Out of memory again

J

Jason_25

64GB DDR4 RAM. I have not yet upgraded to a new system with 128GB DDR5 RAM but I am about to. I may even reduce my storage amount to below the RAM amount to make running out an impossibility. Then I will finallly have a decent system and not be such a bother around here. Jason_25 runs out of RAM again. How boring.

I now have my system in a state where I can only open around 1 tab at a time in the browser. Also killall -9 falkon is unsuccesful most of the time. This command should not return to the cursor until complete but it does anyway and falkon is not killed. Since I have the system in this state and it has not crashed yet or rebooted what can I do to figure out what is going on? I assume the ZFS arc cache should still be allowing me to open at least 1 tab with this much memory?

"top -o res -d 1":
Code: 
last pid: 22643;  load averages:  1.43,  1.17,  0.98   up 104+09:26:55 10:47:46
106 processes: 1 running, 105 sleeping
CPU:  5.4% user,  0.6% nice,  1.7% system,  0.3% interrupt, 92.0% idle
Mem: 37M Active, 3216K Inact, 2464K Laundry, 57G Wired, 480M Free
ARC: 1907M Total, 1026M MFU, 188M MRU, 266K Anon, 18M Header, 673M Other
     804M Compressed, 2921M Uncompressed, 3.63:1 Ratio

  PID USERNAME    THR PRI NICE   SIZE    RES STATE    C   TIME    WCPU COMMAND
11404 jason        29  21    0  1484M   699M uwait    6 150:08  16.99% mpv
26032 jason        30  21    0  1702M   597M uwait    5 430.5H  16.16% mpv
22541 jason        70  21    0  1133M   344M select   2   0:48   3.47% falkon
25807 jason        14  26    0   535M   242M select   4  78.3H   6.64% Xorg
21976 jason        73  20    0  3048M   235M select   4   0:21   0.59% firefox
25861 jason        50  21    0  1141M   152M select   7  14:30   4.00% plasmash
22575 jason        19  36   10    16G    82M uwait    2   0:13   0.78% QtWebEng
22560 jason        12  36   10  8657M    81M uwait    0   0:02   0.00% QtWebEng
25841 jason        18  20    0   651M    78M select   1  15:14   0.49% kwin_x11
21982 jason        29  20    0  2580M    73M select   7   0:04   0.00% firefox
 2316 jason        32  20    0   656M    72M select   6   0:14   0.00% krunner
22561 jason        12  36   10  8659M    60M uwait    5   0:05   1.27% QtWebEng
25977 jason        16  20    0   542M    57M select   3   1:05   0.00% konsole
22638 jason        13  68    0   472M    49M select   5   0:01  59.67% konsole
21985 jason        29  20    0  2534M    38M select   7   0:03   0.59% firefox
21983 jason        28  20    0  2512M    38M select   0   0:01   0.00% firefox
25956 jason         9  20    0   457M    37M select   2 284:31   0.49% konsole
34925 jason        10  20    0   479M    36M select   0   0:22   0.00% konsole
26435 jason        10  20    0   457M    35M select   2  48:52   0.00% konsole
25995 jason         9  20    0   461M    35M select   4 412:12   0.00% konsole
26015 jason         9  20    0   467M    35M select   2 351:41   0.00% konsole
26310 jason         9  20    0   456M    34M select   5 102:43   0.00% konsole
26253 jason         9  20    0   457M    33M select   4   1:37   0.00% konsole
57739 jason        10  20    0   452M    30M select   2 170:44   0.00% ksysguar
25869 jason        10  20    0   427M    24M select   5  11:57   0.00% Discover
25855 jason         9  20    0   327M    23M select   1   0:44   0.00% ksmserve
25829 jason         9  20    0   318M    22M select   0   0:28   0.00% klaunche
25860 jason         9  20    0   320M    21M select   2   0:40   0.00% kaccess
21988 jason        19  20    0  2446M    21M select   3   0:00   0.00% firefox
21987 jason        19  20    0  2446M    21M select   5   0:00   0.00% firefox
 
Run vmstat -m on a freshly booted system. Save the output somewhere. Run it again later and again later. Compare the outputs. If there's a kernel memory leak it will help you discover it.

Probably a good idea to run the above diagnostics and open a bugzilla bug about this.

Also describe what kind of work you do on this system. If it is a bug, it will help track it down. If it's not a bug, it will explain what the workload is causing the kernel to allocate memory as it does.

But without the diagnostics all anyone can do is guess. And guessing doesn't solve problems.
 
cracauer@ said:
That wired memory will not constrain the web browser. Something else is going on here.
Click to expand...
How do you mean?
Wired memory is wired (non-pageable), likely by the kernel, it is not available to userland applications.
So, it does constrain them.

Jason_25 said:
Mem: 37M Active, 3216K Inact, 2464K Laundry, 57G Wired, 480M Free
Click to expand...
Free memory is likely below or near the limit.
Active, Inactive and Laundry are in low megabytes.
Wired memory is suffocating userland.
 
Sorry to take so long to get back to this.

I am willing to admit there could be some misdiagnosing going on but the browser should not be able to freeze the system from several seconds all the way to infinity.

I have not yet restarted but have restarted xorg at least so I could use the computer. It got to the point that one tab even in Firefox - not Falkon - was freezing the computer up. Still only 564M free and I have not even started my streams yet. Furthermore I have yet to start browsing in Amazon again which brings the freezes the quickest. This is the "short reprieve" phase where I can get 1-3 more days out of the computer until it is unusable to the point of needing to be rebooted or just freezes up completely.

My workload is as follows. 1 nano to do list. 3 remote terminals. 1 Firefox window with website status page. 1 terminal window with terminal weather. 2 HD ATSC mpv streams. 1 Falkon window with up to around 50 tabs but usually around 10-20.

As mentioned before my media computer is identical hardware also with FreeBSD and 64GB RAM and behaves similarly. Falkon browser seems to bring on the trouble with that computer as well. It will need a reboot soon. The Problem with Falkon is only a symptom of a greater problem with memory management in FreeBSD unfortunately.

Thank you to Andriy for mentioning that wired memory is suffocating userland - seemingly in my case. This is the first thing I have seen where someone knows what they are talking about and I am not just going crazy here.

I do feel confident that 128GB RAM can "brute force" this problem and allow as much as 6 months instead of 3 months uptime. I am keeping my eye on something low power. I just had a shower thought a few days ago that the world's fastest supercomputer as of like 15 years ago is not strong enough for FreeBSD, pretty cool!

