Guest

Preview Tool

Cisco Bug: CSCvs50962 - RHEL Kernel Crash: "Budget exhausted after napi rescheduled"

Last Modified

Jan 17, 2020

Products (1)

  • Cisco UCS Virtual Interface Card

Known Affected Releases

4.0(4g)C

Description (partial)

Symptom:
Kernel crash with the message:

[  188.038627] bm0: Budget exhausted after napi rescheduled
[  188.158011] ------------[ cut here ]------------
[  188.159667] WARNING: CPU: 48 PID: 20992 at lib/list_debug.c:36 __list_add+0x8a/0xc0
[  188.160765] list_add double add: new=ffff9ff220eb2278, prev=ffff9ff220eb2278, next=ffff9ff22fc1b850.
[  188.162044] Modules linked in: enic(OE) joydev uinput xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter devlink rpcrdma sunrpc ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_core nfit libnvdimm snd_hda_codec_generic iosf_mbi snd_hda_intel crc32_pclmul ghash_clmulni_intel snd_hda_codec aesni_intel lrw snd_hda_core gf128mul glue_helper snd_hwdep ablk_helper snd_seq cryptd snd_seq_device snd_pcm snd_timer snd ppdev soundcore sg virtio_balloon i2c_piix4 parport_pc pcspkr parport ip_tables xfs libcrc32c sd_mod sr_mod crc_t10dif cdrom crct10dif_generic ata_generic pata_acpi virtio_console qxl 8139too drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops floppy crct10dif_pclmul ttm crct10dif_common crc32c_intel ata_piix drm virtio_pci libata virtio_ring 8139cp serio_raw virtio mii drm_panel_orientation_quirks dm_mirror dm_region_hash dm_log dm_mod [last unloaded: enic]
[  188.179036] CPU: 48 PID: 20992 Comm: iperf3 Kdump: loaded Tainted: G           OE  ------------   3.10.0-957.12.1.el7.x86_64 #1
[  188.180617] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20191223_100556-anatol 04/01/2014
[  188.181972] Call Trace:
[  188.182333]  [<ffffffff98163021>] dump_stack+0x19/0x1b
[  188.183047]  [<ffffffff97a97688>] __warn+0xd8/0x100
[  188.183724]  [<ffffffff97a9770f>] warn_slowpath_fmt+0x5f/0x80
[  188.184517]  [<ffffffff97d9502a>] __list_add+0x8a/0xc0
[  188.185234]  [<ffffffff980385b7>] __napi_schedule+0x37/0x50
[  188.186002]  [<ffffffff98038628>] busy_poll_stop+0x58/0x70
[  188.186761]  [<ffffffff980387d3>] sk_busy_loop+0x193/0x2e0
[  188.187522]  [<ffffffffc0876030>] ? enic_adaptive_coal+0xf0/0xf0 [enic]
[  188.188435]  [<ffffffff98092cc4>] tcp_recvmsg+0x7c4/0xb30
[  188.189182]  [<ffffffff97cfca25>] ? sock_has_perm+0x75/0x90
[  188.189955]  [<ffffffff980c1220>] inet_recvmsg+0x80/0xb0
[  188.190698]  [<ffffffff980196ec>] sock_aio_read.part.9+0x14c/0x170
[  188.191548]  [<ffffffff98019731>] sock_aio_read+0x21/0x30
[  188.192308]  [<ffffffff97c40b03>] do_sync_read+0x93/0xe0
[  188.193036]  [<ffffffff97c415e5>] vfs_read+0x145/0x170
[  188.193743]  [<ffffffff97c423ff>] SyS_read+0x7f/0xf0
[  188.194428]  [<ffffffff98175d9b>] system_call_fastpath+0x22/0x27
[  188.195252] ---[ end trace 795ca677b968052a ]---
[  188.195907] ------------[ cut here ]------------

Conditions:
Happens when busy poll is enabled:

# cat /proc/sys/net/core/busy_poll
50
# cat /proc/sys/net/core/busy_read
50

Value 0 means it is disabled.

Enabling tuned profile "network latency" also enables busy poll.
Bug details contain sensitive information and therefore require a Cisco.com account to be viewed.

Bug Details Include

  • Full Description (including symptoms, conditions and workarounds)
  • Status
  • Severity
  • Known Fixed Releases
  • Related Community Discussions
  • Number of Related Support Cases
Bug information is viewable for customers and partners who have a service contract. Registered users can view up to 200 bugs per month without a service contract.