Re: Performance regression introduced by commit b667b8673443 ("pipe: Advance tail pointer inside of wait spinlock in pipe_read()")

[Akemi Yagi]

On Fri, Jan 17, 2020 at 10:11 AM Waiman Long <longman@xxxxxxxxxx> wrote:
>
> On 1/17/20 12:29 PM, Waiman Long wrote:
> > On 1/17/20 12:05 PM, Linus Torvalds wrote:

> >> GNU make v4.2.1 is buggy. The fix was done over two years ago, but
> >> there hasn't been a new release since then, so a lot of distributions
> >> have the buggy version..
> >>
> >> The fix is commit b552b05 ("[SV 51159] Use a non-blocking read with
> >> pselect to avoid hangs.") In the make the git tree.
> >>      Linus
> >
> > Yes, I did use make v4.2.1 which is the version that is shipped in
> > RHEL8. I will build new make and try it.

> > Longman
> >
> I built a make with the lastest make git tree and the problem was gone
> with the new make. So it was a bug in make not the kernel. Sorry for the
> noise.
>
> Longman

If you are using RHEL8, building your own make is the only solution at
this time. There is a bugzilla entry filed for this make bug but the
progress is slow:

https://bugzilla.redhat.com/show_bug.cgi?id=1774790

The same bug in Fedora make was dealt with fairly quickly, thanks to
the great "pressure" from Linus. ;-)

Akemi