These are still from the "affected" system because I have not rebooted yet. I am not understanding much from these statistics right at the moment.

"top -o res -d 1":
Code: 
last pid:  4790;  load averages:  0.25,  0.25,  0.17   up 110+01:17:07 02:37:58
94 processes:  1 running, 93 sleeping
CPU:  5.1% user,  0.6% nice,  1.7% system,  0.3% interrupt, 92.3% idle
Mem: 29M Active, 8216K Inact, 57G Wired, 599M Free
ARC: 1936M Total, 1123M MFU, 142M MRU, 498K Anon, 22M Header, 644M Other
     854M Compressed, 2933M Uncompressed, 3.43:1 Ratio

  PID USERNAME    THR PRI NICE   SIZE    RES STATE    C   TIME    WCPU COMMAND
 4609 jason        17  36   10    25G   402M uwait    2   0:28   0.00% QtWebEng
33037 jason        92  20    0  3713M   373M select   1   6:52   1.27% firefox
 4507 jason        69  20    0  1012M   254M select   2   0:47   1.46% falkon
33045 jason        28  20    0  3027M   240M select   2   0:51   0.00% firefox
32961 jason        31  20    0  1048M   185M select   1   0:37   0.68% plasmash
32908 jason        14  20    0   342M   107M select   3   2:35   1.07% Xorg
 4510 jason        19  37   10    17G   107M uwait    1   0:52   4.83% QtWebEng
 4785 jason        13  24    0   456M    44M select   6   0:01   7.76% konsole
32942 jason        13  20    0   486M    40M select   0   0:09   0.10% kwin_x11
33046 jason        27  20    0  2509M    39M select   4   0:21   0.00% firefox
33048 jason        27  20    0  2545M    39M select   1   1:15   0.39% firefox
 4523 jason        10  20    0   458M    36M select   5   0:03   0.00% konsole
33132 jason         9  20    0   456M    35M select   7   0:48   0.00% konsole
33113 jason         9  20    0   456M    34M select   0   0:06   0.00% konsole
33085 jason         9  20    0   456M    34M select   7   0:01   0.00% konsole
33151 jason         9  20    0   456M    34M select   7   0:01   0.00% konsole
32940 jason        17  20    0   412M    32M select   5   0:23   0.00% kded5
33015 jason        10  20    0   452M    30M select   2   3:55   0.00% ksysguar
32971 jason        10  20    0   427M    26M select   1   0:16   0.00% Discover
32956 jason         9  20    0   321M    24M select   7   0:01   0.00% ksmserve
32963 jason         9  20    0   320M    24M select   1   0:01   0.00% kaccess
32930 jason         9  20    0   318M    23M select   1   0:00   0.00% klaunche
33072 jason        18  20    0  2446M    21M select   3   0:18   0.00% firefox
34341 jason        18  20    0  2446M    21M select   4   0:17   0.00% firefox
34328 jason        18  20    0  2446M    21M select   2   0:18   0.00% firefox
33047 jason         5  20    0   262M    16M select   5   0:00   0.00% firefox
33042 jason         6  20    0   229M    12M select   6   0:00   0.00% firefox
32987 jason         7  20    0   135M    12M select   5   0:03   0.00% kactivit
32959 jason         5  20    0   134M  9804K select   2   0:00   0.00% org_kde_
32950 jason         3  20    0    96M  7668K select   5   0:00   0.00% kglobala
32926 jason         3  68    0   117M  7356K select   0   0:00   0.00% plasma_s

