As a note - from taking a look at some of the linux kernel discussions,
it looks like kmalloc can be used for up to 32*pagesize bytes (128k)...
any idea why our threshold is set to just 1 page?

-- Nathan

------------------------------------------------------------
Nathan Neulinger                       EMail:  [EMAIL PROTECTED]
University of Missouri - Rolla         Phone: (573) 341-6679
UMR Information Technology             Fax: (573) 341-4216
 

> -----Original Message-----
> From: Neulinger, Nathan 
> Sent: Monday, April 12, 2004 11:02 AM
> Cc: '[EMAIL PROTECTED]'
> Subject: RE: [OpenAFS-devel] How can the mem cache possibly 
> not be able to allocate memory? 
> 
> AFS osi_alloc appears to be thresholding at MAX_KMALLOC_SIZE. 
> If <=, it uses kmalloc, otherwise vmalloc. MAX_KMALLOC_SIZE 
> is set to PAGE_SIZE.
> 
> -- Nathan
> 
> ------------------------------------------------------------
> Nathan Neulinger                       EMail:  [EMAIL PROTECTED]
> University of Missouri - Rolla         Phone: (573) 341-6679
> UMR Information Technology             Fax: (573) 341-4216
>  
> 
> > -----Original Message-----
> > From: chas williams (contractor) [mailto:[EMAIL PROTECTED] 
> > Sent: Wednesday, April 07, 2004 10:01 PM
> > To: Neulinger, Nathan
> > Cc: [EMAIL PROTECTED]
> > Subject: Re: [OpenAFS-devel] How can the mem cache possibly 
> > not be able to allocate memory? 
> > 
> > In message <[EMAIL PROTECTED]>,Nathan Neulinger writes:
> > >Apr  7 13:27:51 nic1 kernel: Memory: 4008596k/4194304k 
> > available (2244k
> > >kernel code, 53668k reserved, 1432k data, 168k init, 
> > 3145152k highmem)
> > >
> > >That just plain doesn't make any sense... I tried to give it a 75MB
> > >memcache... Is there something with how afs is trying to 
> > allocate kernel
> > >memory that would limit what it could use? 
> > 
> > well the linux kernel could be placing a limit on memory.  i 
> > would have
> > to guess that afs_osi_Alloc(memCacheBlkSize) is going to 
> > using kmalloc()
> > instead of vmalloc().  kmalloc() gets its buffer from various pools
> > viewable from /proc/slabinfo (in particular the size-NNNN 
> pools).  it
> > seems like you might be hitting a limit on the number of buffers.
> > 
> > perhaps memcache should be implemented to have it own kmem_cache.
> > 
> > 
_______________________________________________
OpenAFS-devel mailing list
[EMAIL PROTECTED]
https://lists.openafs.org/mailman/listinfo/openafs-devel

Reply via email to