From: Vegard Nossum Date: Thu, 13 Oct 2016 07:20:07 GMT Subject: Re: Huge performance bottleneck reading packs Message-ID: In-Reply-To: <20161012230143.5kxcmtityaasra5j@sigill.intra.peff.net> On 10/13/2016 01:01 AM, Jeff King wrote: > On Thu, Oct 13, 2016 at 12:30:52AM +0200, Vegard Nossum wrote: > >> However, the commit found by 'git blame' above appears just fine to me, >> I haven't been able to spot a bug in it. >> >> A closer inspection reveals the problem to really be that this is an >> extremely hot path with more than -- holy cow -- 4,106,756,451 >> iterations on the 'packed_git' list for a single 'git fetch' on my >> repository. I'm guessing the patch above just made the inner loop >> ever so slightly slower. >> >> My .git/objects/pack/ has ~2088 files (1042 idx files, 1042 pack files, >> and 4 tmp_pack_* files). > > Yeah. I agree that the commit you found makes the check a little more > expensive, but I think the root of the problem is calling > prepare_packed_git_one many times. This _should_ happen once for each > pack at program startup, and possibly again if we need to re-scan the > pack directory to account for racing with a simultaneous repack. > > The latter is generally triggered when we fail to look up an object we > expect to exist. So I'd suspect 45e8a74 (has_sha1_file: re-check pack > directory before giving up, 2013-08-30) is playing a part. We dealt with > that to some degree in 0eeb077 (index-pack: avoid excessive re-reading > of pack directory, 2015-06-09), but it would not surprise me if there is > another spot that needs similar treatment. > > Does the patch below help? Yes, ~2m10s -> ~1m25s when I test a git fetch this morning (the other variation in time may be due to different CPU usage by other programs, but I ran with/without the patch multiple times and the difference is consistent). Thanks, Vegard