"vmstat -m":
Code: 
[jason@TRITON /usr/home/jason]$ vmstat -m
            Type  Use Memory Req Size(s)
CAM I/O Scheduler    3   384    3 128
      CAM periph    8  1.9K   31 16,32,64,128,256
       CAM queue   15   39K   51 16,32,1K,16K
   CAM dev queue    6   384    6 64
         CAM SIM    6   768    6 128
         CAM XPT   38   11K 2.7k 16,32,64,128,512,1K,2K,4K,8K,64K
         CAM DEV    9   18K   20 2K
         CAM CCB    0     0 164M 2K
        CAM path   12   384   75 32
        acpiintr    1    64    1 64
          acpica 7.2k  744K 584k 16,32,64,128,256,384,512,1K,2K,4K
        acpitask    1  224K    1  
         acpisem   55  6.9K   55 128
         acpidev  101  6.3K  101 64
       acpi_perf    8  1.0K    8 128
           evdev   20   25K  320 1K,2K
          kbdmux   10   27K   10 16,384,1K,2K,8K,16K
            nvme  544   78K 164M 32,128,1K,2K
         entropy    1    32 310M 16,32,64,128,256,1K,4K
            hdaa    9   61K    9 1K,2K,4K,16K,32K
            hdac    2  1.4K    2 384,1K
           hdacc    2    64    2 32
          feeder   56  6.3K  16k 32,128
           mixer    6   24K    6 4K
             USB   85  160K  112 16,32,64,128,256,384,1K,2K,4K,8K,16K
          USBdev  123  128K  228 32,64,128,256,384,512,2K,4K
           vtbuf   24  4.0M   70 4K
              vt   13   40K  121 64,384,4K,32K
          DEVFS3  464  116K  19k 256
          DEVFS1  436  436K  19k 1K
      DEVFS_RULE   61   21K   61 64,384
           DEVFS   29   576   31 16,128
          DEVFSP   14   896 1.8k 64
   NFSD srvcache    3   68K    3 4K,32K
   NFSD V4client    1   256    1 256
    NFSD lckfile    1   256    1 256
    NFSD session    1  1.0K    1 1K
       pfs_nodes   20  5.0K   20 256
     pfs_vncache    1  128K    1  
            GEOM  132   25K 7.8k 16,32,64,128,256,384,512,1K,2K,8K,16K,64K
       raid_data    0     0  126 32,128,256
          isadev    8  1.0K    8 128
            cdev    1   256    1 256
        filedesc  120  1.4M  58k 16,32,64,128,256,384,512,4K,8K,16K,32K,64K
         pwddesc  111  6.9K 3.6M 64
           sigio    2   128   14 64
        filecaps    6   192 3.8M 16,32,64,128,256,384,512,1K
         kdtrace 1.2k  271K 6.5M 64,256
            kenv  147   14K  147 16,32,64,128,8K
          kqueue  195  124K 3.6M 64,256,512,2K,4K,8K,16K
       proc-args  235  8.8K 8.1M 16,32,64,128,256
           hhook   15  4.9K   17 16,32,384
         ithread  124   24K  124 32,128,256
          prison   10   304   10 16,32
          KTRACE  100   13K  100 128
          linker  817  4.5M 1.5k 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64
K
           lockf  323   37K 5.0M 64,128
      loginclass    2   128    2 64
           cache    1    32    1 32
          devbuf 4.7k  5.8M 121M 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64
K
            temp   49   38K 3.0G 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64
K
          module  541   68K  541 128
        mtx_pool    2   72K    2 8K,64K
             osd  309  5.4K 1.0M 16,32,64,128,256,384
        pmchooks    1   128    1 128
             pmc    1    64    1 64
         session   34  4.3K  74k 128
            proc    3  264K    3 8K
         subproc  354  535K 3.6M 384,4K
            cred   83   21K 1.7M 256
          plimit   32  8.0K 978k 256
         uidinfo    6   33K 321k 128,32K
          sysctl    1    32 157M 32,64
       sysctloid  38k  2.1M  38k 16,32,64,128,256
       sysctltmp    0     0 9.9M 16,64,256,1K
         tidhash    3  396K    3 16K
         callout    8  2.0M    8  
            umtx 4.2k  528K 4.2k 128
        p1003.1b    1    16    1 16
             bus 1.5k  146K  41k 16,32,64,128,256,2K,4K
          bus-sc  127  5.4M 7.5k 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64
K
         devstat    8   16K    8 32,4K
    eventhandler  154   13K  154 64,128
        firmware   24  1.9K   24 16,32,128
      gtaskqueue   54  101K   54 16,32,256,32K
            kobj  351  1.4M 2.8k 4K
         Per-cpu    1    32    1 32
            rman  286   31K  689 32,128
            sbuf    1   128  63M 16,32,64,128,256,512,1K,2K,4K,8K,16K,32K
       toponodes   22  5.5K   22 256
       taskqueue  165   18K  56k 16,32,64,128,256
        terminal   11  2.8K   11 256
          Unitno   24  1.5K  75k 32,64
            vmem    2  1.1M   19 16K,32K,64K
         eventfd  148   19K  28k 128
        ioctlops    0     0  23M 256,384,1K,2K
          select  169   21K 908k 128
             iov    0     0  13G 16,32,64,128,256,384,512,1K,2K,4K
           selfd  584   37K  92G 64
        procdesc    4   512 1.3k 128
         timerfd    1   384    3 384
             msg    4   30K    4 2K,4K,8K,16K
             sem    4  106K    4 2K,4K
             shm   23   76K  19k 2K,32K
             tty   22   22K  19k 1K
             pts   10  2.5K  19k 256
           shmfd  31k  7.6M 240k 256,8K
          soname  103   12K 161M 16,32,64,128
             pcb   17  9.0M  19k 16,32,256,1K,2K
             acl    0     0 136k 4K
          biobuf    7   14K    7 2K
        vfscache    3   16M    3 4K,8K
        vfs_hash    1  8.0M    1  
          vnodes    1   256    1 256
   namei_tracker    0     0    2 32
           mount  293   11K  549 16,32,64,128,256,1K
          statfs    0     0  31M 4K
         VN POLL 2.5k  316K  11k 128
     vnodemarker    3  1.5K    5 512
         fadvise    0     0 121k 32
  chacha20random    1  2.0K    1 2K
             BPF    4   512    6 128
           ifnet    5  8.1K    7 128,2K
          ifaddr   52   13K   84 16,32,64,128,256,384,2K,4K
     ether_multi   22  1.7K  162 16,32,64,128
           clone    8  2.0K    8 256
         lltable   24  7.0K 2.1k 256,384
             tun    3    96    3 32
           iflib   29  206K   33 16,64,128,256,512,2K,8K,16K,32K
            pfil    6   768    6 128
           nhops   28  3.3K   28 64,128
        routetbl  122   35K  472 32,64,128,256,384,512,1K,2K
            vnet    1    64    1 64
       vnet_data    1  112K    1  
  vnet_data_free    1    32    1 32
       80211node    0     0 634k 16
       80211scan    1   16K    1 16K
            igmp    4   512    6 128
      in_mfilter    0     0   28 64
        in_multi    3   768   31 256
     ip_moptions    2   128   27 64
encap_export_host    8   448    8 32,64
        IP reass    1  128K    1  
          CC Mem  136   34K 931k 256
      tfo_ccache    1  128K    1  
       hostcache    1   32K    1 32K
             LRO    4   80K    4 8K,32K
         tcpfunc    1    64    1 64
        syncache    1   68K    1  
       in6_multi   15  1.6K   15 32,256
    ip6_moptions    1    32    1 32
          ip6opt    3   768    3 256
             mld    4   512    6 128
          ip6ndp    5   512    7 64,256
     inpcbpolicy  197  6.2K  19M 32
        secasvar    1  1.0K    1 1K
          sahead    1  1.0K    1 1K
     ipsecpolicy    1  1.0K    1 1K
       ipsec-saq    2  2.0K    2 1K
         netlink    2   512  19k 128,384,2K
     lkpikmalloc  95M   23G  31G 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64
K
          lkpifw   11   352   22 32
             idr 2.2k  823K  28k 128,384
          crypto    4  1.4K    4 64,256,1K
   audit_evclass  238  7.4K  300 32
       ufs_quota    1  8.0M    1  
             UMA  235  4.8K  235 16,32
   vm_fictitious    2   52M    2 64
             rpc    4  8.1K    4 16,128,4K
        pci_link   16  1.3K   16 32,128
        atkbddev    2   128    2 64
          apmdev    1   128    1 128
          busdma  11k  689K  11k 64,256
          bounce  11k   43M  11k  
            intr    4  472K    4 64K
             MCA   32  5.9K   32 64,128,384
            cpus    2    48    2 16,32
        nexusdev    7   112    7 16
         memdesc    1  4.0K    1 4K
      madt_table    0     0    2 64,4K
         io_apic    2  6.0K    2 2K,4K
      local_apic    1  8.0K    1 8K
             msi   19  2.4K   19 128
         solaris 1.4M  396M 4.7G 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,64K
      kstat_data   36   36K   36 1K
           taskq    2   768    2 256,512
       sfs_nodes   22  8.3K   22 384
          dmabuf   19  285K 276k 32,64,128,256,384,512
      drm_driver    1    32    1 32
         drm_kms 0.0E  0.0E   14 64
          fb_kms    2   448    2 64,384
         acpiwmi    2   128    3 64
   netgraph_node    2   256    2 128
     fdesc_mount    1    16    1 16
 
