Page MenuHomeFreeBSD
Feed Advanced Search

Sun, Oct 20

pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

Here's a

Sun, Oct 20, 5:17 PM

Sat, Oct 19

pho added a comment to D22081: Fix pointer loads in uma_vm_zone_stats()..

I tested 63458 for 17 hours with a "-O0" build of uma_core.c. LGTM.

Sat, Oct 19, 7:42 AM

Fri, Oct 18

pho added a comment to D22081: Fix pointer loads in uma_vm_zone_stats()..

Peter, could you post the disassembly of uma_vm_zone_stats() from your -O0 kernel?

Fri, Oct 18, 5:54 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.
In D20635#482367, @pho wrote:

This too, what not what I was hoping for:

Are you compiling with -O0 or some other unusual compiler flags? I suspect the patch in D22081 is required, though it has no effect on generated code in my testing.

Fri, Oct 18, 5:08 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

This too, what not what I was hoping for:

Fri, Oct 18, 12:46 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.
20191018 08:58:59 all (284/676): pipe2.sh
Fri, Oct 18, 8:26 AM

Thu, Oct 17

pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

https://people.freebsd.org/~pho/stress/log/dougm057.txt

Thu, Oct 17, 9:06 AM

Tue, Oct 15

pho added a comment to D21964: Make vm_map a threaded tree.

With debug.vmmap_check=1 I saw this problem:
https://people.freebsd.org/~pho/stress/log/dougm056.txt

Tue, Oct 15, 8:17 AM

Mon, Oct 14

pho added a comment to D21964: Make vm_map a threaded tree.
In D21964#481052, @alc wrote:
In D21964#480590, @pho wrote:

I ran all of the stress2 test on 63130. I found one problem, which to me looks unrelated.
https://people.freebsd.org/~pho/stress/log/quota10-2.txt

Peter,
Are you setting debug.vmmap_check to 1?

Mon, Oct 14, 6:41 PM

Sat, Oct 12

pho added a comment to D21964: Make vm_map a threaded tree.

I ran all of the stress2 test on 63130. I found one problem, which to me looks unrelated.
https://people.freebsd.org/~pho/stress/log/quota10-2.txt

Sat, Oct 12, 7:13 PM

Thu, Oct 10

pho added a comment to D21964: Make vm_map a threaded tree.
startup_alloc from "UMA Zones", 4 boot pages left
startup_alloc from "UMA Zones", 3 boot pages left
startup_alloc from "UMA Hash", 2 boot pages left
startup_alloc from "UMA Zones", 1 boot pages left
Entering uma_startup1 with 0 boot pages left
panic: map 0xfffff80003002000 max = 7d8df000, max_left = 1ff80000000, max_right = 7d8df000
cpuid = 0
time = 1
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xffffffff824ef830
vpanic() at vpanic+0x19d/frame 0xffffffff824ef880
panic() at panic+0x43/frame 0xffffffff824ef8e0
_vm_map_assert_consistent() at _vm_map_assert_consistent+0x3e1/frame 0xffffffff824ef940
vm_map_splay() at vm_map_splay+0x176/frame 0xffffffff824ef9a0
vm_map_lookup_entry() at vm_map_lookup_entry+0xc7/frame 0xffffffff824ef9f0
vm_map_insert() at vm_map_insert+0x1b5/frame 0xffffffff824efae0
kmem_init() at kmem_init+0xab/frame 0xffffffff824efb10
vm_mem_init() at vm_mem_init+0x51/frame 0xffffffff824efb20
mi_startup() at mi_startup+0x210/frame 0xffffffff824efb70
btext() at btext+0x2c
KDB: enter: panic
[ thread pid 0 tid 0 ]
Stopped at      kdb_enter+0x3b: movq    $0,kdb_why
db> x/s version
version:        FreeBSD 13.0-CURRENT #1 r353388M: Thu Oct 10 12:56:20 CEST 2019\012    pho@mercat1.netperf.freebsd.org:/usr/src/sys/amd64/compile/PHO\012
db>
Thu, Oct 10, 11:25 AM

Sat, Oct 5

pho added a comment to D21882: Use a loop macro for enumerating vm map entries.

I ran tests on D21882.62898 for more than a day. No problems seen.

