Hi there, On an embedded network device, while traffic passes on, I execute some command (my APP) to get some network statistic information, then oom-killer kicks in. >From the message, several processes invoke oom-killer in order: 1) inetd 2) klogd 3) my daemon APP After each oom-killer is invoked, memory info dumps. But the data in this memory info are almost the same after each oom-killer is invoked as follows: Mem-info: DMA per-cpu: CPU 0: Hot: hi: 0, btch: 1 usd: 0 Cold: hi: 0, btch: 1 usd: 0 Active:5309 inactive:1454 dirty:0 writeback:0 unstable:0 free:180 slab:307 mapped:16 pagetables:36 DMA free:720kB min:720kB low:900kB high:1080kB active:21236kB inactive:5816kB present:32512kB pages_scanned:44241 all_unreclaimable? yes lowmem_reserve[]: 0 0 DMA: 0*4kB 0*8kB 1*16kB 0*32kB 1*64kB 1*128kB 0*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 720kB Free swap: 0kB 8192 pages of RAM 362 free pages 493 reserved pages 307 slab pages 40 pages shared 0 pages swap cached Out of Memory: Kill process 429 (sh) score 297 and children. Out of memory: Killed process 429 (sh). When the box works normmally, there are about 18M bytes memory left. >From the above message, it seems only 362 free pages(about 1.2M) memory left. How to find out which process eat up the memory? Any clues? Jeffrey -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx Please read the FAQ at http://kernelnewbies.org/FAQ