"vmstat -z":
Code: 
ITEM                   SIZE   LIMIT     USED     FREE      REQ FAIL SLEEP XDOM
kstack_cache:         16384,      0,    1115,       8, 2889248,   0,   0,   0
buffer arena-40:       4096,      0,       0,       0,       0,   0,   0,   0
buffer arena-81:       8192,      0,       0,       0,       0,   0,   0,   0
buffer arena-12:      12288,      0,       0,       0,       0,   0,   0,   0
buffer arena-16:      16384,      0,       0,       0,       0,   0,   0,   0
buffer arena-20:      20480,      0,       0,       0,       0,   0,   0,   0
buffer arena-24:      24576,      0,       0,       0,       0,   0,   0,   0
buffer arena-28:      28672,      0,       0,       0,       0,   0,   0,   0
buffer arena-32:      32768,      0,       0,       0,       0,   0,   0,   0
buffer arena-36:      36864,      0,       0,       0,       0,   0,   0,   0
buffer arena-40:      40960,      0,       0,       0,       0,   0,   0,   0
buffer arena-45:      45056,      0,       0,       0,       0,   0,   0,   0
buffer arena-49:      49152,      0,       0,       0,       0,   0,   0,   0
buffer arena-53:      53248,      0,       0,       0,       0,   0,   0,   0
buffer arena-57:      57344,      0,       0,       0,       0,   0,   0,   0
buffer arena-61:      61440,      0,       0,       0,       0,   0,   0,   0
buffer arena-65:      65536,      0,       0,       0,       0,   0,   0,   0
buf free cache:         432,      0,       0,       0,       0,   0,   0,   0
vm pgcache:            4096,      0,  712973,   11258,1694742411,818154,   0,   
0
vm pgcache:            4096,      0,14816436,    2345,964592442,5801683,   0,   
0
UMA Kegs:               384,      0,     181,       2,     181,   0,   0,   0
UMA Zones:             1536,      0,     207,       2,     207,   0,   0,   0
UMA Slabs 0:             80,      0,  269838,  306106,71527043,   0,   0,   0
UMA Slabs 1:            112,      0,      10,      25,      10,   0,   0,   0
UMA Hash:               256,      0,       0,       0,       0,   0,   0,   0
2 Bucket:                32,      0,     491,    5179,69097353,11536298,   0,   
0
4 Bucket:                48,      0,      56,    4144,25859288,32812843,   0,   
0
8 Bucket:                80,      0,     458,    1942,78673748,29055145,   0,   
0
16 Bucket:              144,      0,     189,    1351,117456484,32824498,   0,  
 0
32 Bucket:              256,      0,     636,     594,84177564,14479969,   0,   
0
64 Bucket:              512,      0,     247,     497,68940986,38612846,   0,   
0
128 Bucket:            1024,      0,     198,     253,32333656,3657385,   0,   0
256 Bucket:            2048,      0,     305,      75,87338850,14766771,   0,   
0
SMR SHARED:              24,      0,       7,     152,       7,   0,   0,   0
SMR CPU:                 32,      0,       7,     152,       7,   0,   0,   0
vmem:                  1856,      0,       1,       1,       1,   0,   0,   0
vmem btag:               56,      0,   46180,   58848, 2738085, 782,   0,   0
VM OBJECT:              264,      0,  338856,   67089,127963502,   0,   0,   0
RADIX NODE:             144,      0,   75412,   88468,1939450058,   0,   0,   0
KMAP ENTRY:              96,      0,     116,       7,     134,   0,   0,   0
MAP ENTRY:               96,      0,  174120,   11352,14188028392,   0,   0,   0
VMSPACE:                616,      0,     101,     199, 3600768,   0,   0,   0
fakepg:                 104,      0,       0,     897,     534,   0,   0,   0
pcpu-4:                   4,      0,       0,       0,       0,   0,   0,   0
pcpu-8:                   8,      0,    3786,    1846,    3941,   0,   0,   0
pcpu-16:                 16,      0,      32,    2016,      32,   0,   0,   0
pcpu-32:                 32,      0,       0,       0,       0,   0,   0,   0
pcpu-64:                 64,      0,     464,     176,     464,   0,   0,   0
malloc-16:               16,      0,   18319,    3101,16262263277,   0,   0,   0
malloc-32:               32,      0,  299804,   44932,9991097643,   0,   0,   0
malloc-64:               64,      0,  313023,   59811,101804772858,   0,   0,   
0
malloc-128:             128,      0,  381797,  223044,6981136964,   0,   0,   0
malloc-256:             256,      0,95319815,    2545,1506647953,   0,   0,   0
malloc-384:             384,      0,  447995,  169695,2030118229,   0,   0,   0
malloc-512:             512,      0,     264,     808,225101773,   0,   0,   0
malloc-1024:           1024,      0,    7842,     370,5694334679,   0,   0,   0
malloc-2048:           2048,      0,    1094,      80,1097294072,   0,   0,   0
malloc-4096:           4096,      0,   21694,      22,57336038,   0,   0,   0
malloc-8192:           8192,      0,     238,      14,113543420,   0,   0,   0
malloc-16384:         16384,      0,     110,      21,87523811,   0,   0,   0
malloc-32768:         32768,      0,     143,      19,   99934,   0,   0,   0
malloc-65536:         65536,      0,      27,      20,12273255,   0,   0,   0
SLEEPQUEUE:              80,      0,    2111,     577,    2111,   0,   0,   0
kenv:                   258,      0,      22,     158,    6032,   0,   0,   0
Files:                   80,      0,    3733,    3117,370636360,   0,   0,   0
filedesc0:             1072,      0,     120,      76, 3600785,   0,   0,   0
PWD:                     40,      0,      28,    3204,11166354,   0,   0,   0
rl_entry:                40,      0,    1727,    2111,    8133,   0,   0,   0
rangeset pctrie nodes:  144,      0,       0,       0,       0,   0,   0,   0
TURNSTILE:              136,      0,    2111,     325,    2111,   0,   0,   0
lkpicurr:               168,      0,     108,    3300,   17053,   0,   0,   0
lkpimm:                  56,      0,      22,    3578,    4779,   0,   0,   0
umtx pi:                 96,      0,       0,       0,     618,   0,   0,   0
umtx_shm:                88,      0,   31086,     792,   32519,   0,   0,   0
ertt:                    72,      0,     144,    1200,  931093,   0,   0,   0
ertt_txseginfo:          40,      0,      54,    2774,113973062,   0,   0,   0
