lkml.org 
[lkml]   [1997]   [May]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: 2.1.40 nfs serving is foobar.
Date
From

Very interesting...

It repeatable to an NFS server on a sequest disk.

Whenever I cat /proc/slabinfo, it goes for a while...then stops
again...sometimes it goes by itself and then stops

(I'm doing tar -czvf <NFS>/mnt/Mail.tar.gz Mail

so its easy to see when it stopsss

The nfs server 2.1.40 on a 486.

: leisner@compaq;cat /proc/slabinfo
slabinfo - version: 1.0
kmem_cache 22 42
tcp_open_request 0 36
sock 56 60
filp 96 100
inode 4096 4110
buffer_head 3752 7150
mm_struct 23 36
vm_area_struct 255 315
uid_cache 3 127
size-131072 0 0
size-65536 0 0
size-32768 0 0
size-16384 0 72
size-8192 27 32
size-4096 13 16
size-2048 0 16
size-1024 29 40
size-512 10 16
size-256 16 42
size-128 40 56
size-64 138 150
size-32 206 252
slab_cache 101 168
: leisner@compaq;cat /proc/slabinfo
slabinfo - version: 1.0
kmem_cache 22 42
tcp_open_request 0 36
sock 56 60
filp 96 100
inode 4096 4110
buffer_head 3454 7150
mm_struct 23 36
vm_area_struct 255 315
uid_cache 3 127
size-131072 0 0
size-65536 0 0
size-32768 0 0
size-16384 0 84
size-8192 27 32
size-4096 13 16
size-2048 0 16
size-1024 29 40
size-512 10 16
size-256 16 42
size-128 40 56
size-64 138 150
size-32 218 252
slab_cache 113 168
: leisner@compaq;cat /proc/slabinfo
slabinfo - version: 1.0
kmem_cache 22 42
tcp_open_request 0 36
sock 56 60
filp 96 100
inode 4096 4110
buffer_head 3026 7150
mm_struct 23 36
vm_area_struct 255 315
uid_cache 3 127
size-131072 0 0
size-65536 0 0
size-32768 0 0
size-16384 0 113
size-8192 27 32
size-4096 13 16
size-2048 0 16
size-1024 29 40
size-512 10 16
size-256 16 42
size-128 39 56
size-64 138 150
size-32 247 252
slab_cache 142 168

In message <199705291931.PAA02905@jenolan.caipgeneral>, you write:
> Date: Tue, 27 May 1997 10:13:01 PDT
> From: "Marty Leisner" <leisner@sdsp.mc.xerox.com>
>
> Running 2.1.40, backing up to a syquest disk over NFS I got:
> IP: queue_glue: no memory for gluing queue c0662de0
> IP: queue_glue: no memory for gluing queue c0662de0
> IP: queue_glue: no memory for gluing queue c0662de0
> IP: queue_glue: no memory for gluing queue c0662de0
> IP: queue_glue: no memory for gluing queue c0662de0
>
>It smells of a memory leak in the IP fragmentation code introduced by
>some cleanups I did recently. Could you, next time you see this, send
>me the output of /proc/slabinfo, this might help me verify that this
>is in fact some memory leak and it might even give me some clues as to
>precisely what is being leaked.
>
>---------------------------------------------////
>Yow! 11.26 MB/s remote host TCP bandwidth & ////
>199 usec remote TCP latency over 100Mb/s ////
>ethernet. Beat that! ////
>-----------------------------------------////__________ o
>David S. Miller, davem@caip.rutgers.edu /_____________/ / // /_/ ><

\
 
 \ /
  Last update: 2005-03-22 13:39    [W:0.048 / U:1.592 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site