touch-packages team mailing list archive
-
touch-packages team
-
Mailing list archive
-
Message #60611
[Bug 1352718] Re: Unknown memory utilization in Ubuntu14.04 Trusty
[Expired for procps (Ubuntu) because there has been no activity for 60
days.]
** Changed in: procps (Ubuntu)
Status: Incomplete => Expired
--
You received this bug notification because you are a member of Ubuntu
Touch seeded packages, which is subscribed to procps in Ubuntu.
https://bugs.launchpad.net/bugs/1352718
Title:
Unknown memory utilization in Ubuntu14.04 Trusty
Status in procps package in Ubuntu:
Expired
Bug description:
I'm running Ubuntu Trusty 14.04 on a new machine with 8GB of RAM, and
it seems to be locking up periodically and nothing is in syslog file.
I've installed Nagios and have been watching the graphs, and it looks
like memory is going high from 7% to 72% in just a span of 10 mins.
Only node process are running on server. In top I found all process
are running very normal memory consumption. Even after stopping node
process. Memory remains with same utilization.
free agrees, claiming I'm using more than 5.7G of memory:
free -h
total used free shared buffers cached
Mem: 7.8G 6.5G 1.3G 2.2M 233M 612M
-/+ buffers/cache: 5.7G 2.1G
Swap: 2.0G 0B 2.0G
However, I'm having trouble determining what exactly is eating all of that memory. Running top or htop doesn't seem to single anything out, and ps_mem.py (https://raw.github.com/pixelb/ps_mem/master/ps_mem.py) claims that I'm using much less than the system thinks...
...
Private + Shared = RAM used Program
184.0 KiB + 29.5 KiB = 213.5 KiB atd
176.0 KiB + 48.5 KiB = 224.5 KiB acpid
164.0 KiB + 99.5 KiB = 263.5 KiB anvil
272.0 KiB + 52.0 KiB = 324.0 KiB upstart-file-bridge
288.0 KiB + 76.0 KiB = 364.0 KiB cron
312.0 KiB + 60.0 KiB = 372.0 KiB irqbalance
208.0 KiB + 188.0 KiB = 396.0 KiB sh (2)
328.0 KiB + 87.5 KiB = 415.5 KiB upstart-udev-bridge
312.0 KiB + 104.5 KiB = 416.5 KiB log
424.0 KiB + 53.5 KiB = 477.5 KiB upstart-socket-bridge
304.0 KiB + 213.5 KiB = 517.5 KiB pickup
336.0 KiB + 213.5 KiB = 549.5 KiB qmgr
396.0 KiB + 165.5 KiB = 561.5 KiB dovecot
360.0 KiB + 205.5 KiB = 565.5 KiB master
528.0 KiB + 52.5 KiB = 580.5 KiB nrpe
608.0 KiB + 148.5 KiB = 756.5 KiB systemd-logind
764.0 KiB + 61.5 KiB = 825.5 KiB dbus-daemon
772.0 KiB + 107.0 KiB = 879.0 KiB top
808.0 KiB + 87.5 KiB = 895.5 KiB systemd-udevd
940.0 KiB + 147.5 KiB = 1.1 MiB ntpd
956.0 KiB + 285.0 KiB = 1.2 MiB getty (6)
1.1 MiB + 134.0 KiB = 1.2 MiB config
1.6 MiB + 121.5 KiB = 1.7 MiB init
2.5 MiB + 22.0 KiB = 2.6 MiB dhclient
2.8 MiB + 476.5 KiB = 3.3 MiB vmtoolsd
4.2 MiB + 452.5 KiB = 4.6 MiB whoopsie
5.1 MiB + 96.5 KiB = 5.2 MiB rsyslogd
3.6 MiB + 2.3 MiB = 5.9 MiB sshd (4)
6.7 MiB + 1.0 MiB = 7.7 MiB bash (3)
8.3 MiB + 277.5 KiB = 8.6 MiB redis-server (3)
13.0 MiB + 26.5 KiB = 13.0 MiB docker
342.0 MiB + 6.9 MiB = 348.9 MiB nodejs (8)
---------------------------------
414.3 MiB
=================================
This other formula for totaling the memory roughly agrees:
# ps -e -orss=,args= | sort -b -k1,1n | awk '{total = total + $1}END{print total}'
503612
If the processes only total 500 MiB, where's the rest of the memory
going?
