| To: | Christoph Hellwig <hch@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH 1/4] xfs: do not update xa_last_pushed_lsn for locked items |
| From: | Alex Elder <aelder@xxxxxxx> |
| Date: | Fri, 7 Oct 2011 17:18:05 -0500 |
| Cc: | <xfs@xxxxxxxxxxx>, Stefan Priebe <s.priebe@xxxxxxxxxxxx> |
| In-reply-to: | <20111006183549.399127499@xxxxxxxxxxxxxxxxxxxxxx> |
| References: | <20111006183257.036884724@xxxxxxxxxxxxxxxxxxxxxx> <20111006183549.399127499@xxxxxxxxxxxxxxxxxxxxxx> |
| Reply-to: | <aelder@xxxxxxx> |
On Thu, 2011-10-06 at 14:32 -0400, Christoph Hellwig wrote: > If an item was locked we should not update xa_last_pushed_lsn and thus skip > it when restarting the AIL scan as we need to be able to lock and write it > out as soon as possible. Otherwise heavy lock contention might starve AIL > pushing too easily, especially given the larger backoff once we moved > xa_last_pushed_lsn all the way to the target lsn. > > Signed-off-by: Christoph Hellwig <hch@xxxxxx> > Reported-by: Stefan Priebe <s.priebe@xxxxxxxxxxxx> > Tested-by: Stefan Priebe <s.priebe@xxxxxxxxxxxx> I remember wondering about that one line during review, but I believe I reasoned something about the "already being reflushed or relogged" made it the right thing to do. Your explanation makes sense though (but what do I know, the original code seemed OK too...). Reviewed-by: Alex Elder <aelder@xxxxxxx> |
| Previous by Date: | [PATCH] Xfstest: make 218 support btrfs, Liu Bo |
|---|---|
| Next by Date: | Re: [PATCH 2/4] xfs: force the log if we encounter pinned buffers in .iop_pushbuf, Alex Elder |
| Previous by Thread: | [PATCH 1/4] xfs: do not update xa_last_pushed_lsn for locked items, Christoph Hellwig |
| Next by Thread: | Re: [PATCH 1/4] xfs: do not update xa_last_pushed_lsn for locked items, Dave Chinner |
| Indexes: | [Date] [Thread] [Top] [All Lists] |