Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*2\.6\.0\-test11\:\s+dst_cache_overflow\s+causing\s+unresponsive\s+box\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*2\.6\.0\-test11\:\s+dst_cache_overflow\s+causing\s+unresponsive\s+box\s*$/: 12 ]

Total 12 documents matching your query.

1. 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "Francois Baligant" <francois@xxxxxxxxxxxx>; Date: Tue, 2 Dec 2003 02:32:17 +0100; We have a problem with a box running 2.6.0-test11-mjb1 and supporting around 90k simultaneous TCP connection. After a few hours/days of running, when a lots of clients connects/disconnects, the conso; /archives/netdev/2003-12/msg00025.html (11,211 bytes)
2. 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Tue, 2 Dec 2003 11:44:31 +0100; No experience with 90k TCP-flows but it seems GC is not able to free some the dst-entries for some reason. This will slowly kill your box with symptoms you describe. We have ask TCP-experts for timer; /archives/netdev/2003-12/msg00033.html (9,741 bytes)
3. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxx>; Date: Tue, 2 Dec 2003 03:26:06 -0800; Let us assume, for the sake of back of the envelope calculations, that all 90k TCP connections speak to unique destinations. Let us further assume that all of them have at least one packet in flight.; /archives/netdev/2003-12/msg00035.html (9,575 bytes)
4. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 02 Dec 2003 07:47:03 -0500; With that many flows the neighbor cache gc may also be killing him. cheers, jamal; /archives/netdev/2003-12/msg00038.html (8,613 bytes)
5. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Tue, 2 Dec 2003 18:56:27 +0100; Yes better tuning as gc_thresh and max_size is in better balance but max_size is same so I'll guess we collect unreclaimable entries util we see dst overflow still'. The long time before overflow is; /archives/netdev/2003-12/msg00040.html (9,922 bytes)
6. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "Francois Baligant" <francois@xxxxxxxxxxxx>; Date: Wed, 3 Dec 2003 01:15:42 +0100; Thanks all for your suggestions. Actually I have noticed that with 90k establish TCP sessions, I have around the double amount of entries in the routing cache. For each TCP session there is an inboun; /archives/netdev/2003-12/msg00060.html (10,638 bytes)
7. 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "Francois Baligant" <francois@xxxxxxxxxxxx>; Date: Tue, 2 Dec 2003 02:32:17 +0100; We have a problem with a box running 2.6.0-test11-mjb1 and supporting around 90k simultaneous TCP connection. After a few hours/days of running, when a lots of clients connects/disconnects, the conso; /archives/netdev/2003-12/msg00424.html (11,226 bytes)
8. 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Tue, 2 Dec 2003 11:44:31 +0100; No experience with 90k TCP-flows but it seems GC is not able to free some the dst-entries for some reason. This will slowly kill your box with symptoms you describe. We have ask TCP-experts for timer; /archives/netdev/2003-12/msg00432.html (9,881 bytes)
9. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxx>; Date: Tue, 2 Dec 2003 03:26:06 -0800; Let us assume, for the sake of back of the envelope calculations, that all 90k TCP connections speak to unique destinations. Let us further assume that all of them have at least one packet in flight.; /archives/netdev/2003-12/msg00434.html (9,711 bytes)
10. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 02 Dec 2003 07:47:03 -0500; With that many flows the neighbor cache gc may also be killing him. cheers, jamal; /archives/netdev/2003-12/msg00437.html (8,790 bytes)
11. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Tue, 2 Dec 2003 18:56:27 +0100; Yes better tuning as gc_thresh and max_size is in better balance but max_size is same so I'll guess we collect unreclaimable entries util we see dst overflow still'. The long time before overflow is; /archives/netdev/2003-12/msg00439.html (10,099 bytes)
12. Re: 2.6.0-test11: dst_cache_overflow causing unresponsive box (score: 1): Author: "Francois Baligant" <francois@xxxxxxxxxxxx>; Date: Wed, 3 Dec 2003 01:15:42 +0100; Thanks all for your suggestions. Actually I have noticed that with 90k establish TCP sessions, I have around the double amount of entries in the routing cache. For each TCP session there is an inboun; /archives/netdev/2003-12/msg00459.html (10,778 bytes)

Current List: 1 - 12
Page: [1]