| To: | linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
|---|---|
| Subject: | What is a reasonable upper limit to the rt_hash_table. |
| From: | Robin Holt <holt@xxxxxxx> |
| Date: | Tue, 7 Dec 2004 11:25:10 -0600 |
| Sender: | netdev-bounce@xxxxxxxxxxx |
| User-agent: | Mutt/1.4.1i |
We have a system with a very large amount of memory. We are noticing pauses of approximately 5 seconds every 10 minutes. We tracked it down to rt_run_flush holding off other timer processing while it scans the rt_hash_table. The following is from the boot: IP: routing cache hash table of 33554432 buckets, 524288Kbytes This seems like an outrageously large value. I realize the 2.6 kernel has rhash_entries as a boot option. Can I get some guidance on what a reasonable upper limit would be? What is this guidance based upon? What is the reason for not making that upper limit a default and let rhash_entries override to make it larger if a site actually needed it? Thank you in advance, Robin Holt |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Hard freeze with 2.6.10-rc3 and QoS, worked fine with 2.6.9, Patrick McHardy |
|---|---|
| Next by Date: | Re: [PATCH] fix select() for SOCK_RAW sockets, Phil Oester |
| Previous by Thread: | [PATCH] PKT_SCHED: validate policer configuration TLVs, Thomas Graf |
| Next by Thread: | e1000, 2.6.9: swapper: page allocation failure. order:1, mode:0x20, Brad Fitzpatrick |
| Indexes: | [Date] [Thread] [Top] [All Lists] |