asoc has been peeled off in sctp_wait_for_sndbuf - vmxnet3: repair memory leak - net: Allow neigh contructor functions ability to modify the primary_key - ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
** Changed in: linux (Ubuntu Zesty) Status: In Progress => Won't Fix -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1703742 Title: Transparent hugepages should default to enabled=madvise Status in linux package in Ubuntu: Fix Released Status in linux-gke package in Ubuntu: Fix Committed Status in linux source package in Xenial: In Progress Status in linux-gke source package in Xenial: Fix Released Status in linux source package in Yakkety: Won't Fix Status in linux source package in Zesty: Won't Fix Status in linux source package in Artful: Fix Released Bug description: SRU Justification, Zesty, Xenial [Impact] Ubuntu kernels should default transparent_hugepages to enabled=madvise, not enabled=always (this corresponds to TRANSPARENT_HUGEPAGE_MADVISE=y in .config). I've blogged about this at some length here: https://blog.nelhage.com/post/transparent-hugepages/ but here is a summary: Transparent Hugepages are a feature that allows the kernel to attempt to automatically back any anonymous maps with "huge" 2MiB page tables, instead of the normal 4k entries. It can produce small net performance gains in certain benchmarks, but also has numerous downsides, in the form of apparent memory leaks and 30% slowdowns or worse for some applications. Many popular pieces of software now refuse to run with hugepages enabled because of known performance issues. Examples of problem reports: MongoDB: https://docs.mongodb.com/manual/tutorial/transparent-huge-pages/ Oracle: https://blogs.oracle.com/linux/entry/performance_issues_with_transparent_huge Splunk: https://docs.splunk.com/Documentation/Splunk/6.5.2/ReleaseNotes/SplunkandTHP Go runtime: https://github.com/golang/go/issues/8832 jemalloc: https://blog.digitalocean.com/transparent-huge-pages-and-alternative-memory-allocators/ node.js: https://github.com/nodejs/node/issues/11077 Setting `enabled=madvise` enables applications that know they benefit from transparent huge pages to opt-in to this feature, while eliminating all the problematic behavior for other applications. Note also that transparent hugepage settings don't affect the use of explicit hugepages via hugetlbfs or mmap(…, MAP_HUGETLB, …) [Fix] Enable CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y [Regression Potential] May marginally impact performance, but the benefits of madvise'd huge transparent hugepage over-weigh this considerably. This has been enabled in Artful since July (and in Bionic) and we've not seen any regression reports, so we are confident this has minimal impact. [Testcase] Kernel ADT tests and stress-ng memory tests should not show any regressions. To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1703742/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
This bug was fixed in the package linux-gke - 4.4.0-1033.33 --- linux-gke (4.4.0-1033.33) xenial; urgency=low * linux-gke: 4.4.0-1033.33 -proposed tracker (LP: #1722308) * Transparent hugepages should default to enabled=madvise (LP: #1703742) - [gke] UBUNTU: SAUCE: use CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y as default [ Ubuntu: 4.4.0-98.121 ] * linux: 4.4.0-98.121 -proposed tracker (LP: #1722299) * Controller lockup detected on ProLiant DL380 Gen9 with P440 Controller (LP: #1720359) - scsi: hpsa: limit transfer length to 1MB * [Dell Docking IE][0bda:8153] Realtek USB Ethernet leads to system hang (LP: #1720977) - r8152: fix the list rx_done may be used without initialization * Add installer support for Broadcom BCM573xx network drivers. (LP: #1720466) - d-i: Add bnxt_en to nic-modules. * snapcraft.yaml: add dpkg-dev to the build deps (LP: #1718886) - snapcraft.yaml: add dpkg-dev to the build deps * Support setting I2C_TIMEOUT via ioctl for i2c-designware (LP: #1718578) - i2c: designware: Use transfer timeout from ioctl I2C_TIMEOUT * 5U84 - ses driver isn't binding right - cannot blink lights on 1 of the 2 5u84 (LP: #1693369) - scsi_transport_sas: add function to get SAS endpoint address - ses: fix discovery of SATA devices in SAS enclosures - scsi: sas: provide stub implementation for scsi_is_sas_rphy - scsi: ses: Fix SAS device detection in enclosure * multipath -ll is not showing the disks which are actually multipath (LP: #1718397) - fs: aio: fix the increment of aio-nr and counting against aio-max-nr * Support Dell Wireless DW5819/5818 WWAN devices (LP: #1721455) - SAUCE: USB: serial: qcserial: add Dell DW5818, DW5819 * CVE-2017-10911 - xen-blkback: don't leak stack data via response ring * implement 'complain mode' in seccomp for developer mode with snaps (LP: #1567597) - seccomp: Provide matching filter for introspection - seccomp: Sysctl to display available actions - seccomp: Operation for checking if an action is available - seccomp: Sysctl to configure actions that are allowed to be logged - seccomp: Selftest for detection of filter flag support - seccomp: Action to log before allowing * implement errno action logging in seccomp for strict mode with snaps (LP: #1721676) - seccomp: Provide matching filter for introspection - seccomp: Sysctl to display available actions - seccomp: Operation for checking if an action is available - seccomp: Sysctl to configure actions that are allowed to be logged - seccomp: Selftest for detection of filter flag support - seccomp: Filter flag to log all actions except SECCOMP_RET_ALLOW * [Xenial] update OpenNSL kernel modules to 6.5.10 (LP: #1721511) - SAUCE: update OpenNSL kernel modules to 6.5.10 * Xenial update to 4.4.90 stable release (LP: #1721550) - cifs: release auth_key.response for reconnect. - mac80211: flush hw_roc_start work before cancelling the ROC - KVM: PPC: Book3S: Fix race and leak in kvm_vm_ioctl_create_spapr_tce() - tracing: Fix trace_pipe behavior for instance traces - tracing: Erase irqsoff trace with empty write - md/raid5: fix a race condition in stripe batch - md/raid5: preserve STRIPE_ON_UNPLUG_LIST in break_stripe_batch_list - scsi: scsi_transport_iscsi: fix the issue that iscsi_if_rx doesn't parse nlmsg properly - crypto: talitos - Don't provide setkey for non hmac hashing algs. - crypto: talitos - fix sha224 - KEYS: fix writing past end of user-supplied buffer in keyring_read() - KEYS: prevent creating a different user's keyrings - KEYS: prevent KEYCTL_READ on negative key - powerpc/pseries: Fix parent_dn reference leak in add_dt_node() - Fix SMB3.1.1 guest authentication to Samba - SMB: Validate negotiate (to protect against downgrade) even if signing off - SMB3: Don't ignore O_SYNC/O_DSYNC and O_DIRECT flags - vfs: Return -ENXIO for negative SEEK_HOLE / SEEK_DATA offsets - nl80211: check for the required netlink attributes presence - bsg-lib: don't free job in bsg_prepare_job - seccomp: fix the usage of get/put_seccomp_filter() in seccomp_get_filter() - arm64: Make sure SPsel is always set - arm64: fault: Route pte translation faults via do_translation_fault - KVM: VMX: Do not BUG() on out-of-bounds guest IRQ - kvm: nVMX: Don't allow L2 to access the hardware CR8 - PCI: Fix race condition with driver_override - btrfs: fix NULL pointer dereference from free_reloc_roots() - btrfs: propagate error to btrfs_cmp_data_prepare caller - btrfs: prevent to set invalid default subvolid - x86/fpu: Don't let userspace set bogus xcomp_bv - gfs2: Fix debugfs glocks dump - timer/sysclt: Restrict timer migration sysctl values to 0 and 1 - KVM: VMX: do not change SN bit in vmx_update_pi_irte() - KVM: VMX: remove WARN_ON_ONCE in
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
** Also affects: linux-gke (Ubuntu) Importance: Undecided Status: New ** No longer affects: linux-gke (Ubuntu Yakkety) ** No longer affects: linux-gke (Ubuntu Zesty) ** No longer affects: linux-gke (Ubuntu Artful) ** Changed in: linux-gke (Ubuntu Xenial) Status: New => Fix Committed ** Changed in: linux-gke (Ubuntu Xenial) Assignee: (unassigned) => Kamal Mostafa (kamalmostafa) ** Changed in: linux-gke (Ubuntu) Status: New => Fix Committed ** Changed in: linux-gke (Ubuntu) Assignee: (unassigned) => Kamal Mostafa (kamalmostafa) -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1703742 Title: Transparent hugepages should default to enabled=madvise Status in linux package in Ubuntu: Fix Released Status in linux-gke package in Ubuntu: Fix Committed Status in linux source package in Xenial: In Progress Status in linux-gke source package in Xenial: Fix Committed Status in linux source package in Yakkety: Won't Fix Status in linux source package in Zesty: In Progress Status in linux source package in Artful: Fix Released Bug description: Ubuntu kernels should default transparent_hugepages to enabled=madvise, not