| To: | Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: Fw: Re: 2.6.12-rc2-mm2 |
| From: | Indrek Kruusa <indrek.kruusa@xxxxxxxxxxx> |
| Date: | Sat, 09 Apr 2005 19:14:20 +0300 |
| Cc: | Andrew Morton <akpm@xxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <E1DK25V-0005Ye-00@xxxxxxxxxxxxxxxxxxxxxxxx> |
| References: | <E1DK25V-0005Ye-00@xxxxxxxxxxxxxxxxxxxxxxxx> |
| Reply-to: | indrek.kruusa@xxxxxxxxxxx |
| Sender: | netdev-bounce@xxxxxxxxxxx |
| User-agent: | Mozilla Thunderbird 1.0 (X11/20050215) |
Herbert Xu wrote: Wait a moment.... with kernel 2.6.10-oci7 (Sam) load average is 3-4x lower and system does not reach this tcp_max_tw_buckets limit. If it is desired I can do more tests with different kernels.Andrew Morton <akpm@xxxxxxxx> wrote:dmesg is not clean though: TCP: time wait bucket table overflow TCP: time wait bucket table overflow TCP: time wait bucket table overflow printk: 392 messages suppressed. What I did: - "bombing" httpd with JMeter (from another computer)This is normal. The number of TCP connections held by your server in the TIME_WAIT state is exceeding tcp_max_tw_buckets. Check out tcp(7) on what this means and how it may or may not be a problem for you. Indrek |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH] NETLINK_UESTABLISHED notifier event, Dmitry Yusupov |
|---|---|
| Next by Date: | [-mm patch] net/ieee80211/ieee80211_tx.c: swapped memset arguments, Adrian Bunk |
| Previous by Thread: | Re: Fw: Re: 2.6.12-rc2-mm2, Indrek Kruusa |
| Next by Thread: | Re: [RFC] TCP congestion schedulers, John Heffner |
| Indexes: | [Date] [Thread] [Top] [All Lists] |