swrbuf:                2360,    128,       0,       0,       0,   0,   0,   0
swwbuf:                2360,     64,       0,       0,       0,   0,   0,   0
nfspbuf:               2360,    128,       0,       0,       0,   0,   0,   0
vnpbuf:                2360,    512,       0,       0,       0,   0,   0,   0
clpbuf:                2360,    128,       0,       0,       0,   0,   0,   0
pbuf:                  2360,     16,       0,     785,       0,   0,   0,   0
FPU_save_area:          832,      0,    1117,     278,14648839,   0,   0,   0
MAC labels:              40,      0,       0,       0,       0,   0,   0,   0
PROC:                  1376,      0,     119,     123, 3600784,   0,   0,   0
PGRP:                   120,      0,      55,    1133,  111871,   0,   0,   0
THREAD:                1824,      0,    1115,     995, 2889248,   0,   0,   0
cpuset:                 200,      0,      23,      73,      23,   0,   0,   0
domainset:               40,      0,       0,       0,       0,   0,   0,   0
audit_record:          1280,      0,       0,       0,       0,   0,   0,   0
mbuf_packet:            256,      0,      21,    2267,19042936385,   0,   0,   0
mbuf:                   256,25280641,     258,    2794,13589972883,   0,   0,   
0
mbuf_cluster:          2048,3950100,    2288,      50,29069333,   0,   0,   0
mbuf_jumbo_page:       4096,1975050,     256,      68,128761798,   0,   0,   0
mbuf_jumbo_9k:         9216, 585200,       0,       0,       0,   0,   0,   0
mbuf_jumbo_16k:       16384, 329175,       0,       0,       0,   0,   0,   0
epoch_record pcpu:      256,      0,       4,      12,       4,   0,   0,   0
ttyinq:                 160,      0,     330,     595,  280650,   0,   0,   0
ttyoutq:                256,      0,     176,     544,  149681,   0,   0,   0
IOMMU_MAP_ENTRY:        104,      0,       0,       0,       0,   0,   0,   0
g_bio:                  376,      0,       0,     380,1242319081,   0,   0,   0
DEVCTL:                1024,   1000,       0,     100,   38170,   0,   0,   0
linux_dma_pctrie:       144,      0,       0,       0,       0,   0,   0,   0
linux_dma_object:        32,      0,       0,       0,       0,   0,   0,   0
vtnet_tx_hdr:            24,      0,       0,     168,       0,   0,   0,   0
cryptop:                280,      0,       0,       0,       0,   0,   0,   0
taskq_zone:             160,      0,       0,     672,93371079,   0,   0,   0
VNODE:                  448,      0,  432925,   65657,39478303,   0,   0,   0
BUF TRIE:               144,      0,       0,  105952,       0,   0,   0,   0
S VFS Cache:            104,      0,  478789,  177464,22337905,   0,   0,   0
STS VFS Cache:          144,      0,       0,       0,       0,   0,   0,   0
L VFS Cache:            320,      0,   66696,     312, 2207042,   0,   0,   0
LTS VFS Cache:          360,      0,       0,       0,       0,   0,   0,   0
NAMEI:                 1024,      0,       0,     148,360710630,   0,   0,   0
NCLNODE:                608,      0,       0,       0,       0,   0,   0,   0
TMPFS node:             232,      0,       0,       0,       0,   0,   0,   0
DIRHASH:               1024,      0,       0,       0,       0,   0,   0,   0
pipe:                   728,      0,     125,     150, 2570926,   0,   0,   0
AIO:                    208,      0,       0,       0,       0,   0,   0,   0
AIOCB:                  552,      0,       0,       0,       0,   0,   0,   0
AIOLIO:                 272,      0,       0,       0,       0,   0,   0,   0
Mountpoints:           2816,      0,      13,      19,      13,   0,   0,   0
zfs_btree_leaf_cache:  4096,      0,     146,      11,61811751,   0,   0,   0
metaslab_alloc_trace_cache:72,      0,       0,       0,       0,   0,   0,   0
brt_entry_cache:         40,      0,       0,       0,       0,   0,   0,   0
brt_pending_entry_cache:160,      0,       0,       0,       0,   0,   0,   0
ddt_cache:            24824,      0,      15,       1,      15,   0,   0,   0
ddt_entry_cache:        392,      0,       0,       0,       0,   0,   0,   0
zio_cache:             1216,      0,      12,     658,1828219406,   0,   0,   0
zio_link_cache:          48,      0,       0,    3108,1587694972,   0,   0,   0
zio_buf_comb_512:       512,      0,    5236,    3012,268720537,   0,   0,   0
zio_buf_comb_1024:     1024,      0,    3556,    2228, 4439688,   0,   0,   0
zio_buf_comb_1536:     1536,      0,    1238,     912, 4376931,   0,   0,   0
zio_buf_comb_2048:     2048,      0,    1361,     383, 1999204,   0,   0,   0
zio_buf_comb_2560:     2560,      0,    1922,     712, 1477853,   0,   0,   0
zio_buf_comb_3072:     3072,      0,    1111,     613, 1274204,   0,   0,   0
zio_buf_comb_3584:     3584,      0,     504,     664,  947077,   0,   0,   0
zio_buf_comb_4096:     4096,      0,   35633,       9,107240290,   0,   0,   0
zio_buf_comb_5120:     5120,      0,       0,      12, 1852613,   0,   0,   0
zio_buf_comb_6144:     6144,      0,       3,      12, 2457519,   0,   0,   0
zio_buf_comb_7168:     7168,      0,       4,      16, 1226403,   0,   0,   0
zio_buf_comb_8192:     8192,      0,       1,      19, 4642421,   0,   0,   0
zio_buf_comb_10240:   10240,      0,       1,      15, 2380313,   0,   0,   0
zio_buf_comb_12288:   12288,      0,       1,      18, 2651591,   0,   0,   0
zio_buf_comb_14336:   14336,      0,       1,      13, 1751177,   0,   0,   0
zio_buf_comb_16384:   16384,      0,   20949,      19,45535358,   0,   0,   0
zio_buf_comb_20480:   20480,      0,       3,      23, 1795355,   0,   0,   0
zio_buf_comb_24576:   24576,      0,       4,      19, 1490937,   0,   0,   0
zio_buf_comb_28672:   28672,      0,       0,      20, 1472102,   0,   0,   0
zio_buf_comb_32768:   32768,      0,       1,      15, 1365859,   0,   0,   0
zio_buf_comb_40960:   40960,      0,       5,      16, 2490238,   0,   0,   0
zio_buf_comb_49152:   49152,      0,       1,      20, 2897326,   0,   0,   0
zio_buf_comb_57344:   57344,      0,       2,      21, 2813819,   0,   0,   0
zio_buf_comb_65536:   65536,      0,       0,      19, 2859485,   0,   0,   0
