Re: svn commit: r289279 - in head/sys: kern vm

hiya, Just bringing this to peoples attention again - the same issue (buf exhaustion, stuck in a loop trying to wake things up) exists. I'm going to commit the sched_yield() change with a big comment about why it's here and that it needs further investigation. That way things are stable again

Re: svn commit: r289279 - in head/sys: kern vm

HI, FYI - this patch did fix my initial issue, but further work in multi-user mode caused it to still hang. I haven't diagnosed it yet; I just put back the yield call so bufdaemon could run. So yeah, we still have some work to do. It hit the same problem; stuck in a loop calling the path to

Re: svn commit: r289279 - in head/sys: kern vm

Hi, try this? adrian@victoria:~/work/freebsd/head-embedded/src/sys/kern % svn diff vfs_bio.c Index: vfs_bio.c === --- vfs_bio.c (revision 290048) +++ vfs_bio.c (working copy) @@ -3623,6 +3623,13 @@ if (bp ==

Re: svn commit: r289279 - in head/sys: kern vm

Hi Tijl, and others; Here's something that Jeff came up with that fixes my problem: adrian@victoria:~/work/freebsd/head-embedded/src % svn diff sys/kern/ Index: sys/kern/vfs_bio.c === --- sys/kern/vfs_bio.c (revision 290048) +++

Re: svn commit: r289279 - in head/sys: kern vm

> On Nov 1, 2015, at 19:20, Adrian Chadd wrote: > > hiya jeff, > > this broke low-memory, no-swap boards (eg MIPS.) > > On a MIPS board (carambola2) with 32MB of RAM, just scp'ing a kernel > into the rootfs on USB hangs the system. After doing some digging, I > found

Re: svn commit: r289279 - in head/sys: kern vm

well, there's one cpu, nbuf=128, so lofreebuffers will be MIN(nbuf/25+20, 128); nbuf=128, so it'll be 25. hifreebuffers will be .. (3*25)/2, so 37. -adrian ___ svn-src-all@freebsd.org mailing list https://lists.freebsd.org/mailman/listinfo/svn-src-all

Re: svn commit: r289279 - in head/sys: kern vm

> On Nov 1, 2015, at 20:15, Adrian Chadd wrote: > > well, there's one cpu, nbuf=128, so lofreebuffers will be > MIN(nbuf/25+20, 128); nbuf=128, so it'll be 25. > hifreebuffers will be .. (3*25)/2, so 37. The values calculated via the old formulas were 12 and 24, BTW.

Re: svn commit: r289279 - in head/sys: kern vm

On Sun, 1 Nov 2015, NGie Cooper wrote: On Nov 1, 2015, at 19:20, Adrian Chadd wrote: hiya jeff, this broke low-memory, no-swap boards (eg MIPS.) On a MIPS board (carambola2) with 32MB of RAM, just scp'ing a kernel into the rootfs on USB hangs the system. After

Re: svn commit: r289279 - in head/sys: kern vm

> On Nov 1, 2015, at 19:33, Adrian Chadd wrote: > > Well, sure, but what was it doing before? Like, what should I tune it to? > > 32MB of RAM (and we still boot/run on 16MB RAM, fwiw) doesn't exactly > leave much in the way of "space" ... I don’t have benchmarks that I

Re: svn commit: r289279 - in head/sys: kern vm

On 1 November 2015 at 20:05, Jeff Roberson wrote: > On Sun, 1 Nov 2015, NGie Cooper wrote: > >> >>> On Nov 1, 2015, at 19:20, Adrian Chadd wrote: >>> >>> hiya jeff, >>> >>> this broke low-memory, no-swap boards (eg MIPS.) >>> >>> On a MIPS board

Re: svn commit: r289279 - in head/sys: kern vm

On 1 November 2015 at 20:20, NGie Cooper wrote: > >> On Nov 1, 2015, at 20:15, Adrian Chadd wrote: >> >> well, there's one cpu, nbuf=128, so lofreebuffers will be >> MIN(nbuf/25+20, 128); nbuf=128, so it'll be 25. >> hifreebuffers will be ..

Re: svn commit: r289279 - in head/sys: kern vm

hiya jeff, this broke low-memory, no-swap boards (eg MIPS.) On a MIPS board (carambola2) with 32MB of RAM, just scp'ing a kernel into the rootfs on USB hangs the system. After doing some digging, I found this: INTERNAL: Allocating one item from buf free cache(0x83fea7e0) uma_zalloc_arg:

Re: svn commit: r289279 - in head/sys: kern vm

On 10/13/2015 7:10 PM, Jeff Roberson wrote: > Author: jeff > Date: Wed Oct 14 02:10:07 2015 > New Revision: 289279 > URL: https://svnweb.freebsd.org/changeset/base/289279 > > Log: > Parallelize the buffer cache and rewrite getnewbuf(). This results in a > 8x performance improvement in a

Re: svn commit: r289279 - in head/sys: kern vm

On Thu, 29 Oct 2015 22:33:34 +0200 Konstantin Belousov wrote: > On Thu, Oct 29, 2015 at 09:25:54PM +0100, Tijl Coosemans wrote: >> On Wed, 14 Oct 2015 02:10:07 + (UTC) Jeff Roberson >> wrote: >>> Author: jeff >>> Date: Wed Oct 14 02:10:07 2015 >>>

Re: svn commit: r289279 - in head/sys: kern vm

On 10/29/2015 1:31 PM, Eric van Gyzen wrote: > On 10/29/2015 15:25, Tijl Coosemans wrote: >> On Wed, 14 Oct 2015 02:10:07 + (UTC) Jeff Roberson >> wrote: >>> Author: jeff >>> Date: Wed Oct 14 02:10:07 2015 >>> New Revision: 289279 >>> URL:

Re: svn commit: r289279 - in head/sys: kern vm

On Thu, Oct 29, 2015 at 09:25:54PM +0100, Tijl Coosemans wrote: > On Wed, 14 Oct 2015 02:10:07 + (UTC) Jeff Roberson > wrote: > > Author: jeff > > Date: Wed Oct 14 02:10:07 2015 > > New Revision: 289279 > > URL: https://svnweb.freebsd.org/changeset/base/289279 > > > > Log:

Re: svn commit: r289279 - in head/sys: kern vm

On Wed, 14 Oct 2015 02:10:07 + (UTC) Jeff Roberson wrote: > Author: jeff > Date: Wed Oct 14 02:10:07 2015 > New Revision: 289279 > URL: https://svnweb.freebsd.org/changeset/base/289279 > > Log: > Parallelize the buffer cache and rewrite getnewbuf(). This results in a >

Re: svn commit: r289279 - in head/sys: kern vm

On 10/29/2015 15:25, Tijl Coosemans wrote: > On Wed, 14 Oct 2015 02:10:07 + (UTC) Jeff Roberson > wrote: >> Author: jeff >> Date: Wed Oct 14 02:10:07 2015 >> New Revision: 289279 >> URL: https://svnweb.freebsd.org/changeset/base/289279 >> >> Log: >> Parallelize the buffer

svn commit: r289279 - in head/sys: kern vm

Author: jeff Date: Wed Oct 14 02:10:07 2015 New Revision: 289279 URL: https://svnweb.freebsd.org/changeset/base/289279 Log: Parallelize the buffer cache and rewrite getnewbuf(). This results in a 8x performance improvement in a micro benchmark on a 4 socket machine. - Get buffer