Slabtop doesn't look like I have a huge cache or anything...
Active / Total Objects (% used) : 672886 / 681837 (98.7%)
Active / Total Slabs (% used) : 15441 / 15441 (100.0%)
Active / Total Caches (% used) : 70 / 101 (69.3%)
Active / Total Size (% used) : 179811.23K / 184282.05K (97.6%)
Minimum / Average / Maximum Object : 0.01K / 0.27K / 8.00K
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
171318 171318 100% 0.19K 4079 42 32632K dentry
127257 127257 100% 0.10K 3263 39 13052K buffer_head
75669 75669 100% 0.96K 2293 33 73376K ext4_inode_cache
35328 34959 98% 0.06K 552 64 2208K kmalloc-64
33354 33354 100% 0.04K 327 102 1308K ext4_extent_status
25560 25560 100% 0.11K 710 36 2840K sysfs_dir_cache
18944 18944 100% 0.01K 37 512 148K kmalloc-8
18848 18848 100% 0.50K 589 32 9424K kmalloc-512
17680 17680 100% 0.05K 208 85 832K shared_policy_node
17248 17248 100% 0.12K 539 32 2156K au_dinfo
15390 9116 59% 0.55K 270 57 8640K radix_tree_node
15372 15372 100% 0.09K 366 42 1464K kmalloc-96
13398 13398 100% 0.75K 319 42 10208K au_icntnr
11424 11424 100% 0.57K 204 56 6528K inode_cache
11312 11312 100% 0.07K 202 56 808K Acpi-ParseExt
11072 11072 100% 0.06K 173 64 692K ext4_free_data
7650 7650 100% 0.04K 75 102 300K Acpi-Namespace
7168 7168 100% 0.02K 28 256 112K kmalloc-16
7014 6598 94% 0.19K 167 42 1336K kmalloc-192
5984 5878 98% 0.12K 187 32 748K kmalloc-128
5504 5196 94% 0.03K 43 128 172K kmalloc-32
3328 3328 100% 0.03K 26 128 104K jbd2_revoke_record_s
3008 3008 100% 0.06K 47 64 188K anon_vma
2912 2494 85% 0.25K 91 32 728K kmalloc-256
2850 2727 95% 0.63K 57 50 1824K proc_inode_cache
1792 1792 100% 0.07K 32 56 128K ext4_io_end
1248 1176 94% 1.00K 39 32 1248K kmalloc-1024
1152 1152 100% 0.66K 24 48 768K shmem_inode_cache
1044 1044 100% 0.11K 29 36 116K jbd2_journal_head
1040 780 75% 0.30K 20 52 320K nf_conntrack_ffffffff81cda040
969 969 100% 0.62K 19 51 608K sock_inode_cache
884 624 70% 0.30K 17 52 272K nf_conntrack_ffff880036b7b000
864 672 77% 0.25K 27 32 216K tw_sock_TCP
756 756 100% 0.88K 21 36 672K mm_struct
630 630 100% 1.06K 21 30 672K signal_cache
624 540 86% 2.00K 39 16 1248K kmalloc-2048
507 507 100% 0.81K 13 39 416K task_xstate
462 462 100% 0.38K 11 42 176K blkdev_requests
378 378 100% 0.19K 9 42 72K au_finfo
365 349 95% 5.98K 73 5 2336K task_struct
364 364 100% 0.30K 7 52 112K nf_conntrack_ffff880036503000
360 360 100% 0.13K 6 60 48K ext4_allocation_context
What other tests can I do to understand my memory usage? Thanks!
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/procps/+bug/1352718/+subscriptions