enabled=always (this corresponds to TRANSPARENT_HUGEPAGE_MADVISE=y in .config). I've blogged about this at some length here: https://blog.nelhage.com/post/transparent-hugepages/ but here is a summary: Transparent Hugepages are a feature that allows the kernel to attempt to automatically back any anonymous maps with "huge" 2MiB page tables, instead of the normal 4k entries. It can produce small net performance gains in certain benchmarks, but also has numerous downsides, in the form of apparent memory leaks and 30% slowdowns or worse for some applications. Many popular pieces of software now refuse to run with hugepages enabled because of known performance issues. Examples of problem reports: MongoDB: https://docs.mongodb.com/manual/tutorial/transparent-huge-pages/ Oracle: https://blogs.oracle.com/linux/entry/performance_issues_with_transparent_huge Splunk: https://docs.splunk.com/Documentation/Splunk/6.5.2/ReleaseNotes/SplunkandTHP Go runtime: https://github.com/golang/go/issues/8832 jemalloc: https://blog.digitalocean.com/transparent-huge-pages-and-alternative-memory-allocators/ node.js: https://github.com/nodejs/node/issues/11077 Setting `enabled=madvise` enables applications that know they benefit from transparent huge pages to opt-in to this feature, while eliminating all the problematic behavior for other applications. Note also that transparent hugepage settings don't affect the use of explicit hugepages via hugetlbfs or mmap(…, MAP_HUGETLB, …) To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1703742/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
This bug was fixed in the package linux - 4.11.0-13.19 --- linux (4.11.0-13.19) artful; urgency=low * CVE-2017-7533 - dentry name snapshots linux (4.11.0-12.18) artful; urgency=low * linux: 4.11.0-12.18 -proposed tracker (LP: #1707635) - no change rebuild to pick up the new binutils. * Adt tests of src:linux time out often on armhf lxc containers (LP: #1705495) - [Packaging] tests -- reduce rebuild test to one flavour - [Packaging] tests -- reduce rebuild test to one flavour -- use filter * [ARM64] config EDAC_GHES=y depends on EDAC_MM_EDAC=y (LP: #1706141) - [Config] set EDAC_MM_EDAC=y for ARM64 * [Hyper-V] hv_netvsc: Exclude non-TCP port numbers from vRSS hashing (LP: #1690174) - hv_netvsc: Exclude non-TCP port numbers from vRSS hashing * ath10k doesn't report full RSSI information (LP: #1706531) - ath10k: add per chain RSSI reporting * ideapad_laptop don't support v310-14isk (LP: #1705378) - platform/x86: ideapad-laptop: Add several models to no_hw_rfkill * Ubuntu 16.04.3: Qemu fails on P9 (LP: #1686019) - KVM: PPC: Pass kvm* to kvmppc_find_table() - KVM: PPC: Use preregistered memory API to access TCE list - KVM: PPC: VFIO: Add in-kernel acceleration for VFIO - powerpc/powernv/iommu: Add real mode version of iommu_table_ops::exchange() - powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal - powerpc/vfio_spapr_tce: Add reference counting to iommu_table - powerpc/mmu: Add real mode support for IOMMU preregistered memory - KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number - KVM: PPC: Book3S HV: Add radix checks in real-mode hypercall handlers * hns: ethtool selftest crashes system (LP: #1705712) - net/hns:bugfix of ethtool -t phy self_test * ThunderX: soft lockup on 4.8+ kernels when running qemu-efi with vhost=on (LP: #1673564) - KVM: arm/arm64: vgic-v3: Use PREbits to infer the number of ICH_APxRn_EL2 registers - KVM: arm/arm64: vgic-v3: Fix nr_pre_bits bitfield extraction - arm64: Add a facility to turn an ESR syndrome into a sysreg encoding - KVM: arm/arm64: vgic-v3: Add accessors for the ICH_APxRn_EL2 registers - KVM: arm64: Make kvm_condition_valid32() accessible from EL2 - KVM: arm64: vgic-v3: Add hook to handle guest GICv3 sysreg accesses at EL2 - KVM: arm64: vgic-v3: Add ICV_BPR1_EL1 handler - KVM: arm64: vgic-v3: Add ICV_IGRPEN1_EL1 handler - KVM: arm64: vgic-v3: Add ICV_IAR1_EL1 handler - KVM: arm64: vgic-v3: Add ICV_EOIR1_EL1 handler - KVM: arm64: vgic-v3: Add ICV_AP1Rn_EL1 handler - KVM: arm64: vgic-v3: Add ICV_HPPIR1_EL1 handler - KVM: arm64: vgic-v3: Enable trapping of Group-1 system registers - KVM: arm64: Enable GICv3 Group-1 sysreg trapping via command-line - KVM: arm64: vgic-v3: Add ICV_BPR0_EL1 handler - KVM: arm64: vgic-v3: Add ICV_IGNREN0_EL1 handler - KVM: arm64: vgic-v3: Add misc Group-0 handlers - KVM: arm64: vgic-v3: Enable