From: Mike Christie <michaelc@cs.wisc.edu>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org, Linus Torvalds <torvalds@osdl.org>,
Andrew Morton <akpm@osdl.org>, David Miller <davem@davemloft.net>,
Rik van Riel <riel@redhat.com>,
Daniel Phillips <phillips@google.com>
Subject: Re: [PATCH 20/20] iscsi: support for swapping over iSCSI.
Date: Thu, 14 Sep 2006 16:03:07 -0500 [thread overview]
Message-ID: <4509C38B.3000808@cs.wisc.edu> (raw)
In-Reply-To: <4509C2DF.8000007@cs.wisc.edu>
Mike Christie wrote:
> Peter Zijlstra wrote:
>> On Thu, 2006-09-14 at 14:22 -0500, Mike Christie wrote:
>>> Peter Zijlstra wrote:
>>>> On Wed, 2006-09-13 at 15:50 -0500, Mike Christie wrote:
>>>>> Peter Zijlstra wrote:
>>>>>> Implement sht->swapdev() for iSCSI. This method takes care of reserving
>>>>>> the extra memory needed and marking all relevant sockets with SOCK_VMIO.
>>>>>>
>>>>>> When used for swapping, TCP socket creation is done under GFP_MEMALLOC and
>>>>>> the TCP connect is done with SOCK_VMIO to ensure their success. Also the
>>>>>> netlink userspace interface is marked SOCK_VMIO, this will ensure that even
>>>>>> under pressure we can still communicate with the daemon (which runs as
>>>>>> mlockall() and needs no additional memory to operate).
>>>>>>
>>>>>> Netlink requests are handled under the new PF_MEM_NOWAIT when a swapper is
>>>>>> present. This ensures that the netlink socket will not block. User-space will
>>>>>> need to retry failed requests.
>>>>>>
>>>>>> The TCP receive path is handled under PF_MEMALLOC for SOCK_VMIO sockets.
>>>>>> This makes sure we do not block the critical socket, and that we do not
>>>>>> fail to process incomming data.
>>>>>>
>>>>>> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
>>>>>> CC: Mike Christie <michaelc@cs.wisc.edu>
>>>>>> ---
>>>>>> drivers/scsi/iscsi_tcp.c | 103 +++++++++++++++++++++++++++++++-----
>>>>>> drivers/scsi/scsi_transport_iscsi.c | 23 +++++++-
>>>>>> include/scsi/libiscsi.h | 1
>>>>>> include/scsi/scsi_transport_iscsi.h | 2
>>>>>> 4 files changed, 113 insertions(+), 16 deletions(-)
>>>>>>
>>>>>> Index: linux-2.6/drivers/scsi/iscsi_tcp.c
>>>>>> ===================================================================
>>>>>> --- linux-2.6.orig/drivers/scsi/iscsi_tcp.c
>>>>>> +++ linux-2.6/drivers/scsi/iscsi_tcp.c
>>>>>> @@ -42,6 +42,7 @@
>>>>>> #include <scsi/scsi_host.h>
>>>>>> #include <scsi/scsi.h>
>>>>>> #include <scsi/scsi_transport_iscsi.h>
>>>>>> +#include <scsi/scsi_device.h>
>>>>>>
>>>>>> #include "iscsi_tcp.h"
>>>>>>
>>>>>> @@ -845,9 +846,13 @@ iscsi_tcp_data_recv(read_descriptor_t *r
>>>>>> int rc;
>>>>>> struct iscsi_conn *conn = rd_desc->arg.data;
>>>>>> struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
>>>>>> - int processed;
>>>>>> + int processed = 0;
>>>>>> char pad[ISCSI_PAD_LEN];
>>>>>> struct scatterlist sg;
>>>>>> + unsigned long pflags = current->flags;
>>>>>> +
>>>>>> + if (sk_has_vmio(tcp_conn->sock->sk))
>>>>>> + current->flags |= PF_MEMALLOC;
>>>>>>
>>>>> Is this too late or not needed or what is it for? This function gets run
>>>>> from the network layer's softirq and at this point we have a skbuff with
>>>>> data that we want to process. The iscsi layer also does not allocate
>>>>> memory for read or write IO in this path.
>>>> I thought I found allocations in that path, lemme search...
