From: Benny Halevy <bhalevy@panasas.com>
To: quanli gui <gqlxj1987@gmail.com>
Cc: linux-pnfs <linux-nfs@vger.kernel.org>
Subject: Re: [pnfs] pnfs first write has very long delay
Date: Thu, 21 Oct 2010 18:48:40 +0200 [thread overview]
Message-ID: <4CC06EE8.7010705@panasas.com> (raw)
In-Reply-To: <AANLkTi=XSSM5+wmCrVzQrZF8rA81OLqDO_dMzUqwHc7g@mail.gmail.com>
On 2010-10-21 14:03, quanli gui wrote:
> When pnfs is mount on the client, I write a file to the mount dir by the
> first time. It must wait a very long time until the pnfs complete the write.
> When the operation waited, I dmesg the operation information. Find that
> NFS: 0 initiated write call (req 0:13/200809, 3035 bytes @ offset 49152)
> --> nfs4_setup_sequence clp c450a800 session c450ac00 sr_slotid 128
> --> nfs41_setup_sequence
> --> nfs4_find_slot used_slots=0007 highest_used=2 max_slots=16
> <-- nfs4_find_slot used_slots=000f highest_used=3 slotid=3
> <-- nfs41_setup_sequence slotid=3 seqid=1
> <-- nfs4_setup_sequence status=0
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=1 slotid=3 max_slotid=3
> cache_this=1
> filelayout_write_call_done new off 40960 orig offset 40960
> pnfs_writeback_done: Begin (status -10008)
What kind of DS are you using?
The 10008 error means that the DS returned NFS4ERR_DELAY
so we need to understand why that happened.
Benny
> put_lseg: lseg ce417e40 ref 3 valid 1
> NFS: 34 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> pnfs_writepages End (trypnfs:0)
> filelayout_write_call_done new off 49152 orig offset 49152
> pnfs_writeback_done: Begin (status -10008)
> put_lseg: lseg ce417e40 ref 2 valid 1
> NFS: 35 nfs_writeback_done (status -10008 count 3035)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> nfs4_renew_state: start
> nfs4_renew_state: failed to call renewd. Reason: lease not expired
> nfs4_renew_state: requeueing work. Lease period = 56
> nfs4_renew_state: done
> nfs4_renew_state: start
> nfs4_renew_state: failed to call renewd. Reason: lease not expired
> nfs4_renew_state: requeueing work. Lease period = 56
> nfs4_renew_state: done
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=2 slotid=0 max_slotid=3
> cache_this=1
> NFS: 29 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=2 slotid=0 max_slotid=2
> cache_this=1
> NFS: 30 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=2 slotid=1 max_slotid=3
> cache_this=1
> NFS: 31 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=2 slotid=1 max_slotid=2
> cache_this=1
> NFS: 32 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=2 slotid=2 max_slotid=3
> cache_this=1
> NFS: 33 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=2 slotid=2 max_slotid=2
> cache_this=1
> NFS: 34 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=2 slotid=3 max_slotid=3
> cache_this=1
> NFS: 35 nfs_writeback_done (status -10008 count 3035)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> nfs4_renew_state: start
> nfs4_renew_state: failed to call renewd. Reason: lease not expired
> nfs4_renew_state: requeueing work. Lease period = 37
> nfs4_renew_state: done
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=3 slotid=0 max_slotid=3
> cache_this=1
> NFS: 29 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=3 slotid=0 max_slotid=2
> cache_this=1
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=3 slotid=1 max_slotid=3
> cache_this=1
> NFS: 30 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> NFS: 31 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=3 slotid=1 max_slotid=2
> cache_this=1
> NFS: 32 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=3 slotid=2 max_slotid=3
> cache_this=1
> NFS: 33 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=3 slotid=2 max_slotid=2
> cache_this=1
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=3 slotid=3 max_slotid=3
> cache_this=1
> NFS: 34 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> NFS: 35 nfs_writeback_done (status -10008 count 3035)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=4 slotid=0 max_slotid=3
> cache_this=1
> NFS: 29 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=4 slotid=0 max_slotid=2
> cache_this=1
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=4 slotid=1 max_slotid=3
> cache_this=1
> NFS: 30 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> NFS: 31 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=4 slotid=1 max_slotid=2
> cache_this=1
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=4 slotid=2 max_slotid=3
> cache_this=1
> NFS: 32 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> NFS: 33 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> encode_compound: tag=
> encode_sequence: sessionid=1287677253:2:2:0 seqid=4 slotid=3 max_slotid=3
> cache_this=1
> encode_compound: tag=
> encode_sequence: sessionid=1287677247:2:2:0 seqid=4 slotid=2 max_slotid=2
> cache_this=1
> NFS: 35 nfs_writeback_done (status -10008 count 3035)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> NFS: 34 nfs_writeback_done (status -10008 count 8192)
> pnfs4_write_done DS write
> <-- pnfs4_write_done status= -11
> I don't know why so many pnfs_write_done() return -11 only for the first
> write. But after the first write, I write files again. This time the time of
> the operation is OK. Please tell me why this thing happen.
>
next parent reply other threads:[~2010-10-21 16:48 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <AANLkTi=XSSM5+wmCrVzQrZF8rA81OLqDO_dMzUqwHc7g@mail.gmail.com>
2010-10-21 16:48 ` Benny Halevy [this message]
2010-10-21 17:08 ` [pnfs] pnfs first write has very long delay William A. (Andy) Adamson
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=4CC06EE8.7010705@panasas.com \
--to=bhalevy@panasas.com \
--cc=gqlxj1987@gmail.com \
--cc=linux-nfs@vger.kernel.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