Sat, Oct 5, 6:26 PM

Fri, Oct 4

pho committed rS353101: Added a regression test..
Added a regression test.
Fri, Oct 4, 10:45 AM

Thu, Oct 3

pho added a comment to D21882: Use a loop macro for enumerating vm map entries.

I ran tests on D21882.62858.diff for 5 1/2 hours without seeing any problems. I'll move on to 62874.

Thu, Oct 3, 4:01 PM

Fri, Sep 27

pho committed rS352789: Added a regression test..
Added a regression test.
Fri, Sep 27, 7:20 AM

Sep 6 2019

pho added a comment to D20664: Changes to vm_map_lookup_entry.

Tested D20664.61715.diff for 6 hours on amd64. No problems seen.

Sep 6 2019, 3:19 PM

Sep 4 2019

pho added a comment to D20664: Changes to vm_map_lookup_entry.

I ran a brief 10 hour test on amd64 with D20664.61638.diff. No problems seen.

Sep 4 2019, 5:36 PM

Sep 3 2019

pho committed rS351738: Disable core dumps..
Disable core dumps.
Sep 3 2019, 7:09 AM
pho committed rS351736: Added problem found..
Added problem found.
Sep 3 2019, 7:02 AM

Sep 2 2019

pho added a comment to D17599: Fix for double free when deleting entries from epoch managed lists.

It is still an issue with HEAD:

:
:
if_delmulti_locked: detaching ifnet instance 0xfffff803d7598000
if_delmulti_locked: detaching ifnet instance 0xfffff803d7598000
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
if_delmulti_locked: detaching ifnet instance 0xfffff803bc652800
Sep 2 2019, 3:21 PM
pho committed rS351689: Added a new nullfs test scenario..
Added a new nullfs test scenario.
Sep 2 2019, 8:03 AM
pho committed rS351688: Added a new tmpfs test scenario..
Added a new tmpfs test scenario.
Sep 2 2019, 8:01 AM
pho committed rS351687: Added finding. Limit load and runtime..
Added finding. Limit load and runtime.
Sep 2 2019, 7:59 AM
pho committed rS351686: Added a regression test..
Added a regression test.
Sep 2 2019, 7:56 AM
pho committed rS351685: Added two more SCTP test case variations..
Added two more SCTP test case variations.
Sep 2 2019, 7:54 AM
pho committed rS351684: Added "Fixed by". Pointed out problem with an uninitialized "flags".
Added "Fixed by". Pointed out problem with an uninitialized "flags"
Sep 2 2019, 7:53 AM

Sep 1 2019

pho added a comment to D21471: vfs: implement usecount implies holdcnt.

I ran the full stress2 test suite with D21471.61489.diff on amd64. No problems seen.

Sep 1 2019, 11:06 PM

Aug 29 2019

pho committed rS351602: Added regression tests..
Added regression tests.
Aug 29 2019, 9:29 AM

Aug 28 2019

pho added a comment to D21412: Rework v_object lifecycle for vnodes..

I ran a full stress2 test on i386 with D21412.61303.diff.
I ran tests on amd64 with D21412.61396.diff for two hours.
No problems seen.

Aug 28 2019, 9:00 PM

Aug 27 2019

pho added a comment to D21412: Rework v_object lifecycle for vnodes..
In D21412#466484, @kib wrote:

Peter, could you, please, start testing this ?

Aug 27 2019, 2:44 PM

Aug 25 2019

pho added a comment to D20814: Make entry simplification one-way.

I ran the full stress2 test with D20814.61081.diff on amd64. LGTM.

Aug 25 2019, 7:00 AM
pho added a comment to D21357: Move OBJT_VNODE specific code from vm_object_terminate() to vnode_destroy_vobject()..

I ran all of the stress2 tests with D21357.61095.diff on amd64. LGTM.

Aug 25 2019, 6:49 AM

Aug 23 2019

pho committed rS351414: Added a test scenario for "recovering from disk failures"..
Added a test scenario for "recovering from disk failures".
Aug 23 2019, 5:04 AM
pho added a comment to D20814: Make entry simplification one-way.

I should be able to free up some test hardware later today.

Aug 23 2019, 4:58 AM

Aug 21 2019

pho added a comment to D21320: amd64: rework PCPU allocation.

I ran a brief 2 hour test with D21320.61033.diff. No problems seen.

