Messages in this thread | | | Subject | Re: Another Linux performance anomaly with 1+ GB files | From | (Scott Laird) | Date | Wed, 12 Nov 1997 12:15:15 -0800 |
| |
In message <346A0F5B.CE471545@star.net>, Bill Hawes writes: >Scott Laird wrote: > >> The only time I've seen the slowdowns, they've occurred during a read >> from the 4k filesystem. I'm not sure if the WCHAN reported by ps is >> accurate or not, but it was reporting 1261d9, which is in the middle >> of try_to_free_buffers, according to my System.map. > >There aren't supposed to be any blocking operations in >try_to_free_buffer. Could the task perhaps be stuck in a tight loop >repeatedly calling try_to_free_buffer()? The next time it gets stuck, >try hitting alt-scroll-lock a few times to get the current address, and >then look this up your System.map. If the address is changing but >usually in try_to_free_buffer(), the system is probably looking for >memory and repeatedly trying to free buffers.
Sure. I haven't seen any problems yet with 2.1.62, but I should be able to drop back to 2.0.x either tonight or tomorrow night for a few tests. I'll see what happens then.
Scott
| |