>>>> found this:
>>>>
>>>> iscsi_tcp_data_recv()
>>>> iscsi_data_rescv()
>>>> iscsi_complete_pdu()
>>>> __iscsi_complete_pdu()
>>>> iscsi_recv_pdu()
>>>> alloc_skb( GFP_ATOMIC);
>>>>
>>> You are right that is for the netlink interface. Could we move the
>>> PF_MEMALLOC setting and clearing to iscsi_recv_pdu and and add it to
>>> iscsi_conn_error in scsi_transport_iscsi.c so that iscsi_iser and
>>> qla4xxx will have it set when they need it. I will send a patch for this
>>> along with a way to have the netlink sock vmio set for all iscsi drivers
>>> that need it.
>> I already have such a patch, look at:
>> http://programming.kicks-ass.net/kernel-patches/vm_deadlock/current/iscsi_vmio.patch
>>
>
> You are drowning me in patches :) I did not see that one. I was still
> commenting on this patch :)
>
> The new patch looks ok.
>
Oh, I think you need a sock_put to go with netlink lookup (lookup does a
hold).
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2006-09-14 21:03 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-12 15:25 [PATCH 00/20] vm deadlock avoidance for NFS, NBD and iSCSI (take 7) Peter Zijlstra
2006-09-12 15:25 ` [PATCH 16/20] iscsi: add session context to ep_connect Peter Zijlstra
2006-09-12 15:25 ` [PATCH 08/20] nfs: enable swap on NFS Peter Zijlstra
2006-09-12 15:25 ` [PATCH 19/20] mm: a process flags to avoid blocking allocations Peter Zijlstra
2006-09-12 15:25 ` [PATCH 18/20] netlink: add SOCK_VMIO support to AF_NETLINK Peter Zijlstra
2006-09-12 15:25 ` [PATCH 10/20] mm: block device swap notification Peter Zijlstra
2006-09-12 15:25 ` [PATCH 20/20] iscsi: support for swapping over iSCSI Peter Zijlstra
2006-09-13 20:50 ` Mike Christie
2006-09-14 6:17 ` Peter Zijlstra
2006-09-14 19:22 ` Mike Christie
2006-09-14 20:35 ` Peter Zijlstra
2006-09-14 20:46 ` Peter Zijlstra
2006-09-14 21:09 ` Mike Christie
2006-09-14 21:28 ` Mike Christie
2006-09-14 21:00 ` Mike Christie
2006-09-14 21:03 ` Mike Christie [this message]
2006-09-14 21:18 ` Peter Zijlstra
2006-09-12 15:25 ` [PATCH 02/20] net: vm deadlock avoidance core Peter Zijlstra
2006-09-12 15:25 ` [PATCH 03/20] mm: add support for non block device backed swap files Peter Zijlstra
2006-09-12 15:25 ` [PATCH 14/20] uml: enable scsi and add iscsi config Peter Zijlstra
2006-09-12 15:25 ` [PATCH 09/20] nfs: make swap on NFS robust Peter Zijlstra
2006-09-12 15:25 ` [PATCH 05/20] uml: rename arch/um remove_mapping() Peter Zijlstra
2006-09-12 15:25 ` [PATCH 12/20] nbd: limit blk_queue Peter Zijlstra
2006-09-12 22:47 ` Jens Axboe
2006-09-12 15:25 ` [PATCH 13/20] nbd: use swapdev hook to make swap deadlock free Peter Zijlstra
2006-09-12 15:25 ` [PATCH 01/20] mm: serialize access to min_free_kbytes Peter Zijlstra
2006-09-12 15:25 ` [PATCH 15/20] iscsi: kernel side tcp connect Peter Zijlstra
2006-09-12 15:25 ` [PATCH 11/20] nbd: request_fn fixup Peter Zijlstra
2006-09-12 22:47 ` Jens Axboe
2006-09-13 0:21 ` Jeff Garzik
2006-09-13 6:14 ` Jens Axboe
2006-09-12 15:25 ` [PATCH 04/20] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2006-09-12 15:25 ` [PATCH 17/20] scsi: propagate the swapdev hook into the scsi stack Peter Zijlstra
2006-09-12 15:25 ` [PATCH 07/20] nfs: add a comment explaining the use of PG_private in the NFS client Peter Zijlstra
2006-09-12 15:25 ` [PATCH 06/20] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2006-09-12 16:37 ` [PATCH 00/20] vm deadlock avoidance for NFS, NBD and iSCSI (take 7) Linus Torvalds
2006-09-12 23:58 ` Nate Diller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4509C38B.3000808@cs.wisc.edu \
--to=michaelc@cs.wisc.edu \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@osdl.org \
--cc=davem@davemloft.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=phillips@google.com \
--cc=riel@redhat.com \
--cc=torvalds@osdl.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox