Messages in this thread | | | Date | Mon, 08 Jun 2009 12:20:15 -0500 | From | Larry Finger <> | Subject | Re: [Bug #13319] Page allocation failures with b43 and p54usb |
| |
KAMEZAWA Hiroyuki wrote: > On Sun, 07 Jun 2009 11:35:27 -0500 > Larry Finger <Larry.Finger@lwfinger.net> wrote: > >> Pekka Enberg wrote: >>> On Sun, Jun 7, 2009 at 5:19 PM, Rik van Riel <riel@redhat.com> wrote: >>>> That is a very strange trace. The Mem-Info indicates >>>> that the system has more than enough memory free, and >>>> also enough memory in higher-order free blocks. >>>> >>>> This would indicate a bug somewhere in the page >>>> allocator - this memory should have been given to this >>>> allocation request. >>> Aha, I always have difficulties deciphering the traces. But lets >>> invite Mel to the party then! >> I'm happy to see some action on this problem. As usual, I'm happy to >> test patches and/or provide diagnostic output. >> > One question. > > Did your system fragmented in same way as to this > (see DMA32, 10052 of order-0 pages) in older kernel ? I think you can check > fragmentation status via /proc/buddyinfo. > = > kernel: Node 0 DMA: 3*4kB 3*8kB 5*16kB 2*32kB 4*64kB 1*128kB 2*256kB 0*512kB > 1*1024kB 0*2048kB 0*4096kB = 2100kB > kernel: Node 0 DMA32: 10062*4kB 1*8kB 1*16kB 0*32kB 1*64kB 1*128kB 0*256kB > 1*512kB 0*1024kB 0*2048kB 0*4096kB = 40976kB > ==
The current system has not been up very long and does not show the fragmentation:
finger@larrylap:~/wireless-testing> cat /proc/buddyinfo Node 0, zone DMA 4 5 4 2 4 1 2 0 1 0 0 Node 0, zone DMA32 261 78 46 55 61 54 37 17 14 12 262
After I did a git pull and a kernel build with the sources on an NFS-mounted volume, the fragmentation increased:
Node 0, zone DMA 4 5 4 2 4 1 2 0 1 0 0 Node 0, zone DMA32 2213 1924 1292 705 285 81 25 8 5 4 141
After a git pull and a kernel build on a second NFS-mounted tree:
Node 0, zone DMA 4 5 4 2 4 1 2 0 1 0 0 Node 0, zone DMA32 3127 3058 1989 756 401 142 56 14 5 3 12
Larry
| |