Aug 21 2019, 6:35 PM

Aug 16 2019

pho added a comment to D13671: Collection of fixes for OOM handling of some corner cases..

D13671.60851.diff LGTM.

Aug 16 2019, 8:30 AM

Aug 3 2019

pho added a comment to D20863: prototype for trimming.

I ran tests on D20863.60414.diff for 6 hours and got this ktr log.

Aug 3 2019, 1:03 PM

Aug 1 2019

pho added a comment to D20814: Make entry simplification one-way.

I ran tests for 15 hours on D20814.60344.diff without seeing any problems.

Aug 1 2019, 6:57 PM
pho added a comment to D20361: procdesc: fix reparenting when the debugger is attached.

I completed a full stress2 test on amd64 without seeing any problems.

Aug 1 2019, 3:19 AM

Jul 31 2019

pho added a comment to D20814: Make entry simplification one-way.

With D20814.60322.diff I got:

20190731 19:27:23 all (1/1): mmap10.sh
panic: vm_map_unwire: lookup failed
cpuid = 12
time = 1564594061
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00c96c5790
vpanic() at vpanic+0x19d/frame 0xfffffe00c96c57e0
panic() at panic+0x43/frame 0xfffffe00c96c5840
vm_map_wire_locked() at vm_map_wire_locked+0x69d/frame 0xfffffe00c96c5900
vm_map_wire() at vm_map_wire+0x40/frame 0xfffffe00c96c5930
kern_mlock() at kern_mlock+0x179/frame 0xfffffe00c96c5980
amd64_syscall() at amd64_syscall+0x2d6/frame 0xfffffe00c96c5ab0
fast_syscall_common() at fast_syscall_common+0x101/frame 0xfffffe00c96c5ab0

https://people.freebsd.org/~pho/stress/log/dougm055.txt

Jul 31 2019, 5:51 PM
pho added a comment to D20814: Make entry simplification one-way.

D20814.60315.diff

20190731 16:18:08 all (17/73): mmap10.sh
panic: Lock vm map (user) not exclusively locked @ ../../../vm/vm_map.c:3102
cpuid = 12
time = 1564582693
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00c7c80800
vpanic() at vpanic+0x19d/frame 0xfffffe00c7c80850
panic() at panic+0x43/frame 0xfffffe00c7c808b0
_sx_xunlock() at _sx_xunlock+0xab/frame 0xfffffe00c7c808d0
_vm_map_unlock() at _vm_map_unlock+0x75/frame 0xfffffe00c7c80900
vm_map_wire() at vm_map_wire+0x58/frame 0xfffffe00c7c80930
kern_mlock() at kern_mlock+0x179/frame 0xfffffe00c7c80980
amd64_syscall() at amd64_syscall+0x2d6/frame 0xfffffe00c7c80ab0

https://people.freebsd.org/~pho/stress/log/dougm054.txt

Jul 31 2019, 2:48 PM

Jul 30 2019

pho added a comment to D21088: Avoid conflicts with libc symbols in libthr jump table..

I ran all of the threaded tests from stress2 on amd64 with D21088.60283.diff.
No problems seen.

Jul 30 2019, 9:12 PM
pho added a comment to D20361: procdesc: fix reparenting when the debugger is attached.

Just a follow up. I'm currently testing your patch on amd64 where I have not yet seen any problems.

Jul 30 2019, 7:03 PM
pho added a comment to D20361: procdesc: fix reparenting when the debugger is attached.

I got this after a 5 hour test on i386, followed by a shutdown:

