On Wed, 10 Dec 2003, Ling-En Kao wrote: > > Hi > > We have a problem with oops (both 1.5.23 and the cvs version), it died > a couple hours after it has been started. > Here is the output of oops.log: > > [0x19465]run_client(): No mem for header! > [0x6b1ac]run_client(): No mem for header! > [0x9a268]fill_mem_obj(): select: timed out. > [0xbcef3]attach_data(): No mem in attach data. > [0x5795e]run_client(): No mem for header! > > There's no other messages abnormal, but sometimes with below messages > from kernel (not always): > > Dec 8 13:54:05 tproxy1 kernel: oops: page allocation failure. order:3, mode:0x20 > Dec 8 13:54:05 tproxy1 kernel: Call Trace: > Dec 8 13:54:05 tproxy1 kernel: [<c013ac0d>] __alloc_pages+0x2de/0x31c > Dec 8 13:54:05 tproxy1 kernel: [<c013ac70>] __get_free_pages+0x25/0x3f > Dec 8 13:54:05 tproxy1 kernel: [<c013e0cd>] cache_grow+0xed/0x345 > > The swap remain unused at that time. > > Tested on both kernel 2.4.23 and 2.6.0-test9-mm5, > glibc-2.2.5, gcc-3.3.2 (gcc-2.95.3 also), Debian GNU/Linux-3.0. > > The request rate varies from 100 req/s to 550 req/s. > > Any ideas what's wrong?
Memory allocations failed (that is what "No mem for header!" and "No mem in attach data" are mean). some malloc's return 0. May-be you have to increase process limits... Anyway - something wrong with memory allocations > > Thanks! > ===================================================================== > If you would like to unsubscribe from this list send message to > [EMAIL PROTECTED] with "unsubscribe oops" in message body. > Archive is accessible on http://lists.paco.net/oops-rus/ > Igor Khasilev | PACO Links, igor at paco dot net | ===================================================================== If you would like to unsubscribe from this list send message to [EMAIL PROTECTED] with "unsubscribe oops" in message body. Archive is accessible on http://lists.paco.net/oops-rus/
