[Starlingx-discuss] Where did my RAM go?
von Hoesslin, Volker
Volker.Hoesslin at swsn.de
Thu Jun 25 09:42:51 UTC 2020
Hi!
i have real RAM problems at my worker nodes, they are equipped with 256GB RAM. unfortunately i can only use a fraction of it for my VMs and i don't understand why? maybe someone can explain to me where all the RAM went?
compute-0:~$ cat /proc/meminfo
MemTotal: 263854428 kB
MemFree: 25030424 kB
MemAvailable: 24584388 kB
Buffers: 35308 kB
Cached: 350236 kB
SwapCached: 0 kB
Active: 27306600 kB
Inactive: 236124 kB
Active(anon): 27168144 kB
Inactive(anon): 8936 kB
Active(file): 138456 kB
Inactive(file): 227188 kB
Unevictable: 5424 kB
Mlocked: 5424 kB
SwapTotal: 0 kB
SwapFree: 0 kB
Dirty: 132 kB
Writeback: 0 kB
AnonPages: 27162864 kB
Mapped: 99272 kB
Shmem: 15880 kB
Slab: 912816 kB
SReclaimable: 132552 kB
SUnreclaim: 780264 kB
KernelStack: 40256 kB
PageTables: 107948 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
CommitLimit: 27069612 kB
Committed_AS: 47150896 kB
VmallocTotal: 34359738367 kB
VmallocUsed: 823656 kB
VmallocChunk: 34224520432 kB
HardwareCorrupted: 0 kB
CmaTotal: 16384 kB
CmaFree: 2114464 kB
HugePages_Total: 200
HugePages_Free: 200
HugePages_Rsvd: 0
HugePages_Surp: 0
Hugepagesize: 1048576 kB
DirectMap4k: 18644 kB
DirectMap2M: 5122048 kB
DirectMap1G: 263192576 kB
compute-0:~$ free
total used free shared buff/cache available
Mem: 263854428 237596844 24955580 15880 1302004 24512988
Swap: 0 0 0
there are two running VMs, one is allocate 32GB and the other one 512MB but the server has only 24GB left? whats going on? this is an dual CPU system with 16x16GB slots full filled.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.starlingx.io/pipermail/starlingx-discuss/attachments/20200625/1d9e63c7/attachment.html>
More information about the Starlingx-discuss
mailing list