panic: vm_fault_hold: fault on nofault entry, addr: 0x83326000
cpuid = 0
time = 1564486041
KDB: stack backtrace:
db_trace_self_wrapper(e6666d,1bdcda4,0,23a17534,bd2eb1,...) at db_trace_self_wrapper+0x2a/frame 0x23a17508
kdb_backtrace(e,0,0,2b06100,2db5000,...) at kdb_backtrace+0x2e/frame 0x23a17568
vpanic(163709e,23a175b0,23a175b0,23a17680,12c2044,...) at vpanic+0x121/frame 0x23a17590
panic(163709e,158dad9,83326000,4895800,7000004,...) at panic+0x14/frame 0x23a175a4
vm_fault_hold(2db5000,83326000,2,0,0) at vm_fault_hold+0x2474/frame 0x23a17680
vm_fault(2db5000,83326000,2,0) at vm_fault+0x4a/frame 0x23a176a8
trap_pfault(8332680c) at trap_pfault+0xf3/frame 0x23a176f4
trap(23a177bc,8,28,28,83df8640,...) at trap+0x3c0/frame 0x23a177b0
calltrap() at 0xffc0316d/frame 0x23a177b0
--- trap 0xc, eip = 0xf7f255, esp = 0x23a177fc, ebp = 0x23a17814 ---
funsetownlst(27e5ea50) at funsetownlst+0xa5/frame 0x23a17814
pgdelete(27e5ea6c,23c00a80,1651842,36,23a178f8,...) at pgdelete+0x60/frame 0x23a17834
leavepgrp(298d46a8,0,1651842,396,44c,...) at leavepgrp+0xd5/frame 0x23a1784c
proc_reap(23c00a80,298d46a8,23a17ba4,36,1edeb50,...) at proc_reap+0x714/frame 0x23a178f8
proc_to_reap(23c00a80,298d46a8,7,0,0,...) at proc_to_reap+0x718/frame 0x23a17998
kern_wait6(23c00a80,7,0,0,23a17ba4,...) at kern_wait6+0x37a/frame 0x23a17a78
kern_wait(23c00a80,ffffffff,23a17ba4,36,0,...) at kern_wait+0x119/frame 0x23a17b80
sys_wait4(23c00a80,23c00d0c) at sys_wait4+0x68/frame 0x23a17c08
syscall(23a17ce8,3b,3b,3b,0,...) at syscall+0x304/frame 0x23a17cdc
Xint0x80_syscall() at 0xffc033b7/frame 0x23a17cdc

https://people.freebsd.org/~pho/stress/log/oshogbo001.txt

Jul 30 2019, 11:59 AM
pho added a comment to D20863: prototype for trimming.

Ran tests for another 23 hours on D20863.60217.diff. No problems seen.

Jul 30 2019, 5:43 AM

Jul 27 2019

pho added a comment to D20814: Make entry simplification one-way.

I tested D20814.60178.diff for 13 hours on amd64 without seeing any problems.

Jul 27 2019, 11:35 AM

Jul 25 2019

pho added a comment to D21027: Simplify handling of superpages in pmap_clear_modify().

The i386 tests finished with one further problem and an incomplete report: https://people.freebsd.org/~pho/stress/log/alc011.txt

Jul 25 2019, 4:10 AM

Jul 24 2019

pho added a comment to D21027: Simplify handling of superpages in pmap_clear_modify().

I finished the full stress2 tests on amd64 without any issues.

Jul 24 2019, 1:58 PM

Jul 22 2019

pho added a comment to D21027: Simplify handling of superpages in pmap_clear_modify().

Sure, happy to.

Jul 22 2019, 3:24 PM
pho added a comment to D20863: prototype for trimming.

https://people.freebsd.org/~pho/D20863.60019.ktr.txt.xz

Jul 22 2019, 3:18 PM
pho added a comment to D20863: prototype for trimming.

I ran tests on a GENERICish kernel for 12 hours without any issue, however a kernel build with "options KTR" does not compile:

Jul 22 2019, 8:15 AM
pho committed rS350208: Added a regression test..
Added a regression test.
Jul 22 2019, 7:20 AM

Jul 21 2019

pho added a comment to D20863: prototype for trimming.

I still see the panic with D20863.59987.diff:

Jul 21 2019, 5:43 PM
pho added a comment to D20814: Make entry simplification one-way.

I ran a brief 4 hour test with this patch.

Jul 21 2019, 3:59 PM
pho added a comment to D20947: Check and avoid overflow when incrementing fp->f_count in fget_unlocked() and fhold()..

I completed a full stress2 test with D20947.59944.diff on amd64. No problems seen.

Jul 21 2019, 9:48 AM
pho added a comment to D20863: prototype for trimming.

With D20863.59975.diff I got:

Jul 21 2019, 8:58 AM

Jul 18 2019

pho added a comment to D20833: factor out common wiring code.

A have completed a full stress2 test of D20833.59786.diff without seeing any problems.

