Hi Gábor, On Fri, 2008-01-18 at 12:58 +0900, Ryusuke Konishi wrote: > > > Could you get information through the following way > > > > I attach the kernel log. Sorry for the long delay, but the machine > frooze > > during kernel recompilation, as i didn't use sysrq before. It > worked. > > Hope the information will be useful. > Great! > > I will look into both logs. > > Anyway, thanks a lot for your effort.
Your log actually gave me a great hint! The following part of the log indicates that the device mapper faced starvation of a memory pool, and was waiting for someone to make room for it. Call Trace: [mempool_alloc+28/228] mempool_alloc+0x1c/0xe4 [<c013dd7f>] mempool_alloc+0x1c/0xe4 [wait_for_completion+125/205] wait_for_completion+0x7d/0xcd [<c036c31f>] wait_for_completion+0x7d/0xcd [default_wake_function+0/12] default_wake_function+0x0/0xc [<c0114c20>] default_wake_function+0x0/0xc [<e08c711a>] nilfs_segbuf_wait+0x79/0x1d7 [nilfs2] [<e08c7268>] nilfs_segbuf_wait+0x1c7/0x1d7 [nilfs2] [<e08c75de>] nilfs_segbuf_write+0x48/0x83 [nilfs2] [<e08ca035>] nilfs_segctor_add_dirty+0x1ca3/0x259f [nilfs2] [update_curr+267/309] update_curr+0x10b/0x135 [<c0113b07>] update_curr+0x10b/0x135 [<e08ca8e0>] nilfs_segctor_add_dirty+0x254e/0x259f [nilfs2] [<e08cbd47>] nilfs_clean_segments+0x3e0/0x9ac [nilfs2] [<e08cab33>] nilfs_segctor_add_segments_to_be_freed+0x202/0x33b [nilfs2] [<e08cbbcc>] nilfs_clean_segments+0x265/0x9ac [nilfs2] [kernel_thread_helper+7/16] kernel_thread_helper+0x7/0x10 [<c0104917>] kernel_thread_helper+0x7/0x10 This seems to arise partly from the current NILFS implementation. I'll advance analysis, and would like to find a possible solution to manage this. In the meantime, you may be able to suppress the problem by avoiding use of the DM (if possible). Thanks, -- Ryusuke Konishi NILFS team NTT http://www.nilfs.org/ _______________________________________________ users mailing list [email protected] https://www.nilfs.org/mailman/listinfo/users