zio_buf_comb_81920:   81920,      0,       5,      19, 7234072,   0,   0,   0
zio_buf_comb_98304:   98304,      0,       1,      21, 7632554,   0,   0,   0
zio_buf_comb_114688: 114688,      0,       1,      19, 1202307,   0,   0,   0
zio_buf_comb_131072: 131072,      0,     637,      25,78797612,   0,   0,   0
zio_buf_comb_163840: 163840,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_196608: 196608,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_229376: 229376,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_262144: 262144,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_327680: 327680,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_393216: 393216,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_458752: 458752,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_524288: 524288,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_655360: 655360,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_786432: 786432,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_917504: 917504,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_1048576:1048576,      0,       0,       0,      16,   0,   0,   0
zio_buf_comb_1310720:1310720,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_1572864:1572864,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_1835008:1835008,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_2097152:2097152,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_2621440:2621440,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_3145728:3145728,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_3670016:3670016,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_4194304:4194304,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_5242880:5242880,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_6291456:6291456,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_7340032:7340032,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_8388608:8388608,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_10485760:10485760,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_12582912:12582912,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_14680064:14680064,      0,       0,       0,       0,   0,   0,   0
zio_buf_comb_16777216:16777216,      0,       0,       0,       0,   0,   0,   0
abd_chunk:             4096,      0,  181139,      19,274889797,   0,   0,   0
sa_cache:               256,      0,  432803,   83287,16930228,   0,   0,   0
dnode_t:                808,      0,  487359,  142371,13704488,   0,   0,   0
arc_buf_hdr_t_full:     232,      0,   95561,   82310,137339674,   0,   0,   0
arc_buf_hdr_t_l2only:    96,      0,       0,       0,       0,   0,   0,   0
arc_buf_t:               32,      0,   21661,   40205,172520747,   0,   0,   0
dmu_buf_impl_t:         304,      0,  462405,  193562,175174835,   0,   0,   0
zil_lwb_cache:          392,      0,       4,     516, 2222721,   0,   0,   0
zil_zcw_cache:           80,      0,       0,    1050, 5203517,   0,   0,   0
sio_cache_0:            136,      0,       0,       0,       0,   0,   0,   0
sio_cache_1:            152,      0,       0,       0,       0,   0,   0,   0
sio_cache_2:            168,      0,       0,       0,       0,   0,   0,   0
zfs_znode_cache:        464,      0,  432803,   60149,16927242,   0,   0,   0
ksiginfo:               112,      0,     222,    1650,11683143,   0,   0,   0
itimer:                 352,      0,       0,       0,       0,   0,   0,   0
KNOTE:                  160,      0,    2456,     619,2448876795,   0,   0,   0
netlink:               2048,      0,       0,       0,      87,   0,   0,   0
socket:                 960,2027688,     481,     123,41432023,   0,   0,   0
IPsec SA lft_c:          16,      0,       0,       0,       0,   0,   0,   0
unpcb:                  256,2027688,     275,     385,22674412,   0,   0,   0
ripcb:                  392,      0,       0,     216,     110,   0,   0,   0
ripcb ports:             32,      0,       0,       0,       0,   0,   0,   0
tcp_inpcb:             1304,      0,     144,      75,  931093,   0,   0,   0
tcp_inpcb ports:         32,      0,      19,    2627,  659782,   0,   0,   0
udp_inpcb:              424,      0,      61,     299,17807838,   0,   0,   0
udp_inpcb ports:         32,      0,      46,    2726,  378509,   0,   0,   0
udplite_inpcb:          424,      0,       0,       0,       0,   0,   0,   0
udplite_inpcb ports:     32,      0,       0,       0,       0,   0,   0,   0
routing nhops:          256,      0,      25,     500,   18526,   0,   0,   0
tcpreass:                48, 246881,       0,    1344,  832541,   0,   0,   0
tcp_log:                408,5000000,       0,       0,       0,   0,   0,   0
tcp_log_id_bucket:      176,      0,       0,       0,       0,   0,   0,   0
tcp_log_id_node:        120,      0,       0,       0,       0,   0,   0,   0
rtentry:                168,      0,      37,     515,   18526,   0,   0,   0
ipq:                     56,  51200,       0,    1296,      27,   0,   0,   0
syncache:               168,  15360,       0,     504,  270112,   0,   0,   0
hostcache:               64,  15360,      37,    3113,   21445,   0,   0,   0
sackhole:                32,      0,       0,    1638,  224413,   0,   0,   0
tfo:                      4,      0,       0,       0,       0,   0,   0,   0
tfo_ccache_entries:      80,      0,       0,       0,       0,   0,   0,   0
ada_ccb:                272,      0,       0,     308,249588290,   0,   0,   0
da_ccb:                 536,      0,       0,       0,       0,   0,   0,   0
swpctrie:               144,7900228,       0,       0,       0,   0,   0,   0
swblk:                  136,7900209,       0,       0,       0,   0,   0,   0
drm_sched_fence:        184,      0,95277854,     952,2515357481,   0,   0,   0
amdgpu_sync:             24,      0,      42,    3030,6636376865,   0,   0,   0
amdgpu_fence:            72,      0,95277874,    1486,2560086460,   0,   0,   0
NetGraph items:          72,   4096,       0,       0,       0,   0,   0,   0
NetGraph data items:     72,   4096,       0,       0,       0,   0,   0,   0
[code]
 