trapping of Group-0 system registers - KVM: arm64: Enable GICv3 Group-0 sysreg trapping via command-line - arm64: Add MIDR values for Cavium cn83XX SoCs - arm64: Add workaround for Cavium Thunder erratum 30115 - KVM: arm64: vgic-v3: Add ICV_DIR_EL1 handler - KVM: arm64: vgic-v3: Add ICV_RPR_EL1 handler - KVM: arm64: vgic-v3: Add ICV_CTLR_EL1 handler - KVM: arm64: vgic-v3: Add ICV_PMR_EL1 handler - KVM: arm64: Enable GICv3 common sysreg trapping via command-line - KVM: arm64: vgic-v3: Log which GICv3 system registers are trapped - arm64: KVM: Make unexpected reads from WO registers inject an undef - KVM: arm64: Log an error if trapping a read-from-write-only GICv3 access - KVM: arm64: Log an error if trapping a write-to-read-only GICv3 access * ath9k freezes suspend resume Ubuntu 17.04 (LP: #1697027) - ath9k: fix an invalid pointer dereference in ath9k_rng_stop() * xhci_hcd: ERROR Transfer event TRB DMA ptr not part of current TD ep_index 2 comp_code 13 (LP: #1667750) - xhci: Bad Ethernet performance plugged in ASM1042A host * Migrating KSM page causes the VM lock up as the KSM page merging list is too large (LP: #1680513) - ksm: introduce ksm_max_page_sharing per page deduplication limit - ksm: fix use after free with merge_across_nodes = 0 - ksm: cleanup stable_node chain collapse case - ksm: swap the two output parameters of chain/chain_prune - ksm: optimize refile of stable_node_dup at the head of the chain * Artful update to v4.11.12 stable release (LP: #1706067) - net/phy: micrel: configure intterupts after autoneg workaround - ipv6: avoid unregistering inet6_dev for loopback - netvsc: don't access netdev->num_rx_queues directly - sfc: Fix MCDI command size for filter operations - net: account for current skb length when deciding about UFO - net: dp83640: Avoid NULL pointer dereference. - tcp: reset sk_rx_dst in
[Group.of.nepali.translators] [Bug 1703742] Re: Transparent hugepages should default to enabled=madvise
** Also affects: linux (Ubuntu Artful) Importance: High Assignee: Colin Ian King (colin-king) Status: In Progress ** Also affects: linux (Ubuntu Xenial) Importance: Undecided Status: New ** Also affects: linux (Ubuntu Yakkety) Importance: Undecided Status: New ** Also affects: linux (Ubuntu Zesty) Importance: Undecided Status: New ** Changed in: linux (Ubuntu Artful) Status: In Progress => Fix Committed -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1703742 Title: Transparent hugepages should default to enabled=madvise Status in linux package in Ubuntu: Fix Committed Status in linux source package in Xenial: New Status in linux source package in Yakkety: New Status in linux source package in Zesty: New Status in linux source package in Artful: Fix Committed Bug description: Ubuntu kernels should default transparent_hugepages to enabled=madvise, not enabled=always (this corresponds to TRANSPARENT_HUGEPAGE_MADVISE=y in .config). I've blogged about this at some length here: https://blog.nelhage.com/post/transparent-hugepages/ but here is a summary: Transparent Hugepages are a feature that allows the kernel to attempt to automatically back any anonymous maps with "huge" 2MiB page tables, instead of the normal 4k entries. It can produce small net performance gains in certain benchmarks, but also has numerous downsides, in the form of apparent memory leaks and 30% slowdowns or worse for some applications. Many popular pieces of software now refuse to run with hugepages enabled because of known performance issues. Examples of problem reports: MongoDB: https://docs.mongodb.com/manual/tutorial/transparent-huge-pages/ Oracle: https://blogs.oracle.com/linux/entry/performance_issues_with_transparent_huge Splunk: https://docs.splunk.com/Documentation/Splunk/6.5.2/ReleaseNotes/SplunkandTHP Go runtime: https://github.com/golang/go/issues/8832 jemalloc: https://blog.digitalocean.com/transparent-huge-pages-and-alternative-memory-allocators/ node.js: https://github.com/nodejs/node/issues/11077 Setting `enabled=madvise` enables applications that know they benefit from transparent huge pages to opt-in to this feature, while eliminating all the problematic behavior for other applications. Note also that transparent hugepage settings don't affect the use of explicit hugepages via hugetlbfs or mmap(…, MAP_HUGETLB, …) To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1703742/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
