lkml.org 
[lkml]   [2001]   [Oct]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Subject2.4.12-ac3 + e2defrag
Date
OK, i ran e2defrag -p 16384 on a disk thinking, hey, 128MB of buffer isn't 
anything to me since i have 770MB of ram and 128MB of swap. Well, according
to top this is e2defrag a quarter of the way running through my 20GB fs.
PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME COMMAND
12023 root 16 0 125M 76M 9304 R 22.8 10.1 5:50 e2defrag

That seems right. Yet this is the /proc/meminfo reading
total: used: free: shared: buffers: cached:
Mem: 790016000 783785984 6230016 4096 632762368 20373504
Swap: 133885952 101707776 32178176
MemTotal: 771500 kB
MemFree: 6084 kB
MemShared: 4 kB
Buffers: 617932 kB
Cached: 6176 kB
SwapCached: 13720 kB
Active: 330800 kB
Inact_dirty: 307032 kB
Inact_clean: 0 kB
Inact_target: 157272 kB
HighTotal: 0 kB
HighFree: 0 kB
LowTotal: 771500 kB
LowFree: 6084 kB
SwapTotal: 130748 kB
SwapFree: 31424 kB

So where does this 500+MB of buffer come from? It grinded the system to a
swapcrazy like state even though it wasn't swapping like crazy. From the way
it was acting i was getting scared that it might oom out and kill e2defrag
even though top seemed to show that the program was only using about 125M.
The question is, why did the kernel decide 610MB of buffers was necessary ?
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:08    [W:0.032 / U:0.168 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site