Jul 18 2019, 5:20 AM

Jul 17 2019

pho added a comment to D20863: prototype for trimming.

I have completed a full stress2 test with D20863.59745.diff on amd64 without seeing any problems.

Jul 17 2019, 1:26 PM

Jul 15 2019

pho added a comment to D20863: prototype for trimming.

Some KTR output for a short test of D20863.59745.diff:
https://people.freebsd.org/~pho/stress/log/dougm051.txt

Jul 15 2019, 7:45 AM
pho added a comment to D20949: Two issues with casueword(9) update..

I tested D20949.59742.diff with all of the threaded tests I have, on i386. No problems seen.

Jul 15 2019, 6:10 AM

Jul 14 2019

pho added a comment to D20863: prototype for trimming.

With D20863.59728.diff I got:

Jul 14 2019, 7:35 AM

Jul 13 2019

pho added a comment to D20863: prototype for trimming.

With D20863.59658.diff I got:

Jul 13 2019, 11:46 AM

Jul 12 2019

pho added a comment to D20893: Fix a next_leaf bug.

I finished the full stress2 test of D20893.59605.diff without finding any problems.

Jul 12 2019, 6:43 PM

Jul 11 2019

pho added a comment to D20893: Fix a next_leaf bug.

The test has now run for 12 hours without any problems. I'll let the test run for the full ~48 hours.

Jul 11 2019, 6:08 AM

Jul 10 2019

pho added a comment to D20893: Fix a next_leaf bug.

As far as I can tell the "panic: freeing free block" was introduced by r349777 and this patch didn't fix that.
I have not observed any other problems while testing with D20893.59572.diff

Jul 10 2019, 4:19 PM
pho added a comment to D20893: Fix a next_leaf bug.

I have tested D20893.59572.diff on amd64 and briefly on i386.
I still see the "panic: freeing free block" on both a MEMGUARD and a GENERICish build.

Jul 10 2019, 11:59 AM

Jul 9 2019

pho committed rS349859: Tests must run as root. Clear last known test..
Tests must run as root. Clear last known test.
Jul 9 2019, 12:14 PM
pho added a comment to D20579: Remove limit on blist_alloc maxsize, allow bigger getswapspace allocations.

Looks like this patch is responsible for the panics I see.

20190709 11:56:55 all (1/1): sort.sh
swap_pager: out of swap space
swp_pager_getswapspace(32): failed
Jul  9 12:03:41 mercat1 kernel: pid 3581 (sort), jid 0, uid 0, was killed: out of swap space
Jul  9 12:03:42 mercat1 kernel: pid 3583 (sort), jid 0, uid 0, was killed: out of swap space
panic: freeing free block: ffffc0, size 16, mask 1
cpuid = 7
time = 1562666624
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe102d95b270
vpanic() at vpanic+0x19d/frame 0xfffffe102d95b2c0
panic() at panic+0x43/frame 0xfffffe102d95b320
blst_meta_free() at blst_meta_free+0x12b/frame 0xfffffe102d95b360
blst_meta_free() at blst_meta_free+0x102/frame 0xfffffe102d95b3a0
blst_meta_free() at blst_meta_free+0x102/frame 0xfffffe102d95b3e0
blst_meta_free() at blst_meta_free+0x102/frame 0xfffffe102d95b420
blst_meta_free() at blst_meta_free+0x102/frame 0xfffffe102d95b460
blist_free() at blist_free+0x2e/frame 0xfffffe102d95b480
swp_pager_freeswapspace() at swp_pager_freeswapspace+0x8a/frame 0xfffffe102d95b4a0
swp_pager_meta_free_all() at swp_pager_meta_free_all+0xbb/frame 0xfffffe102d95b4f0
swap_pager_dealloc() at swap_pager_dealloc+0x115/frame 0xfffffe102d95b510
vm_object_terminate() at vm_object_terminate+0x27b/frame 0xfffffe102d95b560
vm_object_deallocate() at vm_object_deallocate+0x412/frame 0xfffffe102d95b5c0
vm_map_process_deferred() at vm_map_process_deferred+0x7f/frame 0xfffffe102d95b5e0
vm_map_remove() at vm_map_remove+0xc6/frame 0xfffffe102d95b610
vmspace_exit() at vmspace_exit+0xd3/frame 0xfffffe102d95b650
exit1() at exit1+0x5ad/frame 0xfffffe102d95b6c0
sigexit() at sigexit+0xdaf/frame 0xfffffe102d95b9a0
postsig() at postsig+0x336/frame 0xfffffe102d95ba70
ast() at ast+0x4c7/frame 0xfffffe102d95bab0
doreti_ast() at doreti_ast+0x1f/frame 0x7fffffffded0
KDB: enter: panic
[ thread pid 3581 tid 100238 ]
Stopped at      kdb_enter+0x3b: movq    $0,kdb_why
db> x/s version
version:        FreeBSD 13.0-CURRENT #5 r349777: Tue Jul  9 11:37:16 CEST 2019\012    pho@mercat1.netperf.freebsd.org:/usr/src/sys/amd64/compile/MEMGUARD\012
db>

The same test works fine on r349776.

Jul 9 2019, 10:24 AM
pho added a comment to D20863: prototype for trimming.

https://people.freebsd.org/~pho/stress/log/dougm048.txt

Jul 9 2019, 9:35 AM
pho added a comment to D20772: Provide protection against starvation of the ll/sc loops when accessing userpace..
In D20772#452692, @kib wrote:

Thank you, Mark.
Peter, could you, please, run the tests one more time, hopefully this is the last.

Jul 9 2019, 7:29 AM
pho added a comment to D20863: prototype for trimming.

I'll try again and avoid a panic, but in the meantime here's some trace: https://people.freebsd.org/~pho/stress/log/dougm047.txt

Jul 9 2019, 6:26 AM

Jul 8 2019

pho added a comment to D20833: factor out common wiring code.

So, this is unrelated to D20833.

Jul 8 2019, 9:34 AM
pho added a comment to D20833: factor out common wiring code.

The obvious questions are:
Does this happen without the patch in place?
Does this happen before r349777?

Jul 8 2019, 8:29 AM
pho added a comment to D20833: factor out common wiring code.

Came across this panic:

Jul 8 2019, 5:50 AM

Jul 7 2019

pho added a comment to D20833: factor out common wiring code.

I ran tests for 5 hours on i386 with D20833.59496.diff. No problems seen.

Jul 7 2019, 12:48 PM
pho added a comment to D20833: factor out common wiring code.

I have started a brief test run on i386 with D20833.59496.diff.

Jul 7 2019, 9:13 AM

Jul 6 2019

pho added a comment to D20833: factor out common wiring code.

I tested D20833.59460.diff for 5 hours without seeing any problems.

Jul 6 2019, 12:25 PM

Jul 5 2019

pho added a comment to D20579: Remove limit on blist_alloc maxsize, allow bigger getswapspace allocations.

I have run tests on D20579.59404.diff (with the typo fixed) for 8 hours. This included a buildworld / installworld.

Jul 5 2019, 8:15 PM
pho added a comment to D20579: Remove limit on blist_alloc maxsize, allow bigger getswapspace allocations.
cc -c -O2 -pipe -fno-strict-aliasing  -g -nostdinc  -I. -I../../.. -I../../../contrib/ck/include -I../../../contrib/libfdt -D_KERNEL -DHAVE_KERNEL_OPTION_HEADERS -include opt_global.h    -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -MD  -MF.depend.subr_blist.o -MTsubr_blist.o -fdebug-prefix-map=./machine=/usr/src/sys/amd64/include -fdebug-prefix-map=./x86=/usr/src/sys/x86/include -mcmodel=kernel -mno-red-zone -mno-mmx -mno-sse -msoft-float  -fno-asynchronous-unwind-tables -ffreestanding -fwrapv -fstack-protector -gdwarf-2 -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes -Wmissing-prototypes -Wpointer-arith -Wcast-qual -Wundef -Wno-pointer-sign -D__printf__=__freebsd_kprintf__ -Wmissing-include-dirs -fdiagnostics-show-option -Wno-unknown-pragmas -Wno-error-tautological-compare -Wno-error-empty-body -Wno-error-parentheses-equality -Wno-error-unused-function -Wno-error-pointer-sign -Wno-error-shift-negative-value -Wno-address-of-packed-member  -mno-aes -mno-avx  -std=iso9899:1999 -Werror  ../../../kern/subr_blist.c                                                                                                                                                
../../../kern/subr_blist.c:659:17: error: use of undeclared identifier 'BLIST_MAP_RADIX'
        if (maxcount % BLIST_MAP_RADIX != 0)
                       ^
1 error generated.
*** Error code 1
Jul 5 2019, 11:20 AM
pho added a comment to D20833: factor out common wiring code.

