ZFS is logging "Large kmem_alloc(129024, 0x1000), please file an issue at: https://github.com/openzfs/zfs/issues/new"

[arieleizenberg]

System information

Ubuntu 22.04 running 6.2.0-1018-aws #18~22.04.1-Ubuntu.
zfs-2.1.5-1ubuntu6~22.04.2
zfs-kmod-2.1.9-2ubuntu1.1
on AWS u-12tb1.112xlarge x86_64 instance.

Describe the problem you're observing

Our dmesg log contains multiple instances of:

[  190.702131] Large kmem_alloc(129024, 0x1000), please file an issue at:
               https://github.com/openzfs/zfs/issues/new
[  190.702143] CPU: 135 PID: 4163 Comm: modprobe Tainted: P           O       6.2.0-1018-aws #18~22.04.1-Ubuntu
[  190.702147] Hardware name: Amazon EC2 u-12tb1.112xlarge/, BIOS 1.0 10/16/2017
[  190.702150] Call Trace:
[  190.702155]  <TASK>
[  190.702158]  dump_stack_lvl+0x48/0x70
[  190.702178]  dump_stack+0x10/0x20
[  190.702182]  spl_kmem_alloc_impl+0xce/0xf0 [spl]
[  190.702245]  ? __pfx_init_module+0x10/0x10 [zzstd]
[  190.702272]  spl_kmem_zalloc+0x19/0x30 [spl]
[  190.702290]  zstd_mempool_init+0x2e/0x120 [zzstd]
[  190.702311]  ? __pfx_init_module+0x10/0x10 [zzstd]
[  190.702331]  zstd_meminit+0xe/0x40 [zzstd]
[  190.702350]  init_module+0x1c/0xdf0 [zzstd]
[  190.702370]  do_one_initcall+0x46/0x210
[  190.702385]  ? kmalloc_trace+0x2a/0xb0
[  190.702399]  do_init_module+0x52/0x240
[  190.702409]  load_module+0xb96/0xd40
[  190.702413]  ? security_kernel_post_read_file+0x5c/0x80
[  190.702422]  __do_sys_finit_module+0xcc/0x150
[  190.702425]  ? __do_sys_finit_module+0xcc/0x150
[  190.702429]  __x64_sys_finit_module+0x18/0x30
[  190.702432]  do_syscall_64+0x59/0x90
[  190.702441]  ? ksys_mmap_pgoff+0x123/0x270
[  190.702446]  ? __secure_computing+0x9b/0x110
[  190.702457]  ? exit_to_user_mode_prepare+0x3b/0xd0
[  190.702472]  ? syscall_exit_to_user_mode+0x38/0x60
[  190.702484]  ? do_syscall_64+0x69/0x90
[  190.702487]  ? syscall_exit_to_user_mode+0x38/0x60
[  190.702490]  ? do_syscall_64+0x69/0x90
[  190.702492]  ? syscall_exit_to_user_mode+0x38/0x60
[  190.702495]  ? do_syscall_64+0x69/0x90
[  190.702498]  ? do_syscall_64+0x69/0x90
[  190.702501]  entry_SYSCALL_64_after_hwframe+0x73/0xdd
[  190.702518] RIP: 0033:0x7f464f91e88d
[  190.702522] Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 b5 0f 00 f7 d8 64 89 01 >
[  190.702525] RSP: 002b:00007ffec0ec50e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[  190.702530] RAX: ffffffffffffffda RBX: 000055be3628c2c0 RCX: 00007f464f91e88d
[  190.702532] RDX: 0000000000000000 RSI: 000055be358a8cd2 RDI: 0000000000000009
[  190.702534] RBP: 0000000000040000 R08: 0000000000000000 R09: 0000000000000002
[  190.702535] R10: 0000000000000009 R11: 0000000000000246 R12: 000055be358a8cd2
[  190.702537] R13: 000055be3628c280 R14: 000055be36293460 R15: 000055be362960e0
[  190.702541]  </TASK>
[  190.702583] Large kmem_alloc(129024, 0x1000), please file an issue at:
               https://github.com/openzfs/zfs/issues/new
...

[rincebrain]

#14975 #15548 #15691 #15866 and friends.

It's harmless, for your purposes, it's just a warning to tell us we need to adjust a memory allocation because we try to use different functions to allocate things that large or see if we should adjust how we do it. Thanks for reporting it.

[arieleizenberg]

thanks!