Re: [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Subject: Re: [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression
From: Christoph Hellwig <hch@xxxxxx>
Date: Wed, 1 Jul 2020 14:13:44 +0200
Cc: Christoph Hellwig <hch@xxxxxx>, Al Viro <viro@xxxxxxxxxxxxxxxxxx>, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, Ian Kent <raven@xxxxxxxxxx>, David Howells <dhowells@xxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, linux-fsdevel@xxxxxxxxxxxxxxx, linux-security-module@xxxxxxxxxxxxxxx, netfilter-devel@xxxxxxxxxxxxxxx, lkp@xxxxxxxxxxxx
In-reply-to: <20200701091943.GC3874@shao2-debian>
User-agent: Mutt/1.5.17 (2007-11-01)

FYI, this is because stress-nh tests splice using /dev/null.  Which
happens to actually have the iter ops, but doesn't have explicit
splice_read operation.

Follow-Ups:
- Re: [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression
  - From: Linus Torvalds

References:
- [PATCH 13/14] fs: implement default_file_splice_read using __kernel_read
  - From: Christoph Hellwig
- [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression
  - From: kernel test robot

Prev by Date: Re: [libnf_ct PATCH v2 1/9] Handle negative snprintf return values properly
Next by Date: [PATCH nf] netfilter: nf_conntrack: refetch conntrack after nf_conntrack_update()
Previous by thread: [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression
Next by thread: Re: [fs] 140402bab8: stress-ng.splice.ops_per_sec -100.0% regression
Index(es):
- Date
- Thread

[Index of Archives] [Netfitler Users] [Berkeley Packet Filter] [LARTC] [Bugtraq] [Yosemite Forum]

Powered by Linux