Ran a brief test (5 hours) on D20833.59430.diff. No problems seen.

Jul 5 2019, 11:11 AM
pho committed rS349761: Added a regression test..
Added a regression test.
Jul 5 2019, 6:53 AM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

I have run tests on D20635.59379.diff for 24 hours without seeing any problems.

Jul 5 2019, 5:12 AM

Jul 4 2019

pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.
In D20635#451659, @alc wrote:

Peter, can you please retest this patch? I think that all of the open issues have been addressed.

Jul 4 2019, 6:52 PM

Jul 3 2019

pho added a comment to D20833: factor out common wiring code.

I ran tests on D20833.59317.diff for 14 hours. LGTM.

Jul 3 2019, 7:01 AM

Jul 2 2019

pho added a comment to D20664: Changes to vm_map_lookup_entry.

Yes, fetch doesn't work well. Try using wget, which recovers from closed connections.

Jul 2 2019, 8:11 PM
pho added a comment to D20833: factor out common wiring code.
Fatal trap 12: page fault while in kernel mode
cpuid = 0; current process		= 4000 (tmlock)
interrupt enabled, fault virtual address	= 0x20
stack pointer	        = 0x28:0xfffffe00ad822860
resume, IOPL = 0
current process		= 4002 (tmlock)
code segment		= base 0x0, limit 0xfffff, type 0x1b
code segment		= base 0x0, limit 0xfffff, type 0x1b
			= DPL 0, pres 1, long 1, def32 0, gran 1
trap number		= 12
panic: page fault
cpuid = 11
time = 1562057287
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00ac311520
vpanic() at vpanic+0x19d/frame 0xfffffe00ac311570
panic() at panic+0x43/frame 0xfffffe00ac3115d0
trap_fatal() at trap_fatal+0x39c/frame 0xfffffe00ac311630
trap_pfault() at trap_pfault+0x62/frame 0xfffffe00ac311680
trap() at trap+0x2b4/frame 0xfffffe00ac311790
calltrap() at calltrap+0x8/frame 0xfffffe00ac311790
--- trap 0xc, rip = 0xffffffff80f0db15, rsp = 0xfffffe00ac311860, rbp = 0xfffffe00ac311910 ---
vm_map_wire_locked() at vm_map_wire_locked+0x155/frame 0xfffffe00ac311910
vm_map_wire() at vm_map_wire+0x40/frame 0xfffffe00ac311940
kern_mlock() at kern_mlock+0x179/frame 0xfffffe00ac311990
amd64_syscall() at amd64_syscall+0x291/frame 0xfffffe00ac311ab0

https://people.freebsd.org/~pho/stress/log/dougm046.txt

Jul 2 2019, 8:57 AM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

I have completed the selected swap tests and continued to run random tests for a total of 13H30.
No problems seen.

Jul 2 2019, 7:29 AM

Jul 1 2019

pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

This version got me past the test that kept triggering problems. I'll run some more tests ...

Jul 1 2019, 6:36 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.
20190701 18:36:41 all (5/10): swap5.sh
panic: swp_pager_force_pagein: Too many pages: 32
cpuid = 8
time = 1561999005
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00adc594c0
vpanic() at vpanic+0x19d/frame 0xfffffe00adc59510
panic() at panic+0x43/frame 0xfffffe00adc59570
swp_pager_force_pagein() at swp_pager_force_pagein+0x7f/frame 0xfffffe00adc596f0
swap_pager_swapoff_object() at swap_pager_swapoff_object+0xfe/frame 0xfffffe00adc59750
swap_pager_swapoff() at swap_pager_swapoff+0xf9/frame 0xfffffe00adc597d0
swapoff_one() at swapoff_one+0x15e/frame 0xfffffe00adc59820
sys_swapoff() at sys_swapoff+0x1d6/frame 0xfffffe00adc59990
amd64_syscall() at amd64_syscall+0x291/frame 0xfffffe00adc59ab0

https://people.freebsd.org/~pho/stress/log/dougm045.txt

Jul 1 2019, 5:00 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

I'll try Diff 59264.