I have 64GB of memory and I'm running at least 50 tabs in Firefox consistently. I don't think the problem is FreeBSD memory management, though I do agree something is going on with Wired memory. The obvious question is how is Wired memory determined?

Code: 
root@upsilon:/home/kwill # top -o res -d 1

last pid: 22229;  load averages:  0.34,  0.33,  0.28                                               up 2+14:12:26  01:57:27
138 processes: 1 running, 137 sleeping
CPU:  0.7% user,  0.0% nice,  0.3% system,  0.3% interrupt, 98.7% idle
Mem: 2265M Active, 26G Inact, 1818M Laundry, 15G Wired, 393K Buf, 17G Free
ARC: 12G Total, 9663M MFU, 2004M MRU, 3620K Anon, 86M Header, 252M Other
     11G Compressed, 19G Uncompressed, 1.71:1 Ratio
Swap: 32G Total, 32G Free

  PID USERNAME    THR PRI NICE   SIZE    RES STATE    C   TIME    WCPU COMMAND
 2777 kwill       197  21    0    15G  7359M select  15  85:26   1.76% firefox
 2803 kwill        34  20    0  5340M  2634M select  10  35:30   0.88% firefox
 2804 kwill        30  20    0  4689M  1959M select  14   5:01   0.00% firefox
22197 kwill        29  20    0  4651M  1919M select   6   0:20   0.00% firefox
 2782 kwill        29  20    0    25G  1835M select  11  20:19   0.00% firefox
 2791 kwill        31  20    0  4193M  1592M select   5   9:13   0.00% firefox
18866 kwill        32  20    0  3916M  1371M select  15   4:55   0.00% firefox
 2802 kwill        27  20    0  3619M  1209M select   3   7:10   0.00% firefox
 2812 kwill        31  20    0  3584M   942M select   1  15:10   0.00% firefox
 2426 root          3  20    0    25G   914M select   2  77:51   0.00% Xorg
 2780 kwill        28  20    0  3242M   699M select   5   7:27   0.00% firefox
 2813 kwill        29  20    0  3133M   679M select   5  15:09   0.00% firefox
 2809 kwill        28  20    0  2977M   545M select  13   3:41   0.00% firefox
 2781 kwill         5  20    0   853M   538M select  15  15:10   0.00% firefox
 2815 kwill        28  20    0  2912M   483M select  15   1:37   0.00% firefox
22032 kwill        28  20    0  2881M   479M select   2   0:07   0.00% firefox
 
I have small post-processing script for vmstat -z, it multiplies SIZE and USED columns to get memory use in bytes and that sort by that.
According to the script here are 3 top wired memory consumers:
6860006928amdgpu_fence
17531125136drm_sched_fence
24401872640malloc-256
 
So, quite a lot of that memory is used by amdgpu_fence and drm_sched_fence UMA zones.
That's obviously graphics related stuff.
I suspect that there is some memory leak, there should not be that many fence objects.

The top one is malloc-256.
Since that is a malloc zone, there should be a matching line (reporting multi-gigabyte use) in vmstat -m output.
And here it is:
Jason_25 said:
lkpikmalloc 95M 23G 31G 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64K
Click to expand...
So, we can tell that those are 129-256 byte malloc allocations with "lkpikmalloc" tag.
lkpi stands for Linux KPI, so it's very likely also graphics related.
And also very likely to be a leak.
 
Andriy said:
lkpi stands for Linux KPI, so it's very likely also graphics related.
Click to expand...
Jason_25, as it now seems to be graphics related, it is important that you are using the latest and appropriate version of the relevant graphics driver.

Please post:
- which graphics driver: pkg query -x '[%R] %n %v' '^drm(-|-510-|-515-|-61-)kmod'
- what OS: freebsd-version -kru
- which Xorg driver: modesetting (default) or other

For information about the FreeBSD-kmods, see thread, message #66 and subsequent messages.

Below, a list of versions numbers is shown for some common graphics drivers using the Linux KPI on 14.2-RELEASE and 14.3-RELEASE using Latest, the highest numberrd versions are marked for each minor version:
Rich (BB code): 
- 14.2-RELEASE using Latest -
[1-0] # pkg -v; date -u
2.2.0
Wed Jun 25 13:27:47 UTC 2025
[2-0] # pkg rquery -x '[%R] %n %v' '^drm(-|-510-|-515-|-61-)kmod' | column -t
[FreeBSD]        drm-515-kmod  5.15.160.1402000_6      <- highest numbered version
[FreeBSD]        drm-61-kmod   6.1.128.1402000_5       <- highest numbered version
[FreeBSD]        drm-kmod      20250428
[FreeBSD-kmods]  drm-515-kmod  5.15.160.1402000_4
[FreeBSD-kmods]  drm-61-kmod   6.1.128.1402000_4
[3-0] # echo "- 14.3-RELEASE using Latest - "
- 14.3-RELEASE using Latest -
[4-0] # pkg rquery -x '[%R] %n %v' '^drm(-|-510-|-515-|-61-)kmod' | column -t
[FreeBSD]        drm-515-kmod  5.15.160.1402000_6
[FreeBSD]        drm-61-kmod   6.1.128.1402000_5
[FreeBSD]        drm-kmod      20250428
[FreeBSD-kmods]  drm-515-kmod  5.15.160.1403000_4      <- highest numbered version
[FreeBSD-kmods]  drm-61-kmod   6.1.128.1403000_4       <- highest numbered version
[5-0] # pkg version -t 6.1.128.1402000_5 6.1.128.1402000_4
>
[6-0] #

NOTE: strangely some package versions on 14.2R have the highest numbered version present in the FreeBSD repository and not, as expected, in the specialised FreeBSD-kmods repository. The last command ([5-0]) shows, when, for example, comparing versions numbers of drm-61-kmod on 14.2R using Latest:
  1. [FreeBSD] drm-61-kmod 6.1.128.1402000_5
  2. [FreeBSD-kmods] drm-61-kmod 6.1.128.1402000_4
that the [FreeBSD] has indeed the highest version number.