Jul 1 2019, 4:04 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

D20635.59261.diff did not seem to fix the problem.

20190701 17:39:16 all (5/10): swap5.sh
Jul 1 2019, 4:03 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

With D20635.59244.diff I now see a deadlock:
https://people.freebsd.org/~pho/stress/log/dougm044.txt

Jul 1 2019, 9:38 AM
pho added a comment to D20814: Make entry simplification one-way.
20190701 07:18:49 all (2/70): mmap10.sh
panic: _vm_map_clip_start: invalid clip of entry 0xfffff801496d34d0
cpuid = 9
time = 1561958339
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00ad7307a0
vpanic() at vpanic+0x19d/frame 0xfffffe00ad7307f0
panic() at panic+0x43/frame 0xfffffe00ad730850
_vm_map_clip_start() at _vm_map_clip_start+0x81/frame 0xfffffe00ad730890
vm_map_unwire() at vm_map_unwire+0x350/frame 0xfffffe00ad730960
sys_munlockall() at sys_munlockall+0x71/frame 0xfffffe00ad730990
amd64_syscall() at amd64_syscall+0x291/frame 0xfffffe00ad730ab0
fast_syscall_common() at fast_syscall_common+0x101/frame 0xfffffe00ad730ab0

https://people.freebsd.org/~pho/stress/log/dougm043.txt

Jul 1 2019, 5:39 AM
pho committed rS349570: Add missing x bit to the script..
Add missing x bit to the script.
Jul 1 2019, 5:12 AM
pho committed rS349569: Added a regression test..
Added a regression test.
Jul 1 2019, 5:09 AM

Jun 30 2019

pho added a comment to D20664: Changes to vm_map_lookup_entry.

https://people.freebsd.org/~pho/vmcore.1136.gz
https://people.freebsd.org/~pho/src.1136.gz

Jun 30 2019, 7:55 PM
pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

With D20635.59216.diff I see:

20190630 11:39:48 all (5/10): swap5.sh
panic: swapoff: failed to locate 8036 swap blocks
cpuid = 2
time = 1561887597
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe00ad6c26a0
vpanic() at vpanic+0x19d/frame 0xfffffe00ad6c26f0
panic() at panic+0x43/frame 0xfffffe00ad6c2750
swap_pager_swapoff() at swap_pager_swapoff+0x194/frame 0xfffffe00ad6c27d0
swapoff_one() at swapoff_one+0x15e/frame 0xfffffe00ad6c2820
sys_swapoff() at sys_swapoff+0x1d6/frame 0xfffffe00ad6c2990
amd64_syscall() at amd64_syscall+0x291/frame 0xfffffe00ad6c2ab0
fast_syscall_common() at fast_syscall_common+0x101/frame 0xfffffe00ad6c2ab0
--- syscall (424, FreeBSD ELF64, sys_swapoff), rip = 0x8002f88ca, rsp = 0x7fffffffe4c8, rbp = 0x7fffffffe5f0 ---
KDB: enter: panic
[ thread pid 15529 tid 100290 ]
Stopped at      kdb_enter+0x3b: movq    $0,kdb_why
db> x/s version
version:        FreeBSD 13.0-CURRENT #1 r349552M: Sun Jun 30 10:48:06 CEST 2019\012    pho@mercat1.netperf.freebsd.org:/usr/src/sys/amd64/compile/PHO\012
db>

The swap5.sh test scenario is a "Test with out of swap space" test using a 4g memory disk as swap.

Jun 30 2019, 10:56 AM
pho committed rS349553: Added a regression test..
Added a regression test.
Jun 30 2019, 6:44 AM
pho added a comment to D20772: Provide protection against starvation of the ll/sc loops when accessing userpace..

On i386 I ran a buildworld / installworld + random stress2 tests for a total of 10H30.
On amd64 I ran random stress2 test for 10H30.
No problems seen.

Jun 30 2019, 5:56 AM

Jun 29 2019

pho added a comment to D20635: release multiple swap blocks at a time in swp_pager_force_pagein.

https://people.freebsd.org/~pho/stress/log/dougm042.txt

Jun 29 2019, 8:32 PM