Based on the current situation as shown above, I suggest you use one of the following, depending if you need the a specifc drm-X-kmod from FreeBSD or the FreeBSD-kmods repository. For example for drm-61-kmod:
  • pkg uprade -r FreeBSD drm-61-kmod
    - on 14.2_RELEASE using Latest
  • pkg uprade -r FreeBSD-kmods drm-61-kmod
    - on 14.3_RELEASE using Latest
Unfortunately this still seems necessary using pkg 2.2.0* to get a consistant result in all cases. Shown below is a command sequence for 14.2-RELEASE:
Rich (BB code): 
[0-0] # pkg -v; date -u
2.2.0
Wed Jun 25 14:16:30 UTC 2025
[1-0] # pkg query -e '%n = drm-61-kmod' '%n %v'
drm-61-kmod 6.1.128.1402000_4
[2-0] # pkg rquery -e '%n = drm-61-kmod' '[%R] %n %v'
[FreeBSD] drm-61-kmod 6.1.128.1402000_5
[FreeBSD-kmods] drm-61-kmod 6.1.128.1402000_4
[3-0] # pkg upgrade drm-61-kmod                 <- upgrade fails
Updating FreeBSD repository catalogue...
FreeBSD repository is up to date.
Updating FreeBSD-kmods repository catalogue...
FreeBSD-kmods repository is up to date.
All repositories are up to date.
Checking integrity... done (0 conflicting)
Your packages are up to date.
[4-0] # pkg upgrade -r FreeBSD drm-61-kmod
Updating FreeBSD repository catalogue...
FreeBSD repository is up to date.
FreeBSD is up to date.
Checking integrity... done (0 conflicting)
The following 1 package(s) will be affected (of 0 checked):

Installed packages to be UPGRADED:
        drm-61-kmod: 6.1.128.1402000_4 -> 6.1.128.1402000_5 [FreeBSD]

Number of packages to be upgraded: 1

Proceed with this action? [y/N]: y
[1/1] Upgrading drm-61-kmod from 6.1.128.1402000_4 to 6.1.128.1402000_5...
[1/1] Extracting drm-61-kmod-6.1.128.1402000_5: 100%
[5-0] # pkg query -e '%n = drm-61-kmod' '[%R] %n %v'
[FreeBSD] drm-61-kmod 6.1.128.1402000_5
[6-0] #


Alternatively: Building the desired drm-X-kmod on either 14.2R or 14.3R yourself should get you the highest numbered version specifically matched to your kernel version, that is: specific to your minor version.

___
* ports-mgmt/pkg: update to 2.2.0 - 2025-06-18 06:43:32
 
pkg query -x '[%R] %n %v' '^drm(-|-510-|-515-|-61-)kmod': - 2022 looks kind of old.
Code: 
[FreeBSD] drm-510-kmod 5.10.163_9
[FreeBSD] drm-kmod 20220907_1

freebsd-version -kru: - I am a little behind on my updates but this has been happening for a while.
Code: 
14.1-RELEASE-p5
14.1-RELEASE-p5
14.1-RELEASE-p6

uname -a: - This is the version I am actually running. Sure I can update but it will not help.
FreeBSD TRITON 14.1-RELEASE-p5 FreeBSD 14.1-RELEASE-p5 GENERIC amd64

Xorg Driver: - I have been using modesetting on different systems as the "standard" driver.
Code: 
[728775.791] (II) modeset(0): [DRI2] Setup complete
[728775.791] (II) modeset(0): [DRI2]   DRI driver: radeonsi
[728775.791] (II) modeset(0): [DRI2]   VDPAU driver: radeonsi

VladiBG:​

I do not use swap on my systems to preserve SSD life.

Andriy:​

It is a privilege that you would take the time to help. It is cool to see someone drill down and find the problem like that. Also great that I know where to look now when things start to slow down. Check this out:
Problem system (workstation) - running extreme slow - 14.1-RELEASE-P5 - uptime 115 days:
Code: 
lkpikmalloc  96M   23G  31G
Control system (media) - running decently - 14.1-RELEASE - uptime 119 days:
Code: 
lkpikmalloc  13k   45M  3.7G
The systems have identical hardware and only a slight difference in FreeBSD version. The media system can have it's memory filled up and need to be restarted as well. But it is running ok right now.

I am going to try to remove the amdgpu module from memory and cross my fingers. If that does not work I will reboot for the time being. I may need to do some driver specific software updates here.
 
Back up and running now after a reboot. The system seems to have crashed after unloading amdgpu. I even put a sleep 30 and then kldload amdgpu and it never came back. Did not respond to ctrl-alt-del. There was some brief drive activity after pressing the power button but it never did shutdown so I reset.

I found a low power system that I can load up with 128GB RAM. One of those Minisforum motherboards with a super fast mobile Ryzen processor soldered to it. I may just upgrade to that instead of compiling stuff that is probably not going to work anyway.
 
Jason_25 said:
The Problem with Falkon is only a symptom of a greater problem with memory management in FreeBSD unfortunately.
Click to expand...
I realize NetFlix does not run stock -RELEASE FreeBSD, but they, and way too many other companies and people are using the OS. I'm of the opinion that it's memory management is actually pretty darn good.


Jason_25 said:
I do not use swap on my systems to preserve SSD life.
Click to expand...
I've never heard or read this comment before. I have read that real-time video transcoding can be hard on SSD, but not swap. I just did a www search and now I see I have some reading to do. Or just buy more ram, even if its wasted. :)

Thank you.
 
PacketMan said:
I've never heard or read this comment before. I have read that real-time video transcoding can be hard on SSD, but not swap.
Click to expand...
Frequent swap use (too many apps using more RAM than physically exists), is frequent read/write to the SSD for the extra RAM. Having an excess of system RAM isn't a bad idea to avoid swap use.
 
1 week of uptime now with this output (I will post the full line this time):
Code: 
lkpikmalloc  11k   12M 1.6G 16,32,64,128,256,384,512,1K,2K,4K,8K,16K,32K,64K
Everything is fine and should remain fine for about the next 3 months.

I have received the Minisforum motherboard and assembled it into another laptop chassis I made a while ago and it works well. I was able to limit the CPU to 15w power usage and I was suprised it was able to go down that low without crashing or something. Power draw is around .7A at 13.8V in BIOS. This monster 5.5ghz CPU with 64MB cache could run in your pocket if it was a little smaller. Stock power draw was around 3.7A at 13.8V in BIOS and heat was out of control.

Right now it is running with a 16GB stick for testing and troubleshooting but I have just ordered the 128GB SODIMM kit so I am quite serious about this. This much memory is unofficially supported so if it does not work I will order a Gigabyte AORUS mini ITX desktop CPU board and put like a 8600G and 128GB of UDIMMs in it. An affordable desktop CPU like that would be a downgrade though compared to this high end laptop CPU.

I hope that the storage configuration will be 3 x m.2 drives with 1 of the drives plugged into a converter I ordered that converts m.2 into "e-key" or something like that. I understand that PCI-E 4 and 5 even under 1x speed will be very fast so this should not be a bottleneck and will be an ultra fast CPU mini system with 128GB RAM and triple redundant ZFS storage. I will keep the old Ryzen 2400GE system just as it is with it's 1 x m.2 and 2 x sata as a backup system.
 
You must log in or register